Murat A. Erdogdu
Stanford University
H-index: 25
North America-United States
Top articles of Murat A. Erdogdu
Title | Journal | Author(s) | Publication Date |
|---|---|---|---|
Optimal Excess Risk Bounds for Empirical Risk Minimization on -Norm Linear Regression | Advances in Neural Information Processing Systems | Ayoub El Hanchi Murat A Erdogdu | 2024/2/13 |
Gradient-based feature learning under structured data | Advances in Neural Information Processing Systems | Alireza Mousavi-Hosseini Denny Wu Taiji Suzuki Murat A Erdogdu | 2023/12 |
Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning | Advances in Neural Information Processing Systems | Tyler Kastner Murat A Erdogdu Amir-massoud Farahmand | 2024/2/13 |
Sampling from the Mean-Field Stationary Distribution | arXiv preprint arXiv:2402.07355 | Yunbum Kook Matthew S Zhang Sinho Chewi Murat A Erdogdu Mufan Bill Li | 2024/2/12 |
Mean-square analysis of discretized Itô diffusions for heavy-tailed sampling | arXiv preprint arXiv:2303.00570 | Ye He Tyler Farghly Krishnakumar Balasubramanian Murat A Erdogdu | 2023/3/1 |
Learning in the presence of low-dimensional structure: a spiked random matrix perspective | Advances in Neural Information Processing Systems | Jimmy Ba Murat A Erdogdu Taiji Suzuki Zhichao Wang Denny Wu | 2024/2/13 |
Mean-Square Analysis of Discretized It\^ o Diffusions for Heavy-tailed Sampling | arXiv preprint arXiv:2303.00570 | Ye He Tyler Farghly Krishnakumar Balasubramanian Murat A Erdogdu | 2023/3/1 |
Riemannian langevin algorithm for solving semidefinite programs | Bernoulli | Mufan Li Murat A Erdogdu | 2023/11 |
Beyond Labeling Oracles: What does it mean to steal ML models? | arXiv preprint arXiv:2310.01959 | Avital Shafran Ilia Shumailov Murat A Erdogdu Nicolas Papernot | 2023/10/3 |
An analysis of Transformed Unadjusted Langevin Algorithm for Heavy-tailed Sampling | IEEE Transactions on Information Theory | Ye He Krishnakumar Balasubramanian Murat A Erdogdu | 2023/9/22 |
Towards a complete analysis of langevin monte carlo: Beyond poincaré inequality | arXiv preprint arXiv:2303.03589 | Alireza Mousavi-Hosseini Tyler Farghly Ye He Krishnakumar Balasubramanian Murat A Erdogdu | 2023/3/7 |
Improved discretization analysis for underdamped Langevin Monte Carlo | Shunshi Zhang Sinho Chewi Mufan Li Krishna Balasubramanian Murat A Erdogdu | 2023/7/12 | |
-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representations | arXiv preprint arXiv:2207.12545 | Adam Dziedzic Stephan Rabanser Mohammad Yaghini Armin Ale Murat A Erdogdu | 2022/7/25 |
Mirror descent strikes again: Optimal stochastic convex optimization under infinite noise variance | Nuri Mert Vural Lu Yu Krishna Balasubramanian Stanislav Volgushev Murat A Erdogdu | 2022/6/28 | |
Generalization Bounds for Stochastic Gradient Descent via Localized -Covers | Advances in Neural Information Processing Systems | Sejun Park Umut Simsekli Murat A Erdogdu | 2022/12/6 |
Towards a theory of non-log-concave sampling: first-order stationarity guarantees for Langevin Monte Carlo | Krishna Balasubramanian Sinho Chewi Murat A Erdogdu Adil Salim Shunshi Zhang | 2022/6/28 | |
High-dimensional asymptotics of feature learning: How one gradient step improves the representation | Advances in Neural Information Processing Systems | Jimmy Ba Murat A Erdogdu Taiji Suzuki Zhichao Wang Denny Wu | 2022/12/6 |
Convergence and optimality of policy gradient methods in weakly smooth settings | Matthew Shunshi Zhang Murat Erdogdu Animesh Garg | 2022/2 | |
Neural networks efficiently learn low-dimensional representations with sgd | arXiv preprint arXiv:2209.14863 | Alireza Mousavi-Hosseini Sejun Park Manuela Girotti Ioannis Mitliagkas Murat A Erdogdu | 2022/9/29 |
Convergence rate of block-coordinate maximization Burer–Monteiro method for solving large SDPs | Mathematical Programming | Murat A Erdogdu Asuman Ozdaglar Pablo A Parrilo Nuri Denizcan Vanli | 2022/9 |
