Projects

PAC-Bayesian Bound

• Benjamin Guedj, John Shawe-Taylor, A Primer on PAC-Bayesian Learning. Tutorial on ICML 2019.

• Francois Laviolette, A tutorial on the Pac-Bayesian Theory. Tutorial on NIPS 2017.

Information Theoretic Analysis of Generalization Capability

• Thomas Steinke, Lydia Zakynthinou, Open Problem: Information Complexity of VC Learning. COLT 2020.

• Aolin Xu and Maxim Raginsky, Information-theoretic analysis of generalization capability of learning algorithms. NIPS 2017.

Active Learning

• Steve Hanneke, Robert Nowak, Active Learning from Theory to Practice. Tutorial on ICML 2019.

Model Selection Criterion: AIC and BIC

• L. Zheng, Akaike Information Criterion.

• L. Zheng, Bayesian Information Criterion.

Information Flow In Neural Networks

• Ziv Goldfeld, Ewout Van Den Berg, Kristjan Greenewald, Igor Melnyk, Nam Nguyen, Brian Kingsbury, Yury Polyanskiy, Estimating Information Flow in Deep Neural Networks. ICML 2019.

Understanding Neural Networks

• Sanjeev Arora, Toward theoretical understanding of deep learning. Tutorial on ICML 2018.

• S. Mei, A. Montanari, P.-M. Nguyen, A Mean Field View of the Landscape of Two-Layers Neural Networks. PNAS 2018.

Transfer Learning and Domain Adaptation

• Transfer Learning and Domain Adaptation Reading List

Optimal Transport in Machine Learning

• Optimal Transport Theory the New Math for Deep Learning

Community Detection

• E. Abbe, A.S. Bandeira, G. Hall, Exact Recovery in the Stochastic Block Model. IEEE Transactions on Information Theory, Jan. 2016

• E. Mossel, J. Neeman, A. Sly, Consistency Thresholds for the Planted Bisection Model. Electronic Journal of Probability, Mar. 2016.

Robust PCA

• Emmanuel J. Candes, Xiaodong Li, Yi Ma, John Wright, Robust Principal Component Analysis?

Inference on Graph

• Yihong Wu and Jiaming Xu, Statistical inference on graphs.

Generative Adversarial Networks

• Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, Generative Adversarial Networks. NIPS 2014.

• Banghua Zhu, Jiantao Jiao, David Tse, Deconstructing Generative Adversarial Networks.

Variational Autoencoders

• D. P Kingma, Ma. Welling, Auto-Encoding Variational Bayes.

• C. Doersch, Tutorial on Variational Autoencoders.

Matrix Completion with Noise

• Emmanuel J. Candes, Yaniv Plan, Matrix Completion With Noise. Proceedings of IEEE 2010.

• Raghunandan H. Keshavan, Andrea Montanari, and Sewoong Oh, Matrix Completion from Noisy Entries.

Multi-Armed Bandits

• Daniel Russo, Benjamin Van Roy, An Information-Theoretic Analysis of Thompson Sampling. JMLR 2016.

• Daniel Russo, Benjamin Van Roy, Abbas Kazerouni, Ian Osband, Zheng Wen, A Tutorial on Thompson Sampling.

Federated Learning

• P. Kairouz et al, Advances and Open Problems in Federated Learning

Distributionally Robust Learning (Minimax Learning)

• H. Namkoong, J. Duchi, Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences.

• F. Farnia, D. Tse, A Minimax Approach to Supervised Learning.

• J. Lee, M. Raginsky, Minimax Statistical Learning with Wasserstein Distances.

Quantum Machine Learning

• J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe, S. Lloyd, Quantum machine learning. Nature 2017.