Algorithmic Learning Theory 2020: Preface

Aryeh Kontorovich, Gergely Neu; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:1-2

[abs][Download PDF]

Optimal multiclass overfitting by sequence reconstruction from Hamming queries

Jayadev Acharya, Ananda Theertha Suresh; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:3-21

[abs][Download PDF]

Leverage Score Sampling for Faster Accelerated Regression and ERM

Naman Agarwal, Sham Kakade, Rahul Kidambi, Yin-Tat Lee, Praneeth Netrapalli, Aaron Sidford; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:22-47

[abs][Download PDF]

On Learnability wih Computable Learners

Sushant Agarwal, Nivasini Ananthakrishnan, Shai Ben-David, Tosca Lechner, Ruth Urner; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:48-60

[abs][Download PDF]

Optimal $δ$-Correct Best-Arm Selection for Heavy-Tailed Distributions

Shubhada Agrawal, Sandeep Juneja, Peter Glynn; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:61-110

[abs][Download PDF]

A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updates

Yossi Arjevani, Ohad Shamir, Nathan Srebro; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:111-132

[abs][Download PDF]

Distribution Free Learning with Local Queries

Galit Bary-Weisberg, Amit Daniely, Shai Shalev-Shwartz; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:133-147

[abs][Download PDF]

Robust Algorithms for Online $k$-means Clustering

Aditya Bhaskara, Aravinda Kanchana Ruwanpathirana; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:148-173

[abs][Download PDF]

What relations are reliably embeddable in Euclidean space?

Robi Bhattacharjee, Sanjoy Dasgupta; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:174-195

[abs][Download PDF]

First-Order Bayesian Regret Analysis of Thompson Sampling

Sébastien Bubeck, Mark Sellke; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:196-233

[abs][Download PDF]

Cooperative Online Learning: Keeping your Neighbors Updated

Nicolò Cesa-Bianchi, Tommaso Cesari, Claire Monteleoni; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:234-250

[abs][Download PDF]

Cautious Limit Learning

Vanja Doskoč, Timo Kötzing; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:251-276

[abs][Download PDF]

Interactive Learning of a Dynamic Structure

Ehsan Emamjomeh-Zadeh, David Kempe, Mohammad Mahdian, Robert E. Schapire; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:277-296

[abs][Download PDF]

Sampling Without Compromising Accuracy in Adaptive Data Analysis

Benjamin Fish, Lev Reyzin, Benjamin I. P. Rubinstein; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:297-318

[abs][Download PDF]

An adaptive stochastic optimization algorithm for resource allocation

Xavier Fontaine, Shie Mannor, Vianney Perchet; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:319-363

[abs][Download PDF]

Adversarially Robust Learning Could Leverage Computational Hardness.

Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mahmoody Mohammad; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:364-385

[abs][Download PDF]

Exponentiated Gradient Meets Gradient Descent

Udaya Ghai, Elad Hazan, Yoram Singer; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:386-407

[abs][Download PDF]

The Nonstochastic Control Problem

Elad Hazan, Sham Kakade, Karan Singh; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:408-421

[abs][Download PDF]

On the Expressive Power of Kernel Methods and the Efficiency of Kernel Learning by Association Schemes

Kothari K. Pravesh, Livni Roi; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:422-450

[abs][Download PDF]

Don’t Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop

Dmitry Kovalev, Samuel Horváth, Peter Richtárik; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:451-467

[abs][Download PDF]

Algebraic and Analytic Approaches for Parameter Learning in Mixture Models

Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:468-489

[abs][Download PDF]

Robust guarantees for learning an autoregressive filter

Holden Lee, Cyril Zhang; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:490-517

[abs][Download PDF]

Thompson Sampling for Adversarial Bit Prediction

Yuval Lewi, Haim Kaplan, Yishay Mansour; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:518-553

[abs][Download PDF]

On Learning Causal Structures from Non-Experimental Data without Any Faithfulness Assumption

Hanti Lin, Jiji Zhang; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:554-582

[abs][Download PDF]

On the Complexity of Proper Distribution-Free Learning of Linear Classifiers

Philip M. Long, Raphael J. Long; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:583-591

[abs][Download PDF]

Feedback graph regret bounds for Thompson Sampling and UCB

Thodoris Lykouris, Éva Tardos, Drishti Wali; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:592-614

[abs][Download PDF]

Toward universal testing of dynamic network models

Abram Magner, Wojciech Szpankowski; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:615-633

[abs][Download PDF]

On the Analysis of EM for truncated mixtures of two Gaussians

Sai Ganesh Nagarajan, Ioannis Panageas; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:634-659

[abs][Download PDF]

A Non-Trivial Algorithm Enumerating Relevant Features over Finite Fields

Mikito Nanashima; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:660-686

[abs][Download PDF]

Privately Answering Classification Queries in the Agnostic PAC Model

Anupama Nandi, Raef Bassily; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:687-703

[abs][Download PDF]

Efficient Private Algorithms for Learning Large-Margin Halfspaces

Huy Lê Nguyễn, Jonathan Ullman, Lydia Zakynthinou; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:704-724

[abs][Download PDF]

Finding Robust Nash equilibria

Vianney Perchet; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:725-751

[abs][Download PDF]

Top-$k$ Combinatorial Bandits with Full-Bandit Feedback

Idan Rejwan, Yishay Mansour; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:752-776

[abs][Download PDF]

Bandit Algorithms Based on Thompson Sampling for Bounded Reward Distributions

Charles Riou, Junya Honda; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:777-826

[abs][Download PDF]

Approximate Representer Theorems in Non-reflexive Banach Spaces

Kevin Schlegel; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:827-844

[abs][Download PDF]

Online Non-Convex Learning: Following the Perturbed Leader is Optimal

Arun Sai Suggala, Praneeth Netrapalli; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:845-861

[abs][Download PDF]

Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling

Cindy Trinh, Emilie Kaufmann, Claire Vernade, Richard Combes; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:862-889

[abs][Download PDF]

Mixing Time Estimation in Ergodic Markov Chains from a Single Trajectory with Contraction Methods

Geoffrey Wolfer; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:890-905

[abs][Download PDF]

Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies

Tom Zahavy, Avinatan Hasidim, Haim Kaplan, Yishay Mansour; Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:906-934

[abs][Download PDF]