Murat A. Erdogdu

research

∙ 09/07/2023

Gradient-Based Feature Learning under Structured Data

Recent works have demonstrated that the sample complexity of gradient-ba...

0 Alireza Mousavi Hosseini, et al. ∙

research

∙ 07/04/2023

Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

We consider the problem of learning models for risk-sensitive reinforcem...

0 Tyler Kastner, et al. ∙

research

∙ 03/07/2023

Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality

Langevin diffusions are rapidly convergent under appropriate functional ...

0 Alireza Mousavi Hosseini, et al. ∙

research

∙ 03/01/2023

Mean-Square Analysis of Discretized Itô Diffusions for Heavy-tailed Sampling

We analyze the complexity of sampling from a class of heavy-tailed distr...

0 Ye He, et al. ∙

research

∙ 02/16/2023

Improved Discretization Analysis for Underdamped Langevin Monte Carlo

Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample f...

0 Matthew Zhang, et al. ∙

research

∙ 09/29/2022

Neural Networks Efficiently Learn Low-Dimensional Representations with SGD

We study the problem of training a two-layer neural network (NN) of arbi...

0 Alireza Mousavi Hosseini, et al. ∙

research

∙ 09/19/2022

Generalization Bounds for Stochastic Gradient Descent via Localized ε-Covers

In this paper, we propose a new covering technique localized for the tra...

0 Sejun Park, et al. ∙

research

∙ 07/25/2022

p-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representations

The lack of well-calibrated confidence estimates makes neural networks i...

0 Adam Dziedzic, et al. ∙

research

∙ 02/23/2022

Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance

We study stochastic convex optimization under infinite noise variance. S...

0 Nuri Mert Vural, et al. ∙

research

∙ 02/10/2022

Towards a Theory of Non-Log-Concave Sampling: First-Order Stationarity Guarantees for Langevin Monte Carlo

For the task of sampling from a density π∝exp(-V) on ℝ^d, where V is pos...

6 Krishnakumar Balasubramanian, et al. ∙

research

∙ 01/20/2022

Heavy-tailed Sampling via Transformed Unadjusted Langevin Algorithm

We analyze the oracle complexity of sampling from polynomially decaying ...

0 Ye He, et al. ∙

research

∙ 12/23/2021

Analysis of Langevin Monte Carlo from Poincaré to Log-Sobolev

Classically, the continuous-time Langevin diffusion converges exponentia...

0 Sinho Chewi, et al. ∙

research

∙ 09/06/2021

On Empirical Risk Minimization with Dependent and Heavy-Tailed Data

In this work, we establish risk bounds for the Empirical Risk Minimizati...

0 Abhishek Roy, et al. ∙

research

∙ 06/09/2021

Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms

Understanding generalization in deep learning has been one of the major ...

0 Alexander Camuto, et al. ∙

research

∙ 06/07/2021

Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks

Neural network compression techniques have become increasingly popular a...

0 Melih Barsbey, et al. ∙

research

∙ 04/19/2021

Manipulating SGD with Data Ordering Attacks

Machine learning is vulnerable to a wide variety of different attacks. I...

14 Ilia Shumailov, et al. ∙

research

∙ 02/20/2021

Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance

Recent studies have provided both empirical and theoretical evidence ill...

0 Hongjian Wang, et al. ∙

research

∙ 11/06/2020

On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method

The randomized midpoint method, proposed by [SL19], has emerged as an op...

0 Ye He, et al. ∙

research

∙ 10/21/2020

Riemannian Langevin Algorithm for Solving Semidefinite Programs

We propose a Langevin diffusion-based algorithm for non-convex optimizat...

0 Mufan Bill Li, et al. ∙

research

∙ 07/22/2020

A Brief Note on the Convergence of Langevin Monte Carlo in Chi-Square Divergence

We study sampling from a target distribution ν_* ∝ e^-f using the unadju...

0 Murat A. Erdogdu, et al. ∙

research

∙ 06/16/2020

Hausdorff Dimension, Stochastic Differential Equations, and Generalization in Neural Networks

Despite its success in a wide range of applications, characterizing the ...

1 Umut Şimşekli, et al. ∙

research

∙ 06/14/2020

An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias

Structured non-convex learning problems, for which critical points have ...

0 Lu Yu, et al. ∙

research

∙ 05/27/2020

On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness

We study sampling from a target distribution ν_* = e^-f using the unadju...

0 Murat A. Erdogdu, et al. ∙

research

∙ 06/19/2019

Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond

Sampling with Markov chain Monte Carlo methods typically amounts to disc...

0 Xuechen Li, et al. ∙

research

∙ 04/03/2019

Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT

We provide non-asymptotic convergence rates of the Polyak-Ruppert averag...

0 Andreas Anastasiou, et al. ∙

research

∙ 10/29/2018

Global Non-convex Optimization with Discretized Diffusions

An Euler discretization of the Langevin diffusion is known to converge t...

0 Murat A. Erdogdu, et al. ∙

research

∙ 07/12/2018

Convergence Rate of Block-Coordinate Maximization Burer-Monteiro Method for Solving Large SDPs

Semidefinite programming (SDP) with equality constraints arise in many o...

0 Murat A. Erdogdu, et al. ∙

research

∙ 09/19/2017

Inference in Graphical Models via Semidefinite Programming Hierarchies

Maximum A posteriori Probability (MAP) inference in graphical models amo...

0 Murat A. Erdogdu, et al. ∙

research

∙ 11/21/2016

Scalable Approximations for Generalized Linear Problems

In stochastic optimization, the population risk is generally approximate...

0 Murat A. Erdogdu, et al. ∙

research

∙ 11/28/2015

Newton-Stein Method: An optimization method for GLMs via Stein's Lemma

We consider the problem of efficiently computing the maximum likelihood ...

0 Murat A. Erdogdu, et al. ∙

research

∙ 08/12/2015

Convergence rates of sub-sampled Newton methods

We consider the problem of minimizing a sum of n functions over a convex...

0 Murat A. Erdogdu, et al. ∙

Murat A. Erdogdu

Featured Co-authors