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

Project Information

COLT-MDP

Grant agreement ID: 882396

DOI

10.3030/882396

EC signature date 29 April 2020

Start date 1 October 2020

End date 30 September 2026

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost

€ 1 878 125,00

EU contribution

€ 1 878 125,00

Coordinated by

TEL AVIV UNIVERSITY
Israel

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Conference proceedings (49)

Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations

Author(s): Ayush Sekhari, Christoph Dann, Mehryar Mohri, Yishay Mansour, Karthik Sridharan
Published in: NeurIPS 2021b, 2021
Publisher: Conference on Neural Information Processing Systems

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

Author(s): Tom Hess, Michal Moshkovitz, Sivan Sabato
Published in: NeurIPS 2021g, 2021
Publisher: Conference on Neural Information Processing Systems

Principal-Agent Reward Shaping in MDPs

Author(s): Omer Ben-Porat, Yishay Mansour, Michal Moshkovitz, Boaz Taitler
Published in: AAAI 2024, 2024
Publisher: AAAI 2024

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

Author(s): Orin Levy, Alon Cohen, Asaf B. Cassel, Yishay Mansour
Published in: ICML 2023c, 2023
Publisher: PMLR

Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback

Author(s): Tiancheng Jin, Tal Lancewicki, Haipeng Luo, Yishay Mansour, Aviv Rosenberg
Published in: NeurIPS 2022b, 2022
Publisher: NeurIPS 2022, Arxiv, European Workshop on Reinforcement Learning (EWRL 2022), Complex Feedback in Online Learning (CFOL ), 2022

Learnability Gaps of Strategic Classification

Author(s): Lee Cohen, Yishay Mansour, Shay Moran, Han Shao
Published in: COLT 2024, 2024
Publisher: COLT 2024

Stochastic Strategic Patient Buyers: Revenue maximization using posted prices

Author(s): Eitan-Hai Mashiah, Idan Attias, Yishay Mansour
Published in: AAAI 2023b, 2023
Publisher: AAAI

Learning Adversarial Markov Decision Processes with Delayed Feedback

Author(s): Tal Lancewicki, Aviv Rosenberg, Yishay Mansour
Published in: AAAI 2022b, 2022
Publisher: the Association for the Advancement of Artificial Intelligence ; Cambridge University Press

Oracle-Efficient Reinforcement Learning in Factored MDPs with Unknown Structure

Author(s): Aviv Rosenberg, Yishay Mansour
Published in: NeurIPS 2021h, 2021
Publisher: NeurIPS

Non-stochastic Bandits With Evolving Observations

Author(s): Yogev Bar-On, Yishay Mansour
Published in: ALT 2025, 2025
Publisher: ALT 2025

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

Author(s): Chhavi Yadav, Michal Moshkovitz, Kamalika Chaudhuri
Published in: NeurIPS 2022c, 2022
Publisher: NeurIPS 2022, Arxiv, European Workshop on Reinforcement Learning (EWRL 2022), Complex Feedback in Online Learning (CFOL ), 2022

Benign Underfitting of Stochastic Gradient Descent

Author(s): Tomer Koren, Roi Livni, Yishay Mansour, Uri Sherman
Published in: NeurIPS 2022a, 2022
Publisher: NeurIPS 2022

A Theory of Interpretable Approximations

Author(s): Marco Bressan, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen
Published in: COLT 2024, 2024
Publisher: COLT 2024

Prediction with Corrupted Expert Advice

Author(s): Idan Amir, Idan Attias, Tomer Koren, Yishay Mansour, Roi Livni
Published in: NeurIPS 2020a, 2020
Publisher: NeurIPS 2020

Eluder-based Regret for Stochastic Contextual MDPs

Author(s): Orin Levy, Asaf Cassel, Alon Cohen, Yishay Mansour
Published in: FC 2024, 2024
Publisher: FC 2024

Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure

Author(s): Aviv Rosenberg, Yishay Mansour
Published in: NeurIPS 2021e, 2021
Publisher: Conference on Neural Information Processing Systems

Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation

Author(s): Uri Sherman, Tomer Koren, Yishay Mansour:
Published in: ICML 2023d, 2023
Publisher: PMLR

A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability

Author(s): Idan Attias, Steve Hanneke, Yishay Mansour
Published in: NeurIPS 2022d, 2022
Publisher: NeurIPS

Stochastic Shortest Path with Adversarially Changing Costs

Author(s): Aviv Rosenberg, Yishay Mansour
Published in: IJCAI 2021, 2021
Publisher: IJCAI

Optimal Rates for Random Order Online Optimization

Author(s): Uri Sherman, Tomer Koren, Yishay Mansour
Published in: NeurIPS 2021d, 2021
Publisher: Conference on Neural Information Processing Systems

he Real Price of Bandit Information in Multiclass Classification

Author(s): Liad Erez, Alon Cohen, Tomer Koren, Yishay Mansour, Shay Moran
Published in: COLT 2024, 2024
Publisher: COLT 2024

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

Author(s): Liad Erez, Tal Lancewicki, Uri Sherman, Tomer Koren, Yishay Mansour
Published in: ICML 2023b, 2023
Publisher: PMLR

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

Author(s): Amos Beimel, Haim Kaplan, Yishay Mansour, Kobbi Nissim, Thatchaphol Saranurak, Uri Stemmer
Published in: STOC 2022, 2022
Publisher: STOC 2022

Reinforcement Learning Can Be More Efficient with Multiple Rewards

Author(s): Christoph Dann, Yishay Mansour, Mehryar Mohri
Published in: ICML 2023a, 2023
Publisher: International Conference on Machine Learning

Data Reconstruction: When You See It and When You Don't

Author(s): Edith Cohen, Haim Kaplan, Yishay Mansour, Shay Moran, Kobbi Nissim, Uri Stemmer, Eliad Tsfadia
Published in: ITCS 2025, 2025
Publisher: ITCS 2025

Learning Efficiently Function Approximation for Contextual MDP

Author(s): Orin Levy, Yishay Mansour
Published in: EWRL 2022, 2022
Publisher: European Workshop on Reinforcement Learning

Sample Complexity of Uniform Convergence for Multicalibration

Author(s): Eliran Shabat, Lee Cohen, Yishay Mansour
Published in: NeurIPS 2020c, 2020
Publisher: Conference on Neural Information Processing Systems

FriendlyCore: Practical Differentially Private Aggregation

Author(s): Eliad Tsfadia, Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer
Published in: ICML 2022d, 2022
Publisher: ICML 2022

Modeling Attrition in Recommender Systems with Departing Bandits

Author(s): Omer Ben-Porat, Lee Cohen, Liu Leqi, Zachary C. Lipton, Yishay Mansour
Published in: AAAI 2022a, 2022
Publisher: the Association for the Advancement of Artificial Intelligence

Faster Convergence with MultiWay Preferences.

Author(s): Aadirupa Saha, Vitaly Feldman, Yishay Mansour, Tomer Koren
Published in: AISTATS 2024, 2024, Page(s) 433-441
Publisher: AISTATS 2024

Partially Interpretable Models with Guarantees on Coverage and Accuracy

Author(s): Nave Frost, Zachary C. Lipton, Yishay Mansour, Michal Moshkovitz:
Published in: ALT2024, 2024
Publisher: ALT 2024

Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions

Author(s): Tal Lancewicki, Shahar Segal, Tomer Koren, Yishay Mansour
Published in: ICML 2021g, 2021
Publisher: Cambridge University Press

Dueling Bandits with Team Comparisons

Author(s): Lee Cohen, Yishay Mansour, Ulrike Schmidt-Kraepelin
Published in: NeurIPS 2021c, 2021
Publisher: Conference on Neural Information Processing Systems

Separating Adaptive Streaming from Oblivious Streaming

Author(s): Haim Kaplan, Yishay Mansour, Kobbi Nissim, Uri Stemmer
Published in: CRYPTO 2021, 2021
Publisher: The International Association for Cryptologic Research

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

Author(s): Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia
Published in: NeurIPS 2020b, 2020
Publisher: Conference on Neural Information Processing Systems

Differentially Private Multi-Armed Bandits in the Shuffle Model

Author(s): Jay Tenenbaum, Haim Kaplan, Yishay Mansour, Uri Stemmer
Published in: NeurIPS 2021a, 2021
Publisher: Conference on Neural Information Processing Systems

Learning-Augmented Algorithms with Explicit Predictors

Author(s): Marek Eliás, Haim Kaplan, Yishay Mansour, Shay Moran
Published in: NeurIPS 2024, 2024
Publisher: NeurIPS 2024

Minimax Regret for Stochastic Shortest Path

Author(s): Alon Cohen, Yonathan Efroni, Yishay Mansour, Aviv Rosenberg
Published in: NeurIPS 2021f, 2021
Publisher: Conference on Neural Information Processing Systems

Differentially-Private Clustering of Easy Instances

Author(s): Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia
Published in: ICML 2021f, 2021
Publisher: International Conference on Machine Learning 2021 (ICML)

Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation

Author(s): Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
Published in: ICML 2022b, 2022
Publisher: International Conference on Machine Learning (ICML 2022)

Rate-Optimal Policy Optimization for Linear Markov Decision Processes

Author(s): Uri Sherman, Alon Cohen, Tomer Koren, Yishay Mansour
Published in: ICML 2024, 2024
Publisher: ICML 2024

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

Author(s): Orin Levy, Yishay Mansour
Published in: AAAI 2023a, 2022
Publisher: AAAI 2023, European Workshop on Reinforcement Learning (EWRL 2022), Complex Feedback in Online Learning (CFOL), 2022

Fair Wrapping for Black-box Predictions

Author(s): Alexander Soen, Ibrahim Alabdulmohsin, Sanmi Koyejo, Yishay Mansour, Nyalleng Moorosi, Richard Nock, Ke Sun, Lexing Xie
Published in: NeurIPS 2022e, 2022
Publisher: NeurIPS

Optimal Publishing Strategies on a Base Layer

Author(s): Yogev Bar-On, Yishay Mansour
Published in: FC 2024, 2024
Publisher: FC2024

Adversarial Dueling Bandits

Author(s): Aadirupa Saha, Tomer Koren, Yishay Mansour
Published in: ICML 2021a, 2021
Publisher: Cambridge University Press

Cooperative Online Learning in Stochastic and Adversarial MDPs

Author(s): Tal Lancewicki, Aviv Rosenberg, Yishay Mansour
Published in: ICML 2022c, 2022
Publisher: International Conference on Machine Learning (ICML 2022), European Workshop on Reinforcement Learning (EWRL 2022)

Fast Rates for Bandit PAC Multiclass Classification

Author(s): Liad Erez, Alon Cohen, Tomer Koren, Yishay Mansour, Shay Moran
Published in: NeurIPS 2024, Issue 2024, 2024
Publisher: NeurIPS 2024

The Sparse Vector Technique, Revisited

Author(s): Haim Kaplan, Yishay Mansour, Uri Stemmer
Published in: COLT 2021, 2021
Publisher: Association for Computational Learning

Dueling Convex Optimization

Author(s): Aadirupa Saha, Tomer Koren, Yishay Mansour
Published in: ICML 2021e, 2021
Publisher: International Conference on Machine Learning

Book chapters (2)

Uniswap Liquidity Provision: An Online Learning Approach

Author(s): Yogev Bar-On, Yishay Mansour
Published in: Lecture Notes in Computer Science, Financial Cryptography and Data Security. FC 2023 International Workshops, 2023, Page(s) 247-261
Publisher: Springer Nature Switzerland
DOI: 10.1007/978-3-031-48806-1_16

A Theory of Learning with Competing Objectives and User Feedback

Author(s): Pranjal Awasthi, Corinna Cortes, Yishay Mansour, Mehryar Mohri
Published in: Lecture Notes in Computer Science, Artificial Intelligence and Image Analysis, 2024, Page(s) 10-49
Publisher: Springer Nature Switzerland
DOI: 10.1007/978-3-031-63735-3_2

Peer reviewed articles (2)

Adversarially Robust Streaming Algorithms via Differential Privacy

Author(s): Avinatan Hassidim, Haim Kaplan, Yishay Mansour, Yossi Matias, Uri Stemmer:
Published in: JACM, NeurIPS 2020d, Issue Journal of the ACM 69(6): 42:1-42:14 2022,, 2022, ISSN 0004-5411
Publisher: Association for Computing Machinary, Inc.

A machine-learning-based alternative to phylogenetic bootstrap

Author(s): Noa Ecker , Dorothée Huchon , Yishay Mansour , Itay Mayrose , Tal Pupko
Published in: Bioinformatics, Volume 40, Issue 1, July 2024, 2024, Page(s) Pages i208–i217,, ISSN 1367-4803
Publisher: Oxford University Press

Other (3)

Finding Safe Zones of Markov Decision Processes Policies

Author(s): Lee Cohen, Yishay Mansour, Michal Moshkovitz
Published in: 2022
Publisher: Archive

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

Author(s): Yishay Mansour, Michal Moshkovitz, Cynthia Rudin
Published in: 2022
Publisher: Arxiv

Differentially-Private Bayes Consistency

Author(s): Olivier Bousquet, Haim Kaplan, Aryeh Kontorovich, Yishay Mansour, Shay Moran, Menachem Sadigurschi, Uri Stemmer
Published in: 2022
Publisher: Archive