Algorithmic Learning Theory 2022: Preface

Sanjoy Dasgupta, Nika Haghtalab; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:1-2

[abs][Download PDF]

Efficient Methods for Online Multiclass Logistic Regression

Naman Agarwal, Satyen Kale, Julian Zimmert; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:3-33

[abs][Download PDF]

Understanding Simultaneous Train and Test Robustness

Pranjal Awasthi, Sivaraman Balakrishnan, Aravindan Vijayaraghavan; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:34-69

[abs][Download PDF]

Learning what to remember

Robi Bhattacharjee, Gaurav Mahajan; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:70-89

[abs][Download PDF]

Learning with Distributional Inverters

Eric Binnendyk, Marco Carmosino, Antonina Kolokolova, R Ramyaa, Manuel Sabin; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:90-106

[abs][Download PDF]

Universal Online Learning with Unbounded Losses: Memory Is All You Need

Moïse Blanchard, Romain Cosson, Steve Hanneke; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:107-127

[abs][Download PDF]

Social Learning in Non-Stationary Environments

Etienne Boursier, Vianney Perchet, Marco Scarsini; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:128-129

[abs][Download PDF]

Iterated Vector Fields and Conservatism, with Applications to Federated Learning

Zachary Charles, Keith Rush; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:130-147

[abs][Download PDF]

Implicit Parameter-free Online Learning with Truncated Linear Models

Keyi Chen, Ashok Cutkosky, Francesco Orabona; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:148-175

[abs][Download PDF]

Faster Perturbed Stochastic Gradient Methods for Finding Local Minima

Zixiang Chen, Dongruo Zhou, Quanquan Gu; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:176-204

[abs][Download PDF]

Algorithms for learning a mixture of linear classifiers

Aidao Chen, Anindya De, Aravindan Vijayaraghavan; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:205-226

[abs][Download PDF]

Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games

Zixiang Chen, Dongruo Zhou, Quanquan Gu; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:227-261

[abs][Download PDF]

Refined Lower Bounds for Nearest Neighbor Condensation

Rajesh Chitnis; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:262-281

[abs][Download PDF]

Leveraging Initial Hints for Free in Stochastic Linear Bandits

Ashok Cutkosky, Chris Dann, Abhimanyu Das, Qiuyi Zhang; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:282-318

[abs][Download PDF]

Lower Bounds on the Total Variation Distance Between Mixtures of Two Gaussians

Sami Davies, Arya Mazumdar, Soumyabrata Pal, Cyrus Rashtchian; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:319-341

[abs][Download PDF]

Beyond Bernoulli: Generating Random Outcomes that cannot be Distinguished from Nature

Cynthia Dwork, Michael P. Kim, Omer Reingold, Guy N. Rothblum, Gal Yona; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:342-380

[abs][Download PDF]

Privacy Amplification via Shuffling for Linear Contextual Bandits

Evrard Garcelon, Kamalika Chaudhuri, Vianney Perchet, Matteo Pirotta; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:381-407

[abs][Download PDF]

Multicalibrated Partitions for Importance Weights

Parikshit Gopalan, Omer Reingold, Vatsal Sharan, Udi Wieder; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:408-435

[abs][Download PDF]

Efficient and Optimal Fixed-Time Regret with Two Experts

Laura Greenstreet, Nicholas J. A. Harvey, Victor Sanches Portella; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:436-464

[abs][Download PDF]

Limiting Behaviors of Nonconvex-Nonconcave Minimax Optimization via Continuous-Time Systems

Benjamin Grimmer, Haihao Lu, Pratik Worah, Vahab Mirrokni; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:465-487

[abs][Download PDF]

Universally Consistent Online Learning with Arbitrarily Dependent Responses

Steve Hanneke; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:488-497

[abs][Download PDF]

Distinguishing Relational Pattern Languages With a Small Number of Short Strings

Robert C. Holte, S. Mahmoud Mousawi, Sandra Zilles; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:498-514

[abs][Download PDF]

Metric Entropy Duality and the Sample Complexity of Outcome Indistinguishability

Lunjia Hu, Charlotte Peale, Omer Reingold; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:515-552

[abs][Download PDF]

Adversarial Interpretation of Bayesian Inference

Hisham Husain, Jeremias Knoblauch; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:553-572

[abs][Download PDF]

Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure

Hsu Kao, Chen-Yu Wei, Vijay Subramanian; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:573-605

[abs][Download PDF]

Minimization by Incremental Stochastic Surrogate Optimization for Large Scale Nonconvex Problems

Belhal Karimi, Hoi-To Wai, Eric Moulines, Ping Li; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:606-637

[abs][Download PDF]

Polynomial-Time Sum-of-Squares Can Robustly Estimate Mean and Covariance of Gaussians Optimally

Pravesh K. Kothari, Peter Manohar, Brian Hu Zhang; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:638-667

[abs][Download PDF]

Improved rates for prediction and identification of partially observed linear dynamical systems

Holden Lee; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:668-698

[abs][Download PDF]

On the Last Iterate Convergence of Momentum Methods

Xiaoyu Li, Mingrui Liu, Francesco Orabona; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:699-717

[abs][Download PDF]

The Mirror Langevin Algorithm Converges with Vanishing Bias

Ruilin Li, Molei Tao, Santosh S. Vempala, Andre Wibisono; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:718-742

[abs][Download PDF]

On the Initialization for Convex-Concave Min-max Problems

Mingrui Liu, Francesco Orabona; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:743-767

[abs][Download PDF]

Global Riemannian Acceleration in Hyperbolic and Spherical Spaces

David Martínez-Rubio; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:768-826

[abs][Download PDF]

Inductive Bias of Gradient Descent for Weight Normalized Smooth Homogeneous Neural Nets

Depen Morwani, Harish G. Ramaswamy; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:827-880

[abs][Download PDF]

Infinitely Divisible Noise in the Low Privacy Regime

Rasmus Pagh, Nina Mesing Stausholm; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:881-909

[abs][Download PDF]

Scale-Free Adversarial Multi Armed Bandits

Sudeep Raja Putta, Shipra Agrawal; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:910-930

[abs][Download PDF]

Asymptotic Degradation of Linear Regression Estimates with Strategic Data Sources

Benjamin Roussillon, Nicolas Gast, Patrick Loiseau, Panayotis Mertikopoulos; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:931-967

[abs][Download PDF]

Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability

Aadirupa Saha, Akshay Krishnamurthy; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:968-994

[abs][Download PDF]

Faster Rates of Private Stochastic Convex Optimization

Jinyan Su, Lijie Hu, Di Wang; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:995-1002

[abs][Download PDF]

Distributed Online Learning for Joint Regret with Communication Constraints

Dirk Van der Hoeven, Hédi Hadiji, Tim van Erven; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:1003-1042

[abs][Download PDF]

A Model Selection Approach for Corruption Robust Reinforcement Learning

Chen-Yu Wei, Christoph Dann, Julian Zimmert; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:1043-1096

[abs][Download PDF]

TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions

Gellért Weisz, Csaba Szepesvári, András György; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:1097-1137

[abs][Download PDF]

Faster Noisy Power Method

Zhiqiang Xu, Ping Li; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:1138-1164

[abs][Download PDF]

Efficient local planning with linear function approximation

Dong Yin, Botao Hao, Yasin Abbasi-Yadkori, Nevena Lazić, Csaba Szepesvári; Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:1165-1192

[abs][Download PDF]