Patrick Rebeschini

CoRR, March, 2025

Learning mirror maps in policy mirror descent.

[BibT_eX]

[DOI]

Sebastian Rene Towers

Silvia Sapora

Chris Lu

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization.

[BibT_eX]

[DOI]

Simon Vary

David Martínez-Rubio

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

Robust Gradient Descent for Phase Retrieval.

[BibT_eX]

[DOI]

Alex Buna

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Learning Loss Landscapes in Preference Optimization.

[BibT_eX]

[DOI]

Silvia Sapora

Jakob Nicolaus Foerster

Yee Whye Teh

CoRR, 2024

Differentiable Cost-Parameterized Monge Map Estimators.

[BibT_eX]

[DOI]

CoRR, 2024

Meta-learning the mirror map in policy mirror descent.

[BibT_eX]

[DOI]

CoRR, 2024

Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity.

[BibT_eX]

[DOI]

Emmeran Johnson

Ciara Pike-Burke

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Generalization Bounds for Label Noise Stochastic Gradient Descent.

[BibT_eX]

[DOI]

Jung Eun Huh

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

A Novel Framework for Policy Mirror Descent with General Parametrization and Linear Convergence.

[BibT_eX]

[DOI]

Rui Yuan

CoRR, 2023

Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes.

[BibT_eX]

[DOI]

Emmeran Johnson

Ciara Pike-Burke

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence.

[BibT_eX]

[DOI]

Rui Yuan

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization.

[BibT_eX]

[DOI]

CoRR, 2022

Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Condition.

[BibT_eX]

[DOI]

Tomas Vaskevicius

CoRR, 2022

2021

Dimension-Free Rates for Natural Policy Gradient in Multi-Agent Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2021

Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models?

[BibT_eX]

[DOI]

Edgar Dobriban

CoRR, 2021

Nearly Minimax-Optimal Rates for Noisy Sparse Phase Retrieval via Early-Stopped Mirror Descent.

[BibT_eX]

[DOI]

CoRR, 2021

Implicit Regularization in Matrix Sensing via Mirror Descent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Distributed Machine Learning with Sparse Heterogeneous Data.

[BibT_eX]

[DOI]

Sahand Negahban

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

On Optimal Interpolation in Linear Regression.

[BibT_eX]

[DOI]

Eduard Oravkin

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Time-independent Generalization Bounds for SGLD in Non-convex Settings.

[BibT_eX]

[DOI]

Tyler Farghly

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Hadamard Wirtinger Flow for Sparse Phase Retrieval.

[BibT_eX]

[DOI]

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Graph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient Descent.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2020

A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

The Statistical Complexity of Early-Stopped Mirror Descent.

[BibT_eX]

[DOI]

Tomas Vaskevicius

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Decentralised Learning with Random Features and Distributed Gradient Descent.

[BibT_eX]

[DOI]

Lorenzo Rosasco

Proceedings of the 37th International Conference on Machine Learning, 2020

2019

Locality in Network Optimization.

[BibT_eX]

[DOI]

IEEE Trans. Control. Netw. Syst., 2019

A New Approach to Laplacian Solvers and Flow Problems.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2019

Implicit Regularization for Optimal Sparse Recovery.

[BibT_eX]

[DOI]

Tomas Vaskevicius

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Optimal Statistical Rates for Decentralised Non-Parametric Regression with Linear Speed-Up.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Decentralized Cooperative Stochastic Bandits.

[BibT_eX]

[DOI]

David Martínez-Rubio

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2018

Decentralized Cooperative Stochastic Multi-armed Bandits.

[BibT_eX]

[DOI]

David Martínez-Rubio

CoRR, 2018

2017

Accelerated consensus via Min-Sum Splitting.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

2016

Decay of correlation in network flow problems.

[BibT_eX]

[DOI]

Proceedings of the 2016 Annual Conference on Information Science and Systems, 2016

2015

Fast Mixing for Discrete Point Processes.

[BibT_eX]

[DOI]

Amin Karbasi

Proceedings of The 28th Conference on Learning Theory, 2015

2014

Nonlinear Filtering in High Dimension

[BibT_eX]

[DOI]