└── README.md


/README.md:
--------------------------------------------------------------------------------
  1 | # Awesome Meta-Learning Papers [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)
  2 | 
  3 | A summary of meta learning papers based on realm. Sorted by submission date on arXiv.
  4 | 
  5 | # [Topics]()
  6 | 
  7 | * [Survey](#Survey)
  8 | * [Few-shot learning](#Few-shot-learning)
  9 | * [Reinforcement Learning](#Reinforcement-learning)
 10 | * [AutoML](#AutoML)
 11 | * [Task-dependent Methods](#Task-dependent)
 12 | * [Data Aug & Reg](#Data-Aug-&-Reg)
 13 | * [Lifelong learning](#Lifelong-learning)
 14 | * [Domain generalization](#Domain-generalization)     
 15 | * [Neural process](#Neural-process)
 16 | * [Configuration transfer (Adaptation， Hyperparameter Opt)](#Configuration-transfer)
 17 | * [Model compression](#Model-compression)
 18 | * [Kernel learning](#Kernel-learning)
 19 | * [Robustness](#Robustness)
 20 | * [Bayesian inference](#Bayesian-inference)
 21 | * [Optimization](#Optimization)
 22 | * [Theory](#Theory)
 23 | 
 24 | ## [Survey]()
 25 | Meta-Learning in Neural Networks: A Survey [[paper](https://arxiv.org/abs/2004.05439)]
 26 |   - Timothy Hospedales, Antreas Antoniou, Paul Micaelli, Amos Storkey 
 27 | 
 28 | Meta-Learning[[paper](https://www.ml4aad.org/wp-content/uploads/2018/09/chapter2-metalearning.pdf)]
 29 |   - Joaquin Vanschoren
 30 | 
 31 | Meta-Learning: A Survey [[paper](https://arxiv.org/pdf/1810.03548.pdf)]
 32 |   - Joaquin Vanschoren
 33 | 
 34 | Meta-learners’ learning dynamics are unlike learners’  [[paper](https://arxiv.org/pdf/1905.01320.pdf)]
 35 |   - Neil C. Rabinowitz
 36 | 
 37 | ## [Few-shot learning]()
 38 | 
 39 | Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification [[paper](https://arxiv.org/abs/2204.04567)]
 40 |   - Jiangtao Xie, Fei Long, Jiaming Lv, Qilong Wang, Peihua Li --CVPR 2022
 41 | 
 42 | Learning Prototype-oriented Set Representations for Meta-Learning [[paper](https://openreview.net/forum?id=WH6u2SvlLp4)]
 43 |   - Dan dan Guo, Long Tian, Minghe Zhang, Mingyuan Zhou, Hongyuan Zha --ICLR 2022
 44 | 
 45 | On the Role of Pre-training for Meta Few-Shot Learning [[paper](https://openreview.net/forum?id=TwkEGci1Y-)]
 46 |   - Chia-You Chen, Hsuan-Tien Lin, Gang Niu, Masashi Sugiyama, --arXiv 2021
 47 | 
 48 | BOIL: Towards Representation Change for Few-shot Learning [[paper](https://openreview.net/forum?id=umIdUL8rMH)]
 49 |   - Jaehoon Oh, Hyungjun Yoo, ChangHwan Kim, Se-Young Yun --ICLR 2021
 50 | 
 51 | On Episodes, Prototypical Networks, and Few-Shot Learning [[paper](https://openreview.net/pdf?id=bJaZ8leI0QJ)]
 52 |   - Steinar Laenen, Luca Bertinetto --NeurIPS 2021
 53 | 
 54 | Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels [[paper](https://arxiv.org/abs/1910.05199)]
 55 |   - Massimiliano Patacchiola, Jack Turner, Elliot J. Crowley, Michael O'Boyle, Amos Storkey --NeurIPS 2020
 56 | 
 57 | Laplacian Regularized Few-Shot Learning [[paper](http://proceedings.mlr.press/v119/ziko20a/ziko20a.pdf)]
 58 |   - Imtiaz Masud Ziko, Jose Dolz, Eric Granger, Ismail Ben Ayed --ICML 2020
 59 | 
 60 | Few-shot Sequence Learning with Transformer 
 61 |   -  Lajanugen Logeswaran, Ann Lee, Myle Ott, Honglak Lee, Marc´Aurelio Ranzato, Arthur Szlam --NeurIPS 2020 #Meta-Learning
 62 | 
 63 | Prototype Rectification for Few-Shot Learning [[paper](https://arxiv.org/abs/1911.10713)]
 64 |   - Jinlu Liu, Liang Song, Yongqiang Qin --ECCV 2020
 65 | 
 66 | When Does Self-supervision Improve Few-shot Learning? [[paper](https://arxiv.org/pdf/1910.03560.pdf)]
 67 |   - Jong-Chyi Su, Subhransu Maji, Bharath Hariharan --ECCV 2020
 68 |   
 69 | Cross Attention Network for Few-shot Classification [[paper](https://arxiv.org/abs/1910.07677)]
 70 |   - Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen --NeurIPS 2019
 71 | 
 72 | Learning to Learn via Self-Critique [[paper](https://arxiv.org/abs/1905.10295)]
 73 |   - Antreas Antoniou, Amos Storkey  --NeurIPS 2019
 74 |   
 75 | Learning from the Past: Continual Meta-Learning with Bayesian Graph Neural Networks [[paper](https://arxiv.org/abs/1911.04695)]
 76 |   - Yadan Luo, Zi Huang, Zheng Zhang, Ziwei Wang, Mahsa Baktashmotlagh, Yang Yang --AAAI 2020
 77 | 
 78 | Few-Shot Learning with Global Class Representations [[paper](https://arxiv.org/pdf/1908.05257.pdf)]
 79 |   - Tiange Luo, Aoxue Li, Tao Xiang, Weiran Huang, Liwei Wang  --ICCV 2019
 80 | 
 81 | TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning [[paper](https://arxiv.org/pdf/1905.06549.pdf)]
 82 |   - Sung Whan Yoon, Jun Seo, Jaekyun Moon --ICML 2019
 83 | 
 84 | Learning to Learn with Conditional Class Dependencies  [[paper](https://openreview.net/pdf?id=BJfOXnActQ)]
 85 |   - Xiang Jiang, Mohammad Havaei, Farshid Varno, Gabriel Chartrand, Nicolas Chapados, Stan Matwin --ICLR 2019
 86 |  
 87 |  Finding Task-Relevant Features for Few-Shot Learning by Category Traversal [[paper](https://arxiv.org/pdf/1905.11116.pdf)]
 88 |   - Hongyang Li, David Eigen, Samuel Dodge, Matthew Zeiler, Xiaogang Wang --CVPR 2019
 89 |  
 90 | TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning [[paper](https://arxiv.org/abs/1904.05967)]
 91 |   - Xin Wang, Fisher Yu, Ruth Wang, Trevor Darrell, Joseph E. Gonzalez --CVPR 2019
 92 | 
 93 | Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images [[paper](https://arxiv.org/abs/1904.08482)]
 94 |   - Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon --CVPR 2019
 95 | 
 96 | LCC: Learning to Customize and Combine Neural Networks for Few-Shot Learning [[paper](https://arxiv.org/pdf/1904.08479.pdf)]
 97 |   - Yaoyao Liu, Qianru Sun, An-An Liu, Yuting Su, Bernt Schiele, Tat-Seng Chua --CVPR 2019
 98 | 
 99 | Meta-Learning with Differentiable Convex Optimization [[paper](https://arxiv.org/abs/1904.03758)]
100 |   - Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran, Stefano Soatto --CVPR 2019
101 | 
102 | Dense Classification and Implanting for Few-Shot Learning [[paper](https://arxiv.org/pdf/1903.05050.pdf)]
103 |   - Yann Lifchitz, Yannis Avrithis, Sylvaine Picard, Andrei Bursuc --CVPR 2019
104 | 
105 | Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
106 |   - Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol, Hugo Larochelle  -- arXiv 2019
107 |  
108 | Adaptive Cross-Modal Few-Shot Learning [[paper](https://arxiv.org/pdf/1902.07104.pdf)]
109 |   - Chen Xing, Negar Rostamzadeh, Boris N. Oreshkin, Pedro O. Pinheiro --arXiv 2019
110 | 
111 | Meta-Learning with Latent Embedding Optimization [[paper](https://arxiv.org/abs/1807.05960)]
112 |   - Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, Raia Hadsell -- ICLR 2019
113 |  
114 | A Closer Look at Few-shot Classification [[paper](https://arxiv.org/abs/1904.04232)]
115 |   - Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, Jia-Bin Huang  -- ICLR 2019
116 |  
117 | Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning [[paper](https://arxiv.org/pdf/1805.10002.pdf)]
118 |   - Yanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Eunho Yang, Sung Ju Hwang, Yi Yang -- ICLR 2019
119 | 
120 | Dynamic Few-Shot Visual Learning without Forgetting [[paper](https://arxiv.org/pdf/1804.09458v1.pdf)]
121 |   - Spyros Gidaris, Nikos Komodakis --arXiv 2019
122 | 
123 | Meta Learning with Lantent Embedding Optimization [[paper](https://openreview.net/pdf?id=BJgklhAcK7)]
124 |   - Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero & Raia Hadsell --ICLR 2019
125 | 
126 | Adaptive Posterior Learning: few-shot learning with a surprise-based memory module
127 |   - Tiago Ramalho, Marta Garnelo --ICLR 2019
128 | 
129 | How To Train Your MAML [[paper](https://arxiv.org/pdf/1810.09502v1.pdf)]
130 |   - Antreas Antoniou, Harrison Edwards, Amos Storkey -- ICLR 2019
131 | 
132 | TADAM: Task dependent adaptive metric for improved few-shot learning [[paper](https://arxiv.org/abs/1805.10123)]
133 |   - Boris N. Oreshkin, Pau Rodriguez, Alexandre Lacoste --arXiv 2019
134 | 
135 | Few-shot Learning with Meta Metric Learners
136 |   - Yu Cheng, Mo Yu, Xiaoxiao Guo, Bowen Zhou --NIPS 2017 workshop on Meta-Learning
137 | 
138 | Learning Embedding Adaptation for Few-Shot Learning [[paper](https://arxiv.org/pdf/1812.03664.pdf)]
139 |   - Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, Fei Sha --arXiv 2018
140 | 
141 | Meta-Transfer Learning for Few-Shot Learning [[paper](https://arxiv.org/pdf/1812.02391.pdf)]
142 |   - Qianru Sun, Yaoyao Liu, Tat-Seng Chu, Bernt Schiele -- arXiv 2018
143 | 
144 | Task-Agnostic Meta-Learning for Few-shot Learning
145 |   - Muhammad Abdullah Jamal, Guo-Jun Qi, and Mubarak Shah  --arXiv 2018
146 | 
147 | Few-Shot Learning with Graph Neural Networks [[paper](https://arxiv.org/abs/1711.04043)]
148 |   - Victor Garcia, Joan Bruna -- ICLR 2018
149 | 
150 | Prototypical Networks for Few-shot Learning [[paper](https://arxiv.org/pdf/1703.05175.pdf)]
151 |   - Jake Snell, Kevin Swersky, Richard S. Zemel -- NIPS 2017
152 |   
153 | Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks [[paper](https://arxiv.org/abs/1703.03400)]
154 |   - Chelsea Finn, Pieter Abbeel, Sergey Levine -- ICML 2016
155 | 
156 | ### Large scale dataset
157 | Image Deformation Meta-Networks for One-Shot Learning [[paper](https://arxiv.org/pdf/1905.11641.pdf)]
158 |   - Zitian Chen, Yanwei Fu, Yu-Xiong Wang, Lin Ma, Wei Liu, Martial Hebert --CVPR 2019
159 | 
160 | ### Imbalance class
161 | Balanced Meta-Softmax for Long-Tailed Visual Recognition [[paper](https://arxiv.org/abs/2007.10740)]
162 |   - Jiawei Ren, Cunjun Yu, Shunan Sheng, Xiao Ma, Haiyu Zhao, Shuai Yi, Hongsheng Li --NeurIPS 2020
163 | 
164 | MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler [[paper](https://proceedings.neurips.cc/paper/2020/file/a64bd53139f71961c5c31a9af03d775e-Paper.pdf)]
165 |   - Zhining Liu, Pengfei Wei, Jing Jiang, Wei Cao, Jiang Bian, Yi Chang --NeurIPS 2019
166 | 
167 | Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks [[paper](https://openreview.net/pdf?id=rkeZIJBYvr)]
168 |   - Donghyun Na, Hae Beom Lee, Hayeon Lee, Saehoon Kim, Minseop Park, Eunho Yang, Sung Ju Hwang --ICLR 2020
169 | 
170 | Meta-weight-net: Learning an explicit mapping for sample weighting [[paper](https://papers.nips.cc/paper/2019/file/e58cc5ca94270acaceed13bc82dfedf7-Paper.pdf)]
171 |   - Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, Deyu Meng --NeurIPS 2019
172 | 
173 | Learning to Reweight Examples for Robust Deep Learning [[paper](https://arxiv.org/pdf/1803.09050.pdf)]
174 |   - Mengye Ren, Wenyuan Zeng, Bin Yang, Raquel Urtasun --ICML 2018
175 | 
176 | Learning to Model the Tail [[paper](https://papers.nips.cc/paper/7278-learning-to-model-the-tail.pdf)]
177 |   - Yu-Xiong Wang, Deva Ramanan, Martial Hebert --NeurIPS 2017
178 | 
179 | ### Video retargeting
180 | MetaPix: Few-Shot Video Retargeting [[paper](https://openreview.net/forum?id=SJx1URNKwH)]
181 |   - Jessica Lee, Deva Ramanan, Rohit Girdhar --ICLR 2020
182 | 
183 | ### Object detection
184 | Few-shot Object Detection via Feature Reweighting [[paper](https://arxiv.org/abs/1812.01866)]
185 |   - Bingyi Kang, Zhuang Liu, Xin Wang, Fisher Yu, Jiashi Feng, Trevor Darrell --ICCV 2019
186 | 
187 | ### Segmentation
188 | PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment [[paper](https://arxiv.org/abs/1908.06391)]
189 |   - Kaixin Wang, Jun Hao Liew, Yingtian Zou, Daquan Zhou, Jiashi Feng --ICCV 2019
190 | 
191 | ### NLP
192 | Meta-Learning for Few-Shot NMT Adaptation [[paper](https://arxiv.org/abs/2004.02745)]
193 |   - Amr Sharaf, Hany Hassan, Hal Daumé III --arXiv 2020
194 | 
195 | Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks [[paper](https://arxiv.org/pdf/1911.03863.pdf)]
196 |   - Trapit Bansal, Rishikesh Jha, Andrew McCallum  --arXiv 2020
197 | 
198 | Compositional generalization through meta sequence-to-sequence learning [[paper](https://arxiv.org/abs/1906.05381)]
199 |   - Brenden M. Lake  --NeurIPS 2019
200 | 
201 | Few-Shot Representation Learning for Out-Of-Vocabulary Words [[paper](https://arxiv.org/abs/1907.00505)]
202 |   - Ziniu Hu, Ting Chen, Kai-Wei Chang, Yizhou Sun --ACL 2019
203 | 
204 | 
205 | ## Reinforcement learning
206 | 
207 | Offline Meta-Reinforcement Learning with Online Self-Supervision [[paper](https://arxiv.org/abs/2107.03974)]
208 |   - Vitchyr Pong, Ashvin Nair, Laura Smith, Catherine Huang, Sergey Levine  --ICML 2022
209 | 
210 | System-Agnostic Meta-Learning for MDP-based Dynamic Scheduling via Descriptive Policy [[paper](https://arxiv.org/abs/2201.07051)]
211 |   - Lee, Hyun-Suk --AISTATS 2022
212 | 
213 | Meta Learning MDPs with Linear Transition Models [[paper](https://arxiv.org/abs/2201.08732)]
214 |   - Müller, Robert ; Pacchiano, Aldo --AISTATS 2022
215 | 
216 | CoMPS: Continual Meta Policy Search [[paper](https://openreview.net/forum?id=PVJ6j87gOHz)]
217 |   - Glen Berseth, Zhiwei Zhang, Grace Zhang, Chelsea Finn, Sergey Levine --ICLR 2022
218 | 
219 | Modeling and Optimization Trade-off in Meta-learning [[paper](https://proceedings.neurips.cc/paper/2020/hash/7fc63ff01769c4fa7d9279e97e307829-Abstract.html)]
220 |   - Katelyn Gao, Ozan Sener --NeurIPS 2020
221 | 
222 | Information-theoretic Task Selection for Meta-Reinforcement Learning [[paper](https://arxiv.org/abs/2011.01054)]
223 |   - Ricardo Luna Gutierrez, Matteo Leonetti --NeurIPS 2020
224 | 
225 | On the Global Optimality of Model-Agnostic Meta-Learning: Reinforcement Learning and Supervised Learning [[paper](https://proceedings.icml.cc/static/paper_files/icml/2020/1816-Paper.pdf)]
226 |   - Lingxiao Wang, Qi Cai, Zhuoyan Yang, Zhaoran Wang --PMLR 2020
227 | 
228 | Generalized Reinforcement Meta Learning for Few-Shot Optimization [[paper](https://arxiv.org/abs/2005.01246)]
229 |   - Raviteja Anantha, Stephen Pulman, Srinivas Chappidi --ICML 2020
230 | 
231 | VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning [[paper](https://openreview.net/forum?id=Hkl9JlBYvr)]
232 |   - Luisa Zintgraf, Kyriacos Shiarlis, Maximilian Igl, Sebastian Schulze, Yarin Gal, Katja Hofmann, Shimon Whiteson --ICLR 2020
233 | 
234 | Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives [[paper](https://openreview.net/forum?id=ryxgJTEYDr)]
235 |   - Anirudh Goyal, Shagun Sodhani, Jonathan Binas, Xue Bin Peng, Sergey Levine, Yoshua Bengio --ICLR 2020
236 | 
237 | Meta-learning curiosity algorithms [[paper](https://openreview.net/pdf?id=BygdyxHFDS)]
238 |   - Ferran Alet*, Martin F. Schneider*, Tomas Lozano-Perez, Leslie Pack Kaelbling --ICLR 2020
239 | 
240 | Meta-Q-Learning [[paper](https://openreview.net/forum?id=SJeD3CEFPH)]
241 |   - Rasool Fakoor, Pratik Chaudhari, Stefano Soatto, Alexander J. Smola --ICLR 2020
242 |   
243 | Guided Meta-Policy Search [[paper](https://arxiv.org/abs/1904.00956)]
244 |   - Russell Mendonca, Abhishek Gupta, Rosen Kralev, Pieter Abbeel, Sergey Levine, Chelsea Finn
245 | 
246 | ## AutoML
247 | 
248 | Learning meta-features for AutoML [[paper](https://openreview.net/forum?id=DTkEfj0Ygb8)]
249 |   - Herilalaina Rakotoarison, Louisot Milijaona, Andry RASOANAIVO, Michele Sebag, Marc Schoenauer --ICLR 2022
250 | 
251 | Towards Fast Adaptation of Neural Architectures with Meta Learning [[paper](https://openreview.net/forum?id=r1eowANFvr)]
252 |   - Dongze Lian, Yin Zheng, Yintao Xu, Yanxiong Lu, Leyu Lin, Peilin Zhao, Junzhou Huang, Shenghua Gao --ICLR 2020
253 | 
254 | Graph HyperNetworks for Neural Architecture Search [[paper](https://arxiv.org/abs/1810.05749)]
255 |   - Chris Zhang, Mengye Ren, Raquel Urtasun --ICLR 2019
256 | 
257 | Fast Task-Aware Architecture Inference
258 |   - Efi Kokiopoulou, Anja Hauth, Luciano Sbaiz, Andrea Gesmundo, Gabor Bartok, Jesse Berent --arXiv 2019
259 | 
260 | Bayesian Meta-network Architecture Learning
261 |   - Albert Shaw, Bo Dai, Weiyang Liu, Le Song --arXiv 2018
262 |   
263 | ## Task-dependent
264 | 
265 | Meta-Learning with Fewer Tasks through Task Interpolation [[paper](https://openreview.net/forum?id=ajXWF7bVR8d)]
266 |   - Huaxiu Yao, Linjun Zhang, Chelsea Finn --ICLR 2022
267 | 
268 | Meta-Regularization by Enforcing Mutual-Exclusiveness [[paper](https://arxiv.org/abs/2101.09819)]
269 |   - Edwin Pan, Pankaj Rajak, Shubham Shrivastava --arXiv 2021
270 | 
271 | Task-Robust Model-Agnostic Meta-Learning [[paper](https://papers.nips.cc/paper/2020/file/da8ce53cf0240070ce6c69c48cd588ee-Paper.pdf)]
272 |   - Liam Collins, Aryan Mokhtari, Sanjay Shakkottai --NeurIPS 2020
273 | 
274 | Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation [[paper](https://arxiv.org/abs/1910.13616)]
275 |   - Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim --NeurIPS 2019
276 | 
277 | Meta-Learning with Warped Gradient Descent [[paper](https://arxiv.org/pdf/1909.00025.pdf)]
278 |   - Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Hujun Yin, Raia Hadsell --arXiv 2019
279 | 
280 | TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning [[paper](https://arxiv.org/abs/1904.05967)]
281 |   - Xin Wang, Fisher Yu, Ruth Wang, Trevor Darrell, Joseph E. Gonzalez --CVPR 2019
282 | 
283 | TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning [[paper](https://arxiv.org/pdf/1905.06549.pdf)]
284 |   - Sung Whan Yoon, Jun Seo, Jaekyun Moon --ICML 2019
285 | 
286 | Meta-Learning with Latent Embedding Optimization [[paper](https://arxiv.org/abs/1807.05960)]
287 |   - Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, Raia Hadsell -- ICLR 2019
288 | 
289 | Fast Task-Aware Architecture Inference
290 |   - Efi Kokiopoulou, Anja Hauth, Luciano Sbaiz, Andrea Gesmundo, Gabor Bartok, Jesse Berent --arXiv 2019
291 | 
292 | Task2Vec: Task Embedding for Meta-Learning
293 |   - Alessandro Achille, Michael Lam, Rahul Tewari, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes, Stefano Soatto, Pietro Perona--arXiv 2019
294 | 
295 | TADAM: Task dependent adaptive metric for improved few-shot learning
296 |   - Boris N. Oreshkin, Pau Rodriguez, Alexandre Lacoste --arXiv 2019
297 |   
298 | MetaReg: Towards Domain Generalization using Meta-Regularization [[paper](https://papers.nips.cc/paper/7378-metareg-towards-domain-generalization-using-meta-regularization.pdf)]
299 |   - Yogesh Balaji, Swami Sankaranarayanan -- NIPS 2018
300 | 
301 | ### Heterogeneous task
302 | Statistical Model Aggregation via Parameter Matching [[paper]](https://arxiv.org/pdf/1911.00218.pdf)
303 |   - Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh, Kristjan Greenewald, Trong Nghia Hoang --NeurIPS 2019
304 | 
305 | Hierarchically Structured Meta-learning [[paper](https://arxiv.org/pdf/1905.05301.pdf)]
306 |   - Huaxiu Yao, Ying Wei, Junzhou Huang, Zhenhui Li --ICML 2019
307 | 
308 | Hierarchical Meta Learning [[paper](https://arxiv.org/abs/1904.09081)]
309 |   - Yingtian Zou, Jiashi Feng  --arXiv 2019
310 | 
311 | 
312 | ## Data Aug & Reg
313 | MetAug: Contrastive Learning via Meta Feature Augmentation [[paper](https://arxiv.org/abs/2203.05119)]
314 |   - Jiangmeng Li, Wenwen Qiang, Changwen Zheng, Bing Su, Hui Xiong --ICML 2022
315 | 
316 | MetaInfoNet: Learning Task-Guided Information for Sample Reweighting [[paper](https://arxiv.org/abs/2012.05273)]
317 |   - Hongxin Wei, Lei Feng, Rundong Wang, Bo An --arXiv 2020
318 | 
319 | Meta Dropout: Learning to Perturb Latent Features for Generalization [[paper](https://openreview.net/forum?id=BJgd81SYwr)]
320 |   - Hae Beom Lee, Taewook Nam, Eunho Yang, Sung Ju Hwang --ICLR 2020
321 | 
322 | Learning to Reweight Examples for Robust Deep Learning [[paper](https://arxiv.org/abs/1803.09050)]
323 |   - Mengye Ren, Wenyuan Zeng, Bin Yang, Raquel Urtasun --ICML 2018
324 | 
325 | 
326 | ## Lifelong learning
327 | 
328 | Optimizing Reusable Knowledge for Continual Learning via Metalearning [[paper](https://arxiv.org/abs/2106.05390)]
329 |   - Julio Hurtado, Alain Raymond-Saez, Alvaro Soto --NeurIPS 2021
330 | 
331 | Learning where to learn: Gradient sparsity in meta and continual learning [[paper](https://arxiv.org/pdf/2110.14402.pdf)]
332 |   - Johannes von Oswald, Dominic Zhao, Seijin Kobayashi, Simon Schug, Massimo Caccia, Nicolas Zucchet, João Sacramento --NeurIPS 2021
333 | 
334 | Online-Within-Online Meta-Learning [[paper](https://papers.nips.cc/paper/9468-online-within-online-meta-learning)]
335 |   - Giulia Denevi, Dimitris Stamos, Carlo Ciliberto, Massimiliano Pontil
336 |   
337 | Reconciling meta-learning and continual learning with online mixtures of tasks [[paper](https://arxiv.org/abs/1812.06080)]
338 |   - Ghassen Jerfel, Erin Grant, Thomas L. Griffiths, Katherine Heller  --NeurIPS 2019
339 | 
340 | Meta-Learning Representations for Continual Learning [[paper](https://arxiv.org/abs/1905.12588)]
341 |   - Khurram Javed, Martha White  --NeurIPS 2019
342 | 
343 | Online Meta-Learning [[paper](https://arxiv.org/abs/1902.08438)]
344 |   - Chelsea Finn, Aravind Rajeswaran, Sham Kakade, Sergey Levine  --ICML 2019
345 | 
346 | Hierarchically Structured Meta-learning [[paper](https://arxiv.org/pdf/1905.05301.pdf)]
347 |   - Huaxiu Yao, Ying Wei, Junzhou Huang, Zhenhui Li --ICML 2019
348 | 
349 | A Neural-Symbolic Architecture for Inverse Graphics Improved by Lifelong Meta-Learning [[paper](https://arxiv.org/pdf/1905.08910.pdf)]
350 |   - Michael Kissner, Helmut Mayer --arXiv 2019
351 | 
352 | Incremental Learning-to-Learn with Statistical Guarantees [[paper](http://auai.org/uai2018/proceedings/papers/181.pdf)]
353 |   - Giulia Denevi, Carlo Ciliberto, Dimitris Stamos, Massimiliano Pontil --arXiv 2018
354 |   
355 | ## Domain generalization
356 | Meta-learning curiosity algorithms [[paper](https://openreview.net/pdf?id=BygdyxHFDS)]
357 |   - Ferran Alet*, Martin F. Schneider*, Tomas Lozano-Perez, Leslie Pack Kaelbling --ICLR 2020
358 | 
359 | Domain Generalization via Model-Agnostic Learning of Semantic Features [[paper](https://arxiv.org/abs/1910.13580)]
360 |   - Qi Dou, Daniel C. Castro, Konstantinos Kamnitsas, Ben Glocker
361 |   
362 | Learning to Generalize: Meta-Learning for Domain Generalization [[paper](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewFile/16067/16547)]
363 |   - Da Li, Yongxin Yang, Yi-Zhe Song, Timothy M. Hospedales --AAAI 2018
364 | 
365 | ## Bayesian inference
366 | 
367 | Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning [[paper](https://openreview.net/forum?id=FFGDKzLasUa)]
368 |   - Konstantinos Ι. Kalais, Sotirios Chatzis --ICML 2022
369 | 
370 | Meta-Learning with Variational Bayes [[paper](https://arxiv.org/abs/2103.02265)]
371 |   - Lucas D. Lingle --arXiv 2021
372 | 
373 | Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization [[paper](https://openreview.net/forum?id=ryeYpJSKwr)]
374 |   - Michael Volpp, Lukas Froehlich, Kirsten Fischer, Andreas Doerr, Stefan Falkner, Frank Hutter, Christian Daniel --ICLR 2020
375 | 
376 | Bayesian Meta Sampling for Fast Uncertainty Adaptation [[paper](https://openreview.net/forum?id=Bkxv90EKPB)]
377 |   - Zhenyi Wang, Yang Zhao, Ping Yu, Ruiyi Zhang, Changyou Chen --ICLR 2020
378 | 
379 | Meta-Learning Mean Functions for Gaussian Processes [[paper](https://arxiv.org/pdf/1901.08098.pdf)]
380 |   - Vincent Fortuin, Heiko Strathmann, and Gunnar Rätsch --NeurIPS 2019 workshop
381 | 
382 | Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks [[paper](https://openreview.net/pdf?id=rkeZIJBYvr)]
383 |   - Donghyun Na, Hae Beom Lee, Hayeon Lee, Saehoon Kim, Minseop Park, Eunho Yang, Sung Ju Hwang --ICLR 2020
384 | 
385 | Meta-Learning without Memorization [[paper](https://openreview.net/pdf?id=BklEFpEYwS)]
386 |   - Mingzhang Yin, George Tucker, Mingyuan Zhou, Sergey Levine, Chelsea Finn --ICLR 2020
387 | 
388 | Meta-Amortized Variational Inference and Learning [[paper](https://arxiv.org/pdf/1902.01950.pdf)]
389 |   - Mike Wu, Kristy Choi, Noah Goodman, Stefano Ermon  --arXiv 2019
390 | 
391 | Amortized Bayesian Meta-Learning [[paper](https://openreview.net/pdf?id=rkgpy3C5tX)]
392 |   - Sachin Ravi, Alex Beatson --ICLR 2019
393 |   
394 | Neural Processes [[paper](https://arxiv.org/abs/1807.01622)]
395 |   - Marta Garnelo, Jonathan Schwarz, Dan Rosenbaum, Fabio Viola, Danilo J. Rezende, S.M. Ali Eslami, Yee Whye Teh 
396 | 
397 | Meta-Learning Probabilistic Inference For Prediction [[paper](https://arxiv.org/pdf/1805.09921.pdf)]
398 |   - Jonathan Gordon, John Bronskill, Matthias Bauer, Sebastian Nowozin, Richard E. Turner --ICLR 2019
399 | 
400 | Meta-Learning Priors for Efficient Online Bayesian Regression [[paper](https://arxiv.org/abs/1807.08912)]
401 |   - James Harrison, Apoorva Sharma, Marco Pavone --WAFR 2018
402 | 
403 | Probabilistic Model-Agnostic Meta-Learning [[paper](https://arxiv.org/pdf/1806.02817.pdf)]
404 |   - Chelsea Finn, Kelvin Xu, Sergey Levine  --arXiv 2018
405 | 
406 | Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions [[paper](https://arxiv.org/abs/1710.10304)]
407 |   - Scott Reed, Yutian Chen, Thomas Paine, Aäron van den Oord, S. M. Ali Eslami, Danilo Rezende, Oriol Vinyals, Nando de Freitas --ICLR 2018
408 | 
409 | Bayesian Model-Agnostic Meta-Learning [[paper](https://arxiv.org/abs/1806.03836)]
410 |   - Taesup Kim, Jaesik Yoon, Ousmane Dia, Sungwoong Kim, Yoshua Bengio, Sungjin Ahn -- NIPS 2018
411 | 
412 | Meta-learning by adjusting priors based on extended PAC-Bayes theory [[paper](https://arxiv.org/pdf/1711.01244.pdf)]
413 |   - Ron Amit , Ron Meir --ICML 2018
414 | 
415 | ## Neural process
416 | 
417 | Neural Variational Dropout Processes [[paper](https://openreview.net/forum?id=lyLVzukXi08)]
418 |   - Insu Jeon, Youngjin Park, Gunhee Kim --ICLR 2022
419 | 
420 | Neural ODE Processes [[paper](https://arxiv.org/abs/2103.12413)]
421 |   - Alexander Norcliffe, Cristian Bodnar, Ben Day, Jacob Moss, Pietro Liò --ICLR 2021
422 | 
423 | Convolutional Conditional Neural Processes [[paper](https://openreview.net/forum?id=Skey4eBYPS)]
424 |   - Jonathan Gordon, Wessel P. Bruinsma, Andrew Y. K. Foong, James Requeima, Yann Dubois, Richard E. Turner --ICLR 2020
425 | 
426 | Bootstrapping Neural Processes [[paper](https://arxiv.org/pdf/2008.02956.pdf)]
427 |   - Juho Lee, Yoonho Lee, Jungtaek Kim, Eunho Yang, Sung Ju Hwang, Yee Whye Teh --NeurIPS 2020
428 | 
429 | MetaFun: Meta-Learning with Iterative Functional Updates [[paper](http://proceedings.mlr.press/v119/xu20i/xu20i.pdf)]
430 |   - Jin Xu, Jean-Francois Ton, Hyunjik Kim, Adam R. Kosiorek, Yee Whye Teh --ICML 2020
431 | 
432 | Sequential Neural Processes [[paper](https://arxiv.org/abs/1906.10264)]
433 |   - Gautam Singh, Jaesik Yoon, Youngsung Son, Sungjin Ahn --NeurIPS 2019 
434 | 
435 | Neural Processes [[paper](https://arxiv.org/abs/1807.01622)]
436 |   - Marta Garnelo, Jonathan Schwarz, Dan Rosenbaum, Fabio Viola, Danilo J. Rezende, S.M. Ali Eslami, Yee Whye Teh --arXiv 2018
437 | 
438 | Conditional Neural Processes [[paper](https://arxiv.org/abs/1807.01613)]
439 |   - Marta Garnelo, Dan Rosenbaum, Chris J. Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo J. Rezende, S. M. Ali Eslami --ICML 2018
440 | 
441 | ## Configuration transfer
442 | 
443 | Online Hyperparameter Meta-Learning with Hypergradient Distillation [[paper](https://openreview.net/forum?id=01AMRlen9wJ)]
444 |   - Hae Beom Lee, Hayeon Lee, JaeWoong Shin, Eunho Yang, Timothy Hospedales, Sung Ju Hwang --ICLR 2022
445 | 
446 | Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels [[paper](https://arxiv.org/abs/1910.05199)]
447 |   - Massimiliano Patacchiola, Jack Turner, Elliot J. Crowley, Michael O'Boyle, Amos Storkey --NeurIPS 2020
448 | 
449 | Meta-Learning for Few-Shot NMT Adaptation [[paper](https://www.aclweb.org/anthology/2020.ngt-1.5.pdf)]
450 |   - Amr Sharaf, Hany Hassan, Hal Daumé III --arXiv 2020
451 | 
452 | Fast Context Adaptation via Meta-Learning [[paper](https://arxiv.org/pdf/1810.03642.pdf)]
453 |   - Luisa M Zintgraf, Kyriacos Shiarlis, Vitaly Kurin, Katja Hofmann, Shimon Whiteson  --ICML 2019
454 | 
455 | Zero-Shot Knowledge Distillation in Deep Networks [[paper](https://arxiv.org/pdf/1905.08114.pdf)]
456 |   - Gaurav Kumar Nayak *, Konda Reddy Mopuri, Vaisakh Shaj, R. Venkatesh Babu, Anirban Chakraborty --ICML 2019
457 | 
458 | Toward Multimodal Model-Agnostic Meta-Learning [[paper](https://arxiv.org/pdf/1812.07172.pdf)]
459 |   - Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim  --arXiv 2019
460 | 
461 | Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks [[paper](https://arxiv.org/abs/1703.03400)]
462 |   - Chelsea Finn, Pieter Abbeel, Sergey Levine -- ICML 2016
463 | 
464 | ### Semi/Unsupervised learning
465 | 
466 | Unsupervised Learning via Meta-Learning [[paper](https://arxiv.org/abs/1810.02334)]
467 |   - Kyle Hsu, Sergey Levine, Chelsea Finn -- ICLR 2019
468 |   
469 | Meta-Learning Update Rules for Unsupervised Representation Learning [[paper](https://openreview.net/pdf?id=HkNDsiC9KQ)]
470 |   - Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein --ICLR 2019
471 | 
472 | Meta-Learning for Semi-Supervised Few-Shot Classification [[paper](https://arxiv.org/pdf/1803.00676.pdf)]
473 |   - Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel --ICLR 2018
474 | 
475 | Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace [[paper](https://arxiv.org/abs/1903.08254)]
476 |   - Kate Rakelly, Aurick Zhou, Deirdre Quillen, Chelsea Finn, Sergey Levine  --ICML 2018
477 | 
478 | ### Self-supervised learning
479 | 
480 | MAML is a Noisy Contrastive Learner in Classification [[paper](https://openreview.net/pdf?id=LDAwu17QaJz)]
481 |   - Chia Hsiang Kao, Wei-Chen Chiu, Pin-Yu Chen --ICLR 2022
482 | 
483 | Contrastive Learning is Just Meta-Learning [[paper](https://openreview.net/forum?id=gICys3ITSmj)]
484 |   - Renkun Ni, Manli Shu, Hossein Souri, Micah Goldblum, Tom Goldstein --ICLR 2022
485 | 
486 | ### Learning curves
487 | Transferring Knowledge across Learning Processes [[paper](https://openreview.net/forum?id=HygBZnRctX)]
488 |   - Sebastian Flennerhag, Pablo G. Moreno, Neil D. Lawrence, Andreas Damianou --ICLR 2019
489 | 
490 | Meta-Curvature [[paper](https://arxiv.org/abs/1902.03356)]
491 |   - Eunbyung Park, Junier B. Oliva --NeurIPS 2019
492 | 
493 | ### Hyperparameter
494 | LCC: Learning to Customize and Combine Neural Networks for Few-Shot Learning [[paper](https://arxiv.org/pdf/1904.08479.pdf)]
495 |   - Yaoyao Liu, Qianru Sun, An-An Liu, Yuting Su, Bernt Schiele, Tat-Seng Chua --CVPR 2019
496 | 
497 | Gradient-based Hyperparameter Optimization through Reversible Learning [[paper](https://arxiv.org/pdf/1502.03492.pdf)]
498 |   - Dougal Maclaurin, David Duvenaud, Ryan P. Adams --ICML 2016
499 | 
500 | ## Model compression
501 | N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning
502 |   - Anubhav Ashok, Nicholas Rhinehart, Fares Beainy, Kris M. Kitani --ICLR 2018
503 | 
504 | ## Kernel learning
505 | 
506 | Deep Kernel Transfer in Gaussian Processes for Few-shot Learning [[paper](https://arxiv.org/pdf/1910.05199.pdf)]
507 |   - Massimiliano Patacchiola, Jack Turner, Elliot J. Crowley, Michael O’Boyle, Amos Storkey --arXiv 2020
508 | 
509 | Deep Mean Functions for Meta-Learning in Gaussian Processes [[paper](https://arxiv.org/pdf/1901.08098.pdf)]
510 |   - Vincent Fortuin, Gunnar Rätsch --arXiv 2019
511 | 
512 | Kernel Learning and Meta Kernels for Transfer Learning  [[paper](http://www1.icsi.berkeley.edu/~rueckert/papers/rueckert09kernel)]
513 |   - Ulrich Ruckert
514 | 
515 | ## Robustness
516 | A Closer Look at the Training Strategy for Modern Meta-Learning [[paper](https://proceedings.neurips.cc/paper/2020/hash/0415740eaa4d9decbc8da001d3fd805f-Abstract.html)]
517 |   - JIAXIN CHEN, Xiao-Ming Wu, Yanke Li, Qimai LI, Li-Ming Zhan, Fu-lai Chung --NeurIPS 2020
518 | 
519 | Task-Robust Model-Agnostic Meta-Learning [[paper](https://papers.nips.cc/paper/2020/file/da8ce53cf0240070ce6c69c48cd588ee-Paper.pdf)]
520 |   - Liam Collins, Aryan Mokhtari, Sanjay Shakkottai --NeurIPS 2020
521 | 
522 | FeatureBoost: A Meta-Learning Algorithm that Improves Model Robustness [[paper](https://hunch.net/~jl/projects/robust/ml2krobust.pdf)]
523 |   - Joseph O'Sullivan, John Langford, Rich Caruana, Avrim Blum --ICML 2000
524 | 
525 | ## Optimization
526 | 
527 | Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning [[paper](https://arxiv.org/abs/2206.03996)]
528 |   - Momin Abbas, Quan Xiao, Lisha Chen, Pin-Yu Chen, Tianyi Chen --ICML 2022
529 | 
530 | Bootstrapped Meta-Learning [[paper](https://openreview.net/forum?id=b-ny3x071E5)]
531 |   - Sebastian Flennerhag, Yannick Schroecker, Tom Zahavy, Hado van Hasselt, David Silver, Satinder Singh --ICLR 2022
532 | 
533 | Learning where to learn: Gradient sparsity in meta and continual learning [[paper](https://arxiv.org/pdf/2110.14402.pdf)]
534 |   - Johannes von Oswald, Dominic Zhao, Seijin Kobayashi, Simon Schug, Massimo Caccia, Nicolas Zucchet, João Sacramento --NeurIPS 2021
535 | 
536 | 
537 | Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML [[paper](https://openreview.net/pdf/f0530e2cf88af3b74bf61bc8591b7a5a1339c49e.pdf)]
538 |   - Aniruddh Raghu, Maithra Raghu, Samy Bengio, Oriol Vinyals --ICLR 2020
539 | 
540 | Empirical Bayes Transductive Meta-Learning with Synthetic Gradients [[paper](https://arxiv.org/abs/2004.12696)]
541 |   - Shell Xu Hu, Pablo G. Moreno, Yang Xiao, Xi Shen, Guillaume Obozinski, Neil D. Lawrence, Andreas Damianou --ICLR 2020
542 | 
543 | Transferring Knowledge across Learning Processes [[paper](https://openreview.net/forum?id=HygBZnRctX)]
544 |   - Sebastian Flennerhag, Pablo G. Moreno, Neil D. Lawrence, Andreas Damianou --ICLR 2019
545 | 
546 | MetaInit: Initializing learning by learning to initialize [[paper](https://papers.nips.cc/paper/9427-metainit-initializing-learning-by-learning-to-initialize)]
547 |   - Yann N. Dauphin, Samuel Schoenholz  --NeurIPS 2019
548 |   
549 | Meta-Learning with Implicit Gradients [[paper](https://arxiv.org/abs/1909.04630)]
550 |   - Aravind Rajeswaran*, Chelsea Finn*, Sham Kakade, Sergey Levine  --NeurIPS 2019
551 | 
552 | Model-Agnostic Meta-Learning using Runge-Kutta Methods [[paper](https://arxiv.org/abs/1910.07368)]
553 |   - Daniel Jiwoong Im, Yibo Jiang, Nakul Verma --arXiv
554 | 
555 | Learning to Optimize in Swarms [[paper](https://arxiv.org/pdf/1911.03787.pdf)]
556 |   - Yue Cao, Tianlong Chen, Zhangyang Wang, Yang Shen --arXiv 2019
557 | 
558 | Meta-Learning with Warped Gradient Descent [[paper](https://arxiv.org/pdf/1909.00025.pdf)]
559 |   - Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Hujun Yin, Raia Hadsell --ICLR 2020
560 |   
561 | Learning to Generalize to Unseen Tasks with Bilevel Optimization [[paper](https://arxiv.org/pdf/1908.01457.pdf)]
562 |   - Hayeon Lee, Donghyun Na, Hae Beom Lee, Sung Ju Hwang --arXiv 2019
563 | 
564 | Learning to Optimize [[paper](https://arxiv.org/abs/1606.01885)]
565 |   - Ke Li Jitendra Malik --ICLR 2017
566 | 
567 | Gradient-based Hyperparameter Optimization through Reversible Learning [[paper](https://arxiv.org/pdf/1502.03492.pdf)]
568 |   - Dougal Maclaurin, David Duvenaud, Ryan P. Adams --ICML 2016
569 | 
570 | ### Continuous time
571 | 
572 | Continuous-Time Meta-Learning with Forward Mode Differentiation [[paper](https://openreview.net/forum?id=57PipS27Km)]
573 |   - Tristan Deleu, David Kanaa, Leo Feng, Giancarlo Kerg, Yoshua Bengio, Guillaume Lajoie, Pierre-Luc Bacon --ICLR 2022
574 | 
575 | Meta-learning using privileged information for dynamics [[paper](https://arxiv.org/pdf/2104.14290.pdf)]
576 |   - Ben Day, Alexander Norcliffe, Jacob Moss, Pietro Liò --ICLR 2020 #Learning to Learn and SimDL
577 | 
578 | ## Theory
579 | 
580 | Near-Optimal Task Selection with Mutual Information for Meta-Learning [[paper](https://www.comp.nus.edu.sg/~lowkh/pubs/aistats2022.pdf)]
581 |   - Chen, Yizhou; Zhang, Shizhuo; Low, Bryan Kian Hsiang  --AISTATS 2022
582 | 
583 | Learning Tensor Representations for Meta-Learning [[paper](https://arxiv.org/abs/2201.07348)]
584 |   - Samuel Deng, Yilin Guo, Daniel Hsu, Debmalya Mandal --AISTATS 2022
585 | 
586 | Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably? [[paper](https://chentianyi1991.github.io/bamaml_aistats2022.pdf)]
587 |   - Lisha Chen, Tianyi Chen  --AISTATS 2022
588 | 
589 | Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate [[paper](https://openreview.net/forum?id=3rULBvOJ8D2)]
590 |   - Yingtian Zou, Fusheng Liu, Qianxiao Li --ICLR 2022
591 | 
592 | Task Relatedness-Based Generalization Bounds for Meta Learning [[paper](https://openreview.net/forum?id=A3HHaEdqAJL)]
593 |   - Jiechao Guan, Zhiwu Lu --ICLR 2022
594 | 
595 | How Tight Can PAC-Bayes be in the Small Data Regime? [[paper](https://arxiv.org/pdf/2106.03542.pdf)]
596 |   - Andrew Y. K. Foong, Wessel P. Bruinsma, David R. Burt, Richard E. Turner --NeurIPS 2021
597 | 
598 | A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning [[paper](https://arxiv.org/pdf/2106.15615.pdf)]
599 |   - Nikunj Saunshi, Arushi Gupta, and Wei Hu --ICML 2021
600 | 
601 | Bilevel Optimization: Convergence Analysis and Enhanced Design [[paper](http://proceedings.mlr.press/v139/ji21c/ji21c.pdf)]
602 |   - Kaiyi Ji, Junjie Yang, Yingbin Liang --ICML 2021
603 | 
604 | How Important is the Train-Validation Split in Meta-Learning? [[paper](https://arxiv.org/abs/2010.05843)]
605 |   - Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham Kakade, Huan Wang, Caiming Xiong --ICML 2021
606 | 
607 | Information-Theoretic Generalization Bounds for Meta-Learning and Applications [[paper](https://arxiv.org/pdf/2005.04372.pdf)]
608 |   - Sharu Theresa Jose, Osvaldo Simeone --arXiv 2021
609 | 
610 | 
611 | Modeling and Optimization Trade-off in Meta-learning [[paper](https://proceedings.neurips.cc/paper/2020/hash/7fc63ff01769c4fa7d9279e97e307829-Abstract.html)]
612 |   - Katelyn Gao, Ozan Sener --NeurIPS 2020
613 | 
614 | A Closer Look at the Training Strategy for Modern Meta-Learning [[paper](https://proceedings.neurips.cc/paper/2020/hash/0415740eaa4d9decbc8da001d3fd805f-Abstract.html)]
615 |   - JIAXIN CHEN, Xiao-Ming Wu, Yanke Li, Qimai LI, Li-Ming Zhan, Fu-lai Chung --NeurIPS 2020
616 | 
617 | Why Does MAML Outperform ERM? An Optimization Perspective [[paper](https://arxiv.org/pdf/2010.14672.pdf)]
618 |   - Liam Collins, Aryan Mokhtari, Sanjay Shakkottai --arXiv 2020
619 | 
620 | Transfer Meta-Learning: Information-Theoretic Bounds and Information Meta-Risk Minimization [[paper](https://arxiv.org/pdf/2011.02872.pdf)]
621 |   - Sharu Theresa Jose, Osvaldo Simeone, Giuseppe Durisi --arXiv 2020
622 | 
623 | The Advantage of Conditional Meta-Learning for Biased Regularization and Fine-Tuning [[paper](https://arxiv.org/abs/2006.09486)]
624 |   - Giulia Denevi, Massimiliano Pontil, Carlo Ciliberto --NeurIPS 2020
625 | 
626 | Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters [[paper](https://arxiv.org/abs/2006.09486)]
627 |   - Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor --NeurIPS 2020
628 | 
629 | Meta-learning for mixed linear regression [[paper](https://proceedings.icml.cc/static/paper_files/icml/2020/6124-Paper.pdf)]
630 |   - Weihao Kong, Raghav Somani, Zhao Song, Sham Kakade, Sewoong Oh --ICML 2020
631 | 
632 | Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
633 |   - Ferran Alet, Kenji Kawaguchi, Maria Bauza, Nurallah Giray Kuru, Tomás Lozano-Pérez, Leslie Pack Kaelbling  --NeurIPS 2020 #Meta-Learning
634 | 
635 | A Theoretical Analysis of the Number of Shots in Few-Shot Learning [[paper](https://openreview.net/forum?id=HkgB2TNYPS)]
636 |   - Tianshi Cao, Marc T Law, Sanja Fidler --ICLR 2020
637 | 
638 | Efficient Meta Learning via Minibatch Proximal Update [[paper](https://papers.nips.cc/paper/8432-efficient-meta-learning-via-minibatch-proximal-update)]
639 |   - Pan Zhou, Xiaotong Yuan, Huan Xu, Shuicheng Yan, Jiashi Feng --NeurIPS 2019
640 | 
641 | On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms [[paper](https://arxiv.org/pdf/1908.10400.pdf)]
642 |   - Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar --arXiv 2019
643 | 
644 | Meta-learners' learning dynamics are unlike learners' [[paper](https://arxiv.org/abs/1905.01320)]
645 |   - Neil C. Rabinowitz --arXiv 2019
646 | 
647 | Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior [[paper](https://arxiv.org/pdf/1811.09558.pdf)]
648 |   - Zi Wang, Beomjoon Kim, Leslie Pack Kaelbling --NeurIPS 2018
649 | 
650 | Incremental Learning-to-Learn with Statistical Guarantees [[paper](https://arxiv.org/abs/1803.08089)]
651 |   - Giulia Denevi, Carlo Ciliberto, Dimitris Stamos, Massimiliano Pontil  --UAI 2018
652 | 
653 | Meta-learning by adjusting priors based on extended PAC-Bayes theory [[paper](https://arxiv.org/pdf/1711.01244.pdf)]
654 |   - Ron Amit , Ron Meir --ICML 2018
655 | 
656 | Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm [[paper](https://arxiv.org/pdf/1710.11622.pdf)]
657 |   - Chelsea Finn, Sergey Levine --ICLR 2018
658 | 
659 | On the Convergence of Model-Agnostic Meta-Learning [[paper](http://noahgolmant.com/writings/maml.pdf)]
660 |   - Noah Golmant
661 | 
662 | Fast Rates by Transferring from Auxiliary Hypotheses [[paper](https://arxiv.org/pdf/1412.1619.pdf)]
663 |   - Ilja Kuzborskij, Francesco Orabona --arXiv 2014
664 | 
665 | Algorithmic Stability and Meta-Learning  [[paper](http://www.jmlr.org/papers/volume6/maurer05a/maurer05a.pdf)]
666 |   - Andreas Maurer  --JMLR 2005
667 | 
668 | 
669 | ### Online convex optimization
670 | PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees [[paper](http://proceedings.mlr.press/v139/rothfuss21a/rothfuss21a.pdf)]
671 |   - Jonas Rothfuss, Vincent Fortuin, Martin Josifoski, Andreas Krause --ICML 2021
672 | 
673 | Meta-learning with Stochastic Linear Bandits [[paper](https://arxiv.org/abs/2005.04372)]
674 |   - Leonardo Cella, Alessandro Lazaric, Massimiliano Pontil --arXiv 2020
675 | 
676 | Bayesian Online Meta-Learning with Laplace Approximation [[paper](https://arxiv.org/abs/2005.00146)]
677 |   - Pau Ching Yap, Hippolyt Ritter, David Barber --arXiv 2020
678 | 
679 | Online Meta-Learning on Non-convex Setting [[paper](https://arxiv.org/abs/1910.10196)]
680 |   - Zhenxun Zhuang, Yunlong Wang, Kezi Yu, Songtao Lu --arXiv 2019
681 | 
682 | Adaptive Gradient-Based Meta-Learning Methods [[paper](https://arxiv.org/pdf/1906.02717.pdf)]
683 |   - Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar --NeurIPS 2019
684 | 
685 | Learning-to-Learn Stochastic Gradient Descent with Biased Regularization [[paper](https://arxiv.org/abs/1903.10399)]
686 |   - Giulia Denevi, Carlo Ciliberto, Riccardo Grazzi, Massimiliano Pontil  --NeurIPS 2019
687 | 
688 | Provable Guarantees for Gradient-Based Meta-Learning
689 |   -  Mikhail Khodak Maria-Florina Balcan Ameet Talwalkar --arXiv 2019 
690 | 
691 | 


--------------------------------------------------------------------------------