Times are in Central European Time. Note: difference with US Eastern time is 5 hours during the conference.


Tuesday, March 16, 2021

17:00-17:10Welcome notes
17:10-18:10Session 1
Last-Iterate Convergence Rates for Min-Max Optimization: Convergence of Hamiltonian Gradient Descent and Consensus Optimization
Jacob D Abernethy, Kevin A Lai, Andre Wibisono
Last Round Convergence and No-Dynamic Regret in Asymmetric Repeated Games
Le Cong Dinh, Tri-Dung Nguyen, Alain Zemkoho, Long Tran-Thanh
Efficient Algorithms for Stochastic Repeated Second-price Auctions
Juliette Achddou, Olivier Cappé, Aurélien Garivier
Online Learning of Facility Locations
Stephen U Pasteris, Ting He, Fabio Vitale, Shiqiang Wang, Mark Herbster
18:20-19:20Session 2: Award talks
Near-tight closure bounds for the Littlestone and threshold dimensions
Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi
Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions
Gellert Weisz, Philip Amortila, Csaba Szepesvari
Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound
Steve Hanneke, Aryeh Kontorovich
19:40-20:40Session 3
Contrastive learning, multi-view redundancy, and linear models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
Efficient Learning with Arbitrary Covariate Shift
Adam Tauman Kalai, Varun Kanade
No-substitution k-means Clustering with Adversarial Order
Robi Bhattacharjee, Michal Moshkovitz
Unexpected Effects of Online no-Substitution k-means Clustering
Michal Moshkovitz
20:50-21:35Session 4
Characterizing the implicit bias via a primal-dual analysis
Ziwei Ji (University of Illinois at Urbana-Champaign), Matus Telgarsky
A Deep Conditioning Treatment of Neural Networks
Naman Agarwal, Pranjal Awasthi, Satyen Kale
A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layer
Manfred K. Warmuth, Wojciech Kotlowski, Ehsan Amid
21:45-22:45(tentative) Women in ML Social Event

Wednesday, March 17, 2021

17:00-18:00Session 1
Uncertainty quantification using martingales for misspecified Gaussian processes
Willie Neiswanger, Aaditya Ramdas
Precise Minimax Regret for Logistic Regression with Categorical Feature Values
Philippe Jacquet, Gil I Shamir, Wojciech Szpankowski
Submodular Combinatorial Information Measures with Applications in Machine Learning
Rishabh Iyer, Ninad A Khargonkar, Jeffrey A Bilmes, Himanshu Asnani
Intervention Efficient Algorithms for Approximate Learning of Causal Graphs
Raghavendra Addanki, Andrew McGregor, Cameron Musco
18:10-19:10Keynote: Joelle Pineau
19:30-20:30Session 3
Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time
Thibaut Cuvelier, Richard Combes, Eric Gourdin
Stochastic Dueling Bandits with Adversarial Corruption
Arpit Agarwal, Shivani Agarwal, Prathamesh Patil
Non-uniform Consistency of Online Learning with Random Sampling
Changlong Wu, Narayana Santhanam
An Efficient Algorithm for Cooperative Semi-Bandits
Riccardo Della Vecchia, Tommaso R. Cesari
20:40-21:25Session 4
Adaptive Reward-Free Exploration
Emilie Kaufmann, Pierre Menard, Omar Darwiche Domingues, Anders Jonsson, Edouard Leurent, Michal Valko
Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model
Jean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric
Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited
Omar Darwiche Domingues, Pierre Menard, Emilie Kaufmann, Michal Valko
21:30-22:30Business meeting

Thursday, March 18, 2021

17:00-18:15Session 1
Testing Product Distributions: A Closer Look
Arnab Bhattacharyya, Sutanu Gayen, Saravanan Kandasamy, N. V. Vinodchandran
Learning and Testing Irreducible Markov Chains via the k-Cover Time
Siu On Chan, Qinghua Ding, Sing Hei Li
Attribute-Efficient Learning of Halfspaces with Malicious Noise: Near-Optimal Label Complexity and Noise Tolerance
Jie Shen, Chicheng Zhang
Estimating Sparse Discrete Distributions Under Privacy and Communication Constraints
Jayadev Acharya, Peter Kairouz, Yuhan Liu, Ziteng Sun
Learning a mixture of two subspaces over finite fields
Aidao Chen, Anindya De, Aravindan Vijayaraghavan
18:30-20:00Tutorial: Shay Moran
20:15-21:30Session 3
Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Data
Di Wang, Huanyu Zhang, Marco Gaboradi, Jinhui Xu
On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians
Ishaq Aden-Ali, Hassan Ashtiani, Gautam Kamath
Bounding, Concentrating, and Truncating: Unifying Privacy Loss Composition for Data Analytics
Mark B Cesar, Ryan Rogers
Differentially Private Assouad, Fano, and Le Cam
Jayadev Acharya, Ziteng Sun, Huanyu Zhang
Descent-to-Delete: Gradient-Based Methods for Machine Unlearning
Seth Neel, Aaron Roth, Saeed Sharifi -Malvajerdi

Friday, March 19, 2021

17:00-18:00Keynote: Constantinos Daskalakis
18:10-19:10Session 2
Self-Tuning Bandits over Unknown Covariate-Shifts
Joseph Suk, Samory Kpotufe
Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback
Marc Jourdan, Mojmir Mutny, Johannes Kirschner, Andreas Krause
Stochastic Top-$K$ Subset Bandits with Linear Space and Non-Linear Feedback
Mridul Agarwal, Vaneet Aggarwal, Chris Quinn, Abhishek Kumar Umrawal
Optimal Regret Bounds for Generalized Linear Bandits under Parameter Drift
Louis Faury, Yoan Russac, Marc Abeille, Clement Calauzenes
19:30-20:30Session 3
Online Boosting with Bandit Feedback
Nataly Brukhim, Elad Hazan
Learning with comparison feedback
Michela Meister, Sloan Nietert
Sequential prediction under log-loss with side information
Alankrita Bhatt, Young-Han Kim
Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds
Ehsan Emamjomeh-Zadeh, Chen-Yu Wei, Haipeng Luo, David Kempe
20:40-21:25Session 4
Statistical guarantees for generative models without domination
Nicolas Schreuder, Arnak Dalalyan, Victor-Emmanuel Brunel
Efficient sampling from the Bingham distribution
Rong Ge, Holden Lee, Jianfeng Lu, Andrej Risteski
Subspace Embeddings under Nonlinear Transformations
Aarshvi Gajjar, Cameron Musco