Alert button
Picture for Mehryar Mohri

Mehryar Mohri

Alert button

Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality

Jun 20, 2022
Teodor V. Marinov, Mehryar Mohri, Julian Zimmert

Figure 1 for Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality
Figure 2 for Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality
Figure 3 for Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality
Viaarxiv icon

Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation

Jun 19, 2022
Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan

Figure 1 for Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Figure 2 for Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Figure 3 for Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Viaarxiv icon

Strategizing against Learners in Bayesian Games

May 17, 2022
Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan

Viaarxiv icon

$\mathscr{H}$-Consistency Estimation Error of Surrogate Loss Minimizers

May 16, 2022
Pranjal Awasthi, Anqi Mao, Mehryar Mohri, Yutao Zhong

Figure 1 for $\mathscr{H}$-Consistency Estimation Error of Surrogate Loss Minimizers
Figure 2 for $\mathscr{H}$-Consistency Estimation Error of Surrogate Loss Minimizers
Figure 3 for $\mathscr{H}$-Consistency Estimation Error of Surrogate Loss Minimizers
Figure 4 for $\mathscr{H}$-Consistency Estimation Error of Surrogate Loss Minimizers
Viaarxiv icon

Differentially Private Learning with Margin Guarantees

Apr 21, 2022
Raef Bassily, Mehryar Mohri, Ananda Theertha Suresh

Figure 1 for Differentially Private Learning with Margin Guarantees
Figure 2 for Differentially Private Learning with Margin Guarantees
Viaarxiv icon

On the Existence of the Adversarial Bayes Classifier (Extended Version)

Dec 03, 2021
Pranjal Awasthi, Natalie S. Frank, Mehryar Mohri

Figure 1 for On the Existence of the Adversarial Bayes Classifier (Extended Version)
Figure 2 for On the Existence of the Adversarial Bayes Classifier (Extended Version)
Figure 3 for On the Existence of the Adversarial Bayes Classifier (Extended Version)
Figure 4 for On the Existence of the Adversarial Bayes Classifier (Extended Version)
Viaarxiv icon

A Field Guide to Federated Optimization

Jul 14, 2021
Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H. Brendan McMahan, Blaise Aguera y Arcas, Maruan Al-Shedivat, Galen Andrew, Salman Avestimehr, Katharine Daly, Deepesh Data, Suhas Diggavi, Hubert Eichner, Advait Gadhikar, Zachary Garrett, Antonious M. Girgis, Filip Hanzely, Andrew Hard, Chaoyang He, Samuel Horvath, Zhouyuan Huo, Alex Ingerman, Martin Jaggi, Tara Javidi, Peter Kairouz, Satyen Kale, Sai Praneeth Karimireddy, Jakub Konecny, Sanmi Koyejo, Tian Li, Luyang Liu, Mehryar Mohri, Hang Qi, Sashank J. Reddi, Peter Richtarik, Karan Singhal, Virginia Smith, Mahdi Soltanolkotabi, Weikang Song, Ananda Theertha Suresh, Sebastian U. Stich, Ameet Talwalkar, Hongyi Wang, Blake Woodworth, Shanshan Wu, Felix X. Yu, Honglin Yuan, Manzil Zaheer, Mi Zhang, Tong Zhang, Chunxiang Zheng, Chen Zhu, Wennan Zhu

Figure 1 for A Field Guide to Federated Optimization
Figure 2 for A Field Guide to Federated Optimization
Figure 3 for A Field Guide to Federated Optimization
Figure 4 for A Field Guide to Federated Optimization
Viaarxiv icon

Adapting to Misspecification in Contextual Bandits

Jul 12, 2021
Dylan J. Foster, Claudio Gentile, Mehryar Mohri, Julian Zimmert

Viaarxiv icon

Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning

Jul 02, 2021
Christoph Dann, Teodor V. Marinov, Mehryar Mohri, Julian Zimmert

Figure 1 for Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning
Figure 2 for Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning
Figure 3 for Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning
Figure 4 for Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning
Viaarxiv icon

Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations

Jun 22, 2021
Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan

Figure 1 for Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations
Figure 2 for Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations
Viaarxiv icon