( en | de | ru )

 

Disambiguation of "Srebro, Nathan"

Author of the publication

copydeleteadd this publication to your clipboard
When is Agnostic Reinforcement Learning Statistically Tractable?

, , , , and . CoRR, (2023)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

Nathan Srebro

Nathan ben-Nathan

Nathan Rosenbaum

Hans Nathan

Siegfried Nathan

 

Other publications of authors with the same name

Semi-Cyclic Stochastic Gradient Descent., , , , and . ICML, volume 97 of Proceedings of Machine Learning Research, page 1764-1773. PMLR, (2019)When is Agnostic Reinforcement Learning Statistically Tractable?, , , , and . CoRR, (2023)Efficiently Learning Neural Networks: What Assumptions May Suffice?, , and . CoRR, (2023)Fair Learning with Private Demographic Data., , and . ICML, volume 119 of Proceedings of Machine Learning Research, page 7066-7075. PMLR, (2020)Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels., , , and . ICML, volume 139 of Proceedings of Machine Learning Research, page 7379-7389. PMLR, (2021)The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication., , , and . COLT, volume 134 of Proceedings of Machine Learning Research, page 4386-4437. PMLR, (2021)Interpolation Learning With Minimum Description Length., and . CoRR, (2023)Semi-Cyclic Stochastic Gradient Descent., , , , and . CoRR, (2019)Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models., , , , and . ICML, volume 97 of Proceedings of Machine Learning Research, page 4683-4692. PMLR, (2019)The Implicit Bias of Gradient Descent on Separable Data, , , , and . (2017)cite arxiv:1710.10345Comment: Final JMLR version, with improved discussions over v3. Main improvements in journal version over conference version (v2 appeared in ICLR): We proved the measure zero case for main theorem (with implications for the rates), and the multi-class case.