Murat A Erdogdu

Categorical Distributional Reinforcement Learning with Kullback-Leibler Divergence: Convergence and Asymptotics ICML 2025 Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics ICLR 2025 Robust Feature Learning for Multi-Index Models in High Dimensions ICLR 2025 A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers NeurIPS 2024 On the Efficiency of ERM in Feature Learning NeurIPS 2024 Pruning is Optimal for Learning Sparse Features in High-Dimensions COLT 2024 Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning NeurIPS 2023 Gradient-Based Feature Learning under Structured Data NeurIPS 2023 Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective NeurIPS 2023 Neural Networks Efficiently Learn Low-Dimensional Representations with SGD ICLR 2023 Optimal Excess Risk Bounds for Empirical Risk Minimization on p-Norm Linear Regression NeurIPS 2023 Analysis of Langevin Monte Carlo from Poincare to Log-Sobolev COLT 2022 Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings AAAI 2022 Generalization Bounds for Stochastic Gradient Descent via Localized ε-Covers NeurIPS 2022 High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation NeurIPS 2022 Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance COLT 2022 Towards a Theory of Non-Log-Concave Sampling:First-Order Stationarity Guarantees for Langevin Monte Carlo COLT 2022 Understanding the Variance Collapse of SVGD in High Dimensions ICLR 2022 An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias NeurIPS 2021 Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance NeurIPS 2021 Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms NeurIPS 2021 Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks NeurIPS 2021 Manipulating SGD with Data Ordering Attacks NeurIPS 2021 On Empirical Risk Minimization with Dependent and Heavy-Tailed Data NeurIPS 2021 On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness COLT 2021 Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks NeurIPS 2020 On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method NeurIPS 2020 Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond NeurIPS 2019 Global Non-convex Optimization with Discretized Diffusions NeurIPS 2018 Inference in Graphical Models via Semidefinite Programming Hierarchies NeurIPS 2017 Robust Estimation of Neural Signals in Calcium Imaging NeurIPS 2017 Scaled Least Squares Estimator for GLMs in Large-Scale Problems NeurIPS 2016 Convergence rates of sub-sampled Newton methods NeurIPS 2015 Newton-Stein Method: A Second Order Method for GLMs via Stein's Lemma NeurIPS 2015 Estimating LASSO Risk and Noise Level NeurIPS 2013