Ohad Shamir

12 catalog papers. Identity-linked publications and additional name matches are distinguished below.

ORCID: 0009-0002-0919-3163

Publications

• An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization — Journal of Machine Learning Research 2024 (name-matched, not ORCID-linked)
• The Implicit Bias of Benign Overfitting — Journal of Machine Learning Research 2023 (name-matched, not ORCID-linked)
• Oracle Complexity in Nonsmooth Nonconvex Optimization — Journal of Machine Learning Research 2022 (name-matched, not ORCID-linked)
• Gradient Methods Never Overfit On Separable Data — Journal of Machine Learning Research 2021 (name-matched, not ORCID-linked)
• Distribution-Specific Hardness of Learning Neural Networks — Journal of Machine Learning Research 2018 (name-matched, not ORCID-linked)
• An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback — Journal of Machine Learning Research 2017 (name-matched, not ORCID-linked)
• On Lower and Upper Bounds in Smooth and Strongly Convex Optimization — Journal of Machine Learning Research 2016 (name-matched, not ORCID-linked)
• The Sample Complexity of Learning Linear Predictors with the Squared Loss — Journal of Machine Learning Research 2015 (name-matched, not ORCID-linked)
• Matrix Completion with the Trace Norm: Learning, Bounding, and Transducing — Journal of Machine Learning Research 2014 (name-matched, not ORCID-linked)
• Optimal Distributed Online Prediction Using Mini-Batches — Journal of Machine Learning Research 2012 (name-matched, not ORCID-linked)
• Efficient Learning with Partially Observed Attributes — Journal of Machine Learning Research 2011 (name-matched, not ORCID-linked)
• Learnability, Stability and Uniform Convergence — Journal of Machine Learning Research 2010 (name-matched, not ORCID-linked)