└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Kyurae Kim's Awesome Papers 2 | The papers that made me stay awake all night long. 3 | Let me know if you have anything interesting to share! 4 | 5 | ## Interests 6 | * High-performance computing 7 | * Probabilistic machine learning 8 | * Bayesian Statistics 9 | * Bayesian inference 10 | * Bayesian optimization 11 | * Heterogeneous, specialized hardware 12 | * Image processing 13 | * Signal Processing 14 | 15 | ## Awesome Papers 16 | * Blei, David M., Andrew Y. Ng, and Michael I. Jordan. [**"Latent Dirichlet Allocation."**](http://www.jmlr.org/papers/volume3/blei03a/blei03a.pdf) *Journal of machine Learning research* 3.Jan (2003): 993-1022. 17 | 18 | * Neal, Radford M. [**"Bayesian Learning for Neural Networks."**](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.446.9306&rep=rep1&type=pdf) Vol. 118. Springer Science & Business Media, 2012. 19 | 20 | * Chaney, Allison, et al. [**"Detecting and Characterizing Events."**](http://dirichlet.net/pdf/chaney16detecting.pdf) *Proceedings of the Conference on Empirical Methods in Natural Language Processing*. 2016. 21 | 22 | * Regier, Jeffrey, et al. [**"Approximate inference for constructing astronomical catalogs from images."**](https://projecteuclid.org/journals/annals-of-applied-statistics/volume-13/issue-3/Approximate-inference-for-constructing-astronomical-catalogs-from-images/10.1214/19-AOAS1258.full) *The Annals of Applied Statistics* 13.3 (2019): 1884-1926. 23 | * [Juliacon 2017 Talk](https://juliacomputing.com/case-studies/celeste.html) 24 | 25 | * Shanbhag, Naresh R., et al. [**"Shannon-inspired Statistical Computing for The Nanoscale Era."**](https://ieeexplore.ieee.org/document/8482253) *Proceedings of the IEEE* 107.1 (2019): 90-107. 26 | * [Stanford Seminar](https://www.youtube.com/watch?v=zwzYNura0Ps) 27 | 28 | * Ungar, David, and Sam S. Adams. [**"Harnessing Emergence for Manycore Programming: Early Experience Integrating Ensembles, Adverbs, and Object-based Inheritance."**](https://dl.acm.org/citation.cfm?id=1869546) *Proceedings of the ACM International Conference Companion on Object Oriented Programming Systems languages and Applications Companion* (OOPSLA). ACM, 2010. 29 | * [STI Conference Presentation](https://youtu.be/GBtqQwcJoN0) 30 | 31 | * Thompson, Neil, and Svenja Spanuth. [**"The Decline of Computers As a General Purpose Technology: Why Deep Learning and the End of Moore’s Law are Fragmenting Computing."**](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3287769) Available at SSRN 3287769 (2018). 32 | 33 | * Hammernik, Kerstin, et al. [**"Learning a Variational Network for Reconstruction of Accelerated MRI Data."**](https://arxiv.org/abs/1704.00447) *Magnetic resonance in medicine* 79.6 (2018): 3055-3071. 34 | * Previous works 35 | * Chen, Yunjin, Wei Yu, and Thomas Pock. [**"On learning optimized reaction-diffusion processes for effective image restoration."**](https://arxiv.org/abs/1503.05768) *Proceedings of the IEEE conference on computer vision and pattern recognition* (CVPR), 2015. 36 | 37 | * Fuchs, Adi, and David Wentzlaff. [**"The Accelerator Wall: Limits of Chip Specialization."**](http://parallel.princeton.edu/papers/wall-hpca19.pdf) *Proceedings of the IEEE International Symposium on High-Performance Computer Architecture* (HPCA'19). 38 | 39 | * Ulyanov, Dmitry, Andrea Vedaldi, and Victor Lempitsky. [**"Deep Image Prior."**](https://arxiv.org/abs/1711.10925) *Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition* (CVPR'18). 40 | * Follow-up works 41 | * Zezhou Cheng, Matheus Gadelha, Subhransu Maji, Daniel Sheldon. [**"A Bayesian Perspective on the Deep Image Prior"**](https://arxiv.org/abs/1904.07457). *Proceedings of the Conference on Computer Vision and Pattern Recognition* (CVPR'19). 42 | 43 | * de Fine Licht, Johannes, et al. [**"Transformations of high-level synthesis codes for high-performance computing."**](https://arxiv.org/abs/1805.08288) *IEEE Transactions on Parallel and Distributed Systems* 32.5 (2020): 1014-1029. 44 | 45 | * Kendall, Alex, and Yarin Gal. [**"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?."**](https://arxiv.org/abs/1703.04977) *Advances in neural information processing systems* (NIPS). 2017. 46 | 47 | * Boyd, Stephen, et al. [**"Distributed optimization and statistical learning via the alternating direction method of multipliers."**](http://web.stanford.edu/~boyd/papers/admm_distr_stats.html) *Foundations and Trends® in Machine learning* 3.1 (2011): 1-122. 48 | * [Microsoft Research Talk](https://www.youtube.com/watch?v=Xg0ozgCXXB8) 49 | 50 | * Pearce, Tim, et al. [**"Uncertainty in Neural Networks: Bayesian Ensembling."**](https://arxiv.org/abs/1810.05546) In Proceedings of Artificial Intelligence and Statistics (AISTATS'20). 2020. 51 | 52 | * Qiang Liu and Dilin Wang. 2016. [**"Stein Variational Gradient Descent: a General Purpose Bayesian Inference Algorithm."**](https://dl.acm.org/citation.cfm?id=3157362) *Advances in Neural Information Processing Systems* (NIPS'16), 2016. 53 | * [Interactive demo](https://chi-feng.github.io/mcmc-demo/app.html). Select *SVGD* for the algorithm. 54 | * Follow-up works 55 | * Han, Jun, and Qiang Liu. [**"Stein Variational Gradient Descent Without Gradient."**](http://proceedings.mlr.press/v80/han18b.html) *Proceedings of the International Conference on Machine Learning* (ICML'18), in PMLR 80:1900-1908 56 | * Han, Jun, and Qiang Liu. [**"Stein Variational Adaptive Importance Sampling."**](http://auai.org/uai2017/proceedings/papers/217.pdf) *Proceedings of the Conference on Uncertainty in Artificial Intelligence* (UAI'17). 57 | 58 | * Wilson Ye Chen, Alessandro Barp, Francois-Xavier Briol, Jackson Gorham, Mark Girolami, Lester Mackey and Chris Oates. (2019). [**"Stein Point Markov Chain Monte Carlo"**](http://proceedings.mlr.press/v97/chen19b.html), *Proceedings of the International Conference on Machine Learning* (ICML'19), in PMLR 97:1011-1021 59 | 60 | * Jordan, Michael I. [**"Dynamical, Symplectic and Stochastic Perspectives on Gradient-Based Optimization."**](https://eta.impa.br/dl/PL012.pdf) University of California, Berkeley (2018). 61 | * [ICM 2018 Talk](https://www.youtube.com/watch?v=wXNWVhE2Dl4) 62 | 63 | * Kruskal, Clyde P., and Alan Weiss. [**"Allocating Independent Subtasks on Parallel Processors."**](https://ieeexplore.ieee.org/abstract/document/1701915) *IEEE Transactions on Software engineering 10*, 1001-1016, 1985. 64 | * Follow-up works 65 | * Bast, Hannah. [Ph.D. Thesis](http://ad.informatik.uni-freiburg.de/files/phd-thesis-hannah-bast.pdf/view?set_language=en), 2000 66 | 67 | * Solnik, Benjamin, et al. [**"Bayesian Optimization for a Better Dessert."**](https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/46507.pdf) (2017). 68 | 69 | * Dai, Z., Yu, H., Low, B.K.H. & Jaillet, P.. (2019). [**"Bayesian Optimization Meets Bayesian Optimal Stopping"**](http://proceedings.mlr.press/v97/dai19a.html). *Proceedings of the 36th International Conference on Machine Learning (ICML)*, in PMLR 97:1496-1506 70 | 71 | * Hartwig Anzt, Terry Cojean, Chen Yen-Chen, Jack Dongarra, Goran Flegar, Pratik Nayak, Stanimire Tomov, Yuhsiang M. Tsai, and Weichung Wang. [**"Load-balancing Sparse Matrix Vector Product Kernels on GPUs"**](https://doi.org/10.1145/3380930). *ACM Transactions on Parallel Computing*. 7, 1, Article 2 (March 2020). 72 | 73 | * Kathleen E. Hamilton, Catherine D. Schuman, Steven R. Young, Ryan S. Bennink, Neena Imam, and Travis S. Humble. [**"Accelerating Scientific Computing in the Post-Moore’s Era"**](https://doi.org/10.1145/3380940). *ACM Transactions on Parallel Computing*. 7, 1, Article 6 (March 2020). 74 | 75 | * Mikkola, Petrus, et al. [**"Projective Preferential Bayesian Optimization"**](https://arxiv.org/abs/2002.03113). *Proceedings of the International Conference on Machine Learning (ICML'20)*, 2020. 76 | 77 | * Slaughter, Elliott, et al. [**"Task Bench: A Parameterized Benchmark for Evaluating Parallel Runtime Performance."**](https://arxiv.org/abs/1908.05790) *Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis* (SC'20), 2020. 78 | 79 | * Geoffrey Roeder, Yuhuai Wu, David K. Duvenaud. [**"Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference."** 80 | ](https://proceedings.neurips.cc/paper/2017/hash/e91068fff3d7fa1594dfdf3b4308433a-Abstract.html) *Advances in Neural Information Processing Systems 30* (NeurIPS'17), 2017. 81 | 82 | * Vaden Masrani, Tuan Anh Le, Frank Wood. [**"The Thermodynamic Variational Objective."**](https://papers.nips.cc/paper/2019/hash/618faa1728eb2ef6e3733645273ab145-Abstract.html) *Advances in Neural Information Processing Systems* 32 (NeurIPS'19), 2019. 83 | * Follow-up works 84 | * Rob Brekelmans, Vaden Masrani, Frank Wood, Greg Ver Steeg, Aram Galstyan. [**"All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference."**](http://proceedings.mlr.press/v119/brekelmans20a.html) Proceedings of the International Conference on Machine Learning (ICML'20), PMLR 119:1111-1122, 2020. 85 | * Vu Nguyen, et al. [**"Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective."**](https://proceedings.neurips.cc/paper/2020/file/3f2dff7862a70f97a59a1fa02c3ec110-Paper.pdf) Advances in Neural Information Processing Systems 33 (NeurIPS'20). 86 | 87 | * Tijana Radivojević, Elena Akhmatskaya. [**"Modified Hamiltonian Monte Carlo for Bayesian inference."**](https://link.springer.com/content/pdf/10.1007/s11222-019-09885-x.pdf) *Statistics and Computing* 30, 377–404, 2020. 88 | 89 | * Gilboa, Guy, Nir Sochen, and Yehoshua Y. Zeevi. [**"Image enhancement and denoising by complex diffusion processes."**](https://www.cs.jhu.edu/~misha/ReadingSeminar/Papers/Gilboa04.pdf) *IEEE Transactions on Pattern Analysis and Machine Intelligence* 26.8 (2004): 1020-1036. 90 | 91 | * Tzu-Mao Li, Jaakko Lehtinen, Ravi Ramamoorthi, Wenzel Jakob, Frédo Durand. [**"Anisotropic Gaussian Mutations for Metropolis Light Transport through Hessian-Hamiltonian Dynamics."**](https://people.csail.mit.edu/tzumao/h2mc/) 92 | *ACM Transactions on Graphics* 34(6) (Proceedings of ACM SIGGRAPH Asia 2015). 93 | 94 | * Eric Brochu, Tyson Brochu, Nando de Freitas. [**"A Bayesian interactive optimization approach to procedural animation design."**](http://haikufactory.com/files/sca2010.pdf) *Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation* (SCA'10), 103-112. 95 | 96 | * Fearnhead, Paul, and Benjamin M. Taylor. [**"An adaptive sequential Monte Carlo sampler."**](https://projecteuclid.org/journals/bayesian-analysis/volume-8/issue-2/An-Adaptive-Sequential-Monte-Carlo-Sampler/10.1214/13-BA814.full) *Bayesian Analysis* 8.2 (2013): 411-438. 97 | 98 | * Akash Kumar Dhaka, *et al.* ["**Robust, Accurate Stochastic Optimization for Variational Inference.**"](https://papers.nips.cc/paper/2020/hash/7cac11e2f46ed46c339ec3d569853759-Abstract.html) *Advances in Neural Information Processing Systems* (NeurIPS'20). 99 | 100 | * Yu, Yongjian, and Scott T. Acton. **"Speckle reducing anisotropic diffusion."** IEEE Transactions on image processing 11.11 (2002): 1260-1270. 101 | * Follow-up works 102 | * Aja-Fernández, Santiago, and Carlos Alberola-López. **"On the estimation of the coefficient of variation for anisotropic diffusion speckle filtering."** *IEEE Transactions on Image Processing* 15.9 (2006): 2694-2701. 103 | * Krissian, Karl, et al. **"Oriented speckle reducing anisotropic diffusion."** *IEEE Transactions on Image Processing* 16.5 (2007): 1412-1424. 104 | 105 | * Shan, Tie-Jun, and Kailath, T., **"Adaptive beamforming for coherent signals and interference."** *IEEE Transactions on Acoustics, Speech, and Signal Processing* 33(3), Jun 1985. 106 | 107 | * Yuko Ishiwaka, Xiao S. Zeng, Michael Lee Eastman, Sho Kakazu, Sarah Gross, Ryosuke Mizutani, and Masaki Nakada, [**"Foids: bio-inspired fish simulation for generating synthetic datasets."**](https://doi.org/10.1145/3478513.3480520) *ACM Transactions on Graphics* 40, 6, Article 207, Dec 2021. 108 | 109 | * Surjanovic, Nikola, et al. [**"Parallel Tempering With a Variational Reference."**](https://papers.nips.cc/paper_files/paper/2022/hash/03cd3cf3f74d4f9ce5958de269960884-Abstract-Conference.html) *Advances in Neural Information Processing Systems* 35 (2022): 565-577. 110 | 111 | * Andrieu, Christophe, and Arnaud Doucet. **"Joint Bayesian model selection and estimation of noisy sinusoids via reversible jump MCMC."** *IEEE Transactions on Signal Processing* 47.10 (1999): 2667-2676. 112 | 113 | * Mishchenko, Konstantin, Ahmed Khaled, and Peter Richtárik. [**"Random reshuffling: Simple analysis with vast improvements."**](https://proceedings.neurips.cc/paper/2020/hash/c8cc6e90ccbff44c9cee23611711cdc4-Abstract.html) *Advances in Neural Information Processing Systems* 33 (2020): 17309-17320. 114 | 115 | * Jacob, Pierre E., John O’Leary, and Yves F. Atchadé. [**"Unbiased Markov chain Monte Carlo methods with couplings."**](https://arxiv.org/abs/1708.03625) *Journal of the Royal Statistical Society: Series B (Statistical Methodology)* 82.3 (2020). 116 | 117 | * De Bortoli, Valentin, et al. [**"Diffusion Schrödinger bridge with applications to score-based generative modeling."**](https://proceedings.neurips.cc/paper/2021/hash/940392f5f32a7ade1cc201767cf83e31-Abstract.html) *Advances in Neural Information Processing Systems* 34 (2021): 17695-17709. 118 | 119 | * Giordano, Ryan, Tamara Broderick, and Michael I. Jordan. [**"Covariances, robustness and variational bayes."**](https://jmlr.org/papers/v19/17-670.html) *Journal of machine learning research* 19.51 (2018). 120 | 121 | * Doucet, Arnaud, Will Grathwohl, Alexander G. Matthews, and Heiko Strathmann. [**"Score-based diffusion meets annealed importance sampling."**](https://proceedings.neurips.cc/paper_files/paper/2022/hash/86b7128efa3950df7c0f6c0342e6dcc1-Abstract-Conference.html) *Advances in Neural Information Processing Systems* 35 (2022): 21482-21494. 122 | 123 | * Heng, Jeremy, Adrian N. Bishop, George Deligiannidis, and Arnaud Doucet. [**"Controlled sequential Monte Carlo."**](https://projecteuclid.org/journals/annals-of-statistics/volume-48/issue-5/Controlled-sequential-Monte-Carlo/10.1214/19-AOS1914.short) *Annals of Statistics* 48, no. 5 (2020). 124 | 125 | * Kobak, Dmitry, Jonathan Lomond, and Benoit Sanchez. [**"The optimal ridge penalty for real-world high-dimensional data can be zero or negative due to the implicit ridge regularization."**](https://jmlr.org/papers/v21/19-844.html) *The Journal of Machine Learning Research* 21.1 (2020): 6863-6878. 126 | 127 | * Bernton, Espen, et al. [**"Schrodinger Bridge Samplers."**](https://arxiv.org/abs/1912.13170) *arXiv preprint* arXiv:1912.13170 (2019). 128 | 129 | * Bardenet, Rémi, Arnaud Doucet, and Chris Holmes. [**"On Markov chain Monte Carlo methods for tall data."**](https://jmlr.org/papers/v18/15-205.html) *Journal of Machine Learning Research* 18.47 (2017). 130 | 131 | * Karagiannis, Georgios, and Christophe Andrieu. **"Annealed importance sampling reversible jump MCMC algorithms."** *Journal of Computational and Graphical Statistics* 22.3 (2013): 623-648. 132 | 133 | * Aubry, Mathieu, Sylvain Paris, Samuel W. Hasinoff, Jan Kautz, and Frédo Durand. [**"Fast local laplacian filters: Theory and applications."**](https://dl.acm.org/doi/10.1145/2629645) *ACM Transactions on Graphics* (TOG) 33.5 (2014): 1-14. 134 | 135 | 136 | * A. Dieuleveut, G. Fort, E. Moulines and H. -T. Wai, **"Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning,"** in *IEEE Transactions on Signal Processing*, vol. 71, pp. 3117-3148, 2023. 137 | 138 | * Kunstner, Frederik, Raunak Kumar, and Mark Schmidt. **"Homeomorphic-invariance of em: Non-asymptotic convergence in kl divergence for exponential families via mirror descent."** International Conference on Artificial Intelligence and Statistics. PMLR, 2021. 139 | 140 | * Altschuler, Jason M., and Pablo A. Parrilo. **"Acceleration by stepsize hedging II: Silver stepsize schedule for smooth convex optimization."** arXiv preprint arXiv:2309.16530 (2023). 141 | 142 | * Biron-Lattes, Miguel, Nikola Surjanovic, Saifuddin Syed, Trevor Campbell, and Alexandre Bouchard-Côté. **"autoMALA: Locally adaptive Metropolis-adjusted Langevin algorithm."** International Conference on Artificial Intelligence and Statistics. PMLR, 2024. 143 | 144 | * Taylor, Adrien, and Francis Bach. **"Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions."** Conference on Learning Theory. PMLR, 2019. 145 | 146 | * Durmus, Alain, Szymon Majewski, and Błażej Miasojedow. **"Analysis of Langevin Monte Carlo via convex optimization."** Journal of Machine Learning Research 20.73 (2019): 1-46 147 | 148 | * Lacoste–Julien, Simon, Ferenc Huszár, and Zoubin Ghahramani. **"Approximate inference for the loss-calibrated Bayesian."** Proceedings of the International Conference on Artificial Intelligence and Statistics. PMLR, 2011. 149 | 150 | * Akyildiz, Ö. Deniz, Francesca Romana Crucinio, Mark Girolami, Tim Johnston, and Sotirios Sabanis. **"Interacting particle langevin algorithm for maximum marginal likelihood estimation."** arXiv preprint arXiv:2303.13429 (2023). 151 | 152 | * Fong, Edwin, Chris Holmes, and Stephen G. Walker. **"Martingale posterior distributions."** Journal of the Royal Statistical Society Series B: Statistical Methodology 85.5 (2023): 1357-1391. 153 | 154 | * Zamani, Moslem, and François Glineur. **"Exact convergence rate of the last iterate in subgradient methods."** arXiv preprint arXiv:2307.11134 (2023). 155 | 156 | * Syed, Saifuddin, Alexandre Bouchard-Côté, Kevin Chern, and Arnaud Doucet. **"Optimised annealed sequential monte carlo samplers."** arXiv preprint arXiv:2408.12057 (2024). 157 | --------------------------------------------------------------------------------