Computational Learning Theory: compact representation, efficient computation, and societal challenges in learning MDPs

Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations

Autorzy: Ayush Sekhari, Christoph Dann, Mehryar Mohri, Yishay Mansour, Karthik Sridharan
Opublikowane w: 2021
Wydawca: Conference on Neural Information Processing Systems

A Constant Approximation Algorithm for Sequential Random-Order No-Substitution k-Median Clustering

Autorzy: Tom Hess, Michal Moshkovitz, Sivan Sabato
Opublikowane w: 2021
Wydawca: Conference on Neural Information Processing Systems

Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation

Autorzy: Orin Levy, Alon Cohen, Asaf B. Cassel, Yishay Mansour
Opublikowane w: ICML 2023c, 2023
Wydawca: PMLR

Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback

Autorzy: Tiancheng Jin, Tal Lancewicki, Haipeng Luo, Yishay Mansour, Aviv Rosenberg
Opublikowane w: NeurIPS 2022b, 2022
Wydawca: NeurIPS 2022, Arxiv, European Workshop on Reinforcement Learning (EWRL 2022), Complex Feedback in Online Learning (CFOL ), 2022

Stochastic Strategic Patient Buyers: Revenue maximization using posted prices

Autorzy: Eitan-Hai Mashiah, Idan Attias, Yishay Mansour
Opublikowane w: AAAI 2023b, 2023
Wydawca: AAAI

Learning Adversarial Markov Decision Processes with Delayed Feedback

Autorzy: Tal Lancewicki, Aviv Rosenberg, Yishay Mansour
Opublikowane w: 2022
Wydawca: the Association for the Advancement of Artificial Intelligence ; Cambridge University Press

Oracle-Efficient Reinforcement Learning in Factored MDPs with Unknown Structure

Autorzy: Aviv Rosenberg, Yishay Mansour
Opublikowane w: 2021
Wydawca: NeurIPS

A Learning-Theoretic Framework for Certified Auditing of Machine Learning Models

Autorzy: Chhavi Yadav, Michal Moshkovitz, Kamalika Chaudhuri
Opublikowane w: NeurIPS 2022c, 2022
Wydawca: NeurIPS 2022, Arxiv, European Workshop on Reinforcement Learning (EWRL 2022), Complex Feedback in Online Learning (CFOL ), 2022

Benign Underfitting of Stochastic Gradient Descent

Autorzy: Tomer Koren, Roi Livni, Yishay Mansour, Uri Sherman
Opublikowane w: NeurIPS 2022a, 2022
Wydawca: NeurIPS 2022

Prediction with Corrupted Expert Advice

Autorzy: Idan Amir, Idan Attias, Tomer Koren, Yishay Mansour, Roi Livni
Opublikowane w: 2020
Wydawca: NeurIPS 2020

Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure

Autorzy: Aviv Rosenberg, Yishay Mansour
Opublikowane w: 2021
Wydawca: Conference on Neural Information Processing Systems

Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation

Autorzy: Uri Sherman, Tomer Koren, Yishay Mansour:
Opublikowane w: ICML 2023d, 2023
Wydawca: PMLR

A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability

Autorzy: Idan Attias, Steve Hanneke, Yishay Mansour
Opublikowane w: NeurIPS 2022d, 2022
Wydawca: NeurIPS

Stochastic Shortest Path with Adversarially Changing Costs

Autorzy: Aviv Rosenberg, Yishay Mansour
Opublikowane w: IJCAI 2021, 2021
Wydawca: IJCAI

Optimal Rates for Random Order Online Optimization

Autorzy: Uri Sherman, Tomer Koren, Yishay Mansour
Opublikowane w: 2021
Wydawca: Conference on Neural Information Processing Systems

Regret Minimization and Convergence to Equilibria in General-sum Markov Games

Autorzy: Liad Erez, Tal Lancewicki, Uri Sherman, Tomer Koren, Yishay Mansour
Opublikowane w: ICML 2023b, 2023
Wydawca: PMLR

Dynamic algorithms against an adaptive adversary: generic constructions and lower bounds.

Autorzy: Amos Beimel, Haim Kaplan, Yishay Mansour, Kobbi Nissim, Thatchaphol Saranurak, Uri Stemmer
Opublikowane w: STOC 2022, 2022
Wydawca: STOC 2022

Reinforcement Learning Can Be More Efficient with Multiple Rewards

Autorzy: Christoph Dann, Yishay Mansour, Mehryar Mohri
Opublikowane w: ICML 2023a, 2023
Wydawca: International Conference on Machine Learning

Learning Efficiently Function Approximation for Contextual MDP

Autorzy: Orin Levy, Yishay Mansour
Opublikowane w: 2022
Wydawca: European Workshop on Reinforcement Learning

Sample Complexity of Uniform Convergence for Multicalibration

Autorzy: Eliran Shabat, Lee Cohen, Yishay Mansour
Opublikowane w: 2020
Wydawca: Conference on Neural Information Processing Systems

FriendlyCore: Practical Differentially Private Aggregation

Autorzy: Eliad Tsfadia, Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer
Opublikowane w: ICML 2022d, 2022
Wydawca: ICML 2022

Modeling Attrition in Recommender Systems with Departing Bandits

Autorzy: Omer Ben-Porat, Lee Cohen, Liu Leqi, Zachary C. Lipton, Yishay Mansour
Opublikowane w: 2022
Wydawca: the Association for the Advancement of Artificial Intelligence

Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions

Autorzy: Tal Lancewicki, Shahar Segal, Tomer Koren, Yishay Mansour
Opublikowane w: 2021
Wydawca: Cambridge University Press

Dueling Bandits with Team Comparisons

Autorzy: Lee Cohen, Yishay Mansour, Ulrike Schmidt-Kraepelin
Opublikowane w: 2021
Wydawca: Conference on Neural Information Processing Systems

Separating Adaptive Streaming from Oblivious Streaming

Autorzy: Haim Kaplan, Yishay Mansour, Kobbi Nissim, Uri Stemmer
Opublikowane w: 2021
Wydawca: The International Association for Cryptologic Research

Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity

Autorzy: Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia
Opublikowane w: 2020
Wydawca: Conference on Neural Information Processing Systems

Differentially Private Multi-Armed Bandits in the Shuffle Model

Autorzy: Jay Tenenbaum, Haim Kaplan, Yishay Mansour, Uri Stemmer
Opublikowane w: 2021
Wydawca: Conference on Neural Information Processing Systems

Minimax Regret for Stochastic Shortest Path

Autorzy: Alon Cohen, Yonathan Efroni, Yishay Mansour, Aviv Rosenberg
Opublikowane w: 2021
Wydawca: Conference on Neural Information Processing Systems

Differentially-Private Clustering of Easy Instances

Autorzy: Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia
Opublikowane w: ICML 2021f, 2021
Wydawca: International Conference on Machine Learning 2021 (ICML)

Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation

Autorzy: Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
Opublikowane w: ICML 2022b, 2022
Wydawca: International Conference on Machine Learning (ICML 2022)

Optimism in Face of a Context: Regret Guratees for Stochastic Contextual MDP

Autorzy: Orin Levy, Yishay Mansour
Opublikowane w: AAAI 2023a, 2022
Wydawca: AAAI 2023, European Workshop on Reinforcement Learning (EWRL 2022), Complex Feedback in Online Learning (CFOL), 2022

Fair Wrapping for Black-box Predictions

Autorzy: Alexander Soen, Ibrahim Alabdulmohsin, Sanmi Koyejo, Yishay Mansour, Nyalleng Moorosi, Richard Nock, Ke Sun, Lexing Xie
Opublikowane w: NeurIPS 2022e, 2022
Wydawca: NeurIPS

Adversarial Dueling Bandits

Autorzy: Aadirupa Saha, Tomer Koren, Yishay Mansour
Opublikowane w: 2021
Wydawca: Cambridge University Press

Cooperative Online Learning in Stochastic and Adversarial MDPs

Autorzy: Tal Lancewicki, Aviv Rosenberg, Yishay Mansour
Opublikowane w: ICML 2022c, 2022
Wydawca: International Conference on Machine Learning (ICML 2022), European Workshop on Reinforcement Learning (EWRL 2022)

The Sparse Vector Technique, Revisited

Autorzy: Haim Kaplan, Yishay Mansour, Uri Stemmer
Opublikowane w: 2021
Wydawca: Association for Computational Learning

Dueling Convex Optimization

Autorzy: Aadirupa Saha, Tomer Koren, Yishay Mansour
Opublikowane w: ICML 2021e, 2021
Wydawca: International Conference on Machine Learning

Adversarially Robust Streaming Algorithms via Differential Privacy

Autorzy: Avinatan Hassidim, Haim Kaplan, Yishay Mansour, Yossi Matias, Uri Stemmer:
Opublikowane w: JACM, NeurIPS 2020d, Numer Journal of the ACM 69(6): 42:1-42:14 2022,, 2022, ISSN 0004-5411
Wydawca: Association for Computing Machinary, Inc.

Finding Safe Zones of Markov Decision Processes Policies

Autorzy: Lee Cohen, Yishay Mansour, Michal Moshkovitz
Opublikowane w: 2022
Wydawca: Archive

There is no Accuracy-Interpretability Tradeoff in Reinforcement Learning for Mazes

Autorzy: Yishay Mansour, Michal Moshkovitz, Cynthia Rudin
Opublikowane w: 2022
Wydawca: Arxiv

Differentially-Private Bayes Consistency

Autorzy: Olivier Bousquet, Haim Kaplan, Aryeh Kontorovich, Yishay Mansour, Shay Moran, Menachem Sadigurschi, Uri Stemmer
Opublikowane w: 2022
Wydawca: Archive

Publikacje

Udostępnij tę stronę

Pobierz