Murat A Erdogdu
35 papers · 2013–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
π Conference Polyglot (5) π§ Keyword Pioneer π£ Hot Topic Early Bird π Interdisciplinary Bridge π Academic Marathon (12)
π§
Keyword Pioneer
πΊοΈ
Taxonomy Completionist
(49)
π
Conference Polyglot
(5)
π
Conference Loyalist
(24)
π
Grand Slam
π
Keyword Champion
(4)
π¬
Deep Specialist
(10)
ποΈ
Keyword Collector
(147)
π
Century Club
(35)
π₯
Unstoppable
(11)
π
Trend Setter
β‘
Prolific Year
(7)
Conferences
NIPS (24)
COLT (5)
ICLR (4)
AAAI (1)
ICML (1)
Top co-authors
Research topics
Keywords
stochastic gradient descent
(7)
convergence rate
(5)
langevin monte carlo
(4)
markov chain monte carlo
(4)
generalization bound
(4)
feature learning
(3)
empirical risk minimization
(3)
sample complexity
(3)
gradient descent
(3)
asymptotic normality
(2)
non-convex optimization
(2)
stochastic gradient
(2)
statistical estimation
(2)
generalized linear model
(2)
stochastic process
(2)
convex optimization
(2)
maximum likelihood
(2)
learning theory
(2)
linear regression
(2)
sampling algorithm
(2)
Papers
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
Categorical Distributional Reinforcement Learning with Kullback-Leibler Divergence: Convergence and Asymptotics
ICML 2025
On the Efficiency of ERM in Feature Learning
NIPS 2024
A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
NIPS 2024
Pruning is Optimal for Learning Sparse Features in High-Dimensions
COLT 2024
Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression
NIPS 2023
Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
ICLR 2023
Gradient-Based Feature Learning under Structured Data
NIPS 2023
Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning
NIPS 2023
Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective
NIPS 2023
High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
NIPS 2022
Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$-Covers
NIPS 2022
Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings
AAAI 2022
Analysis of Langevin Monte Carlo from Poincare to Log-Sobolev
COLT 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
Manipulating SGD with Data Ordering Attacks
NIPS 2021
An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias
NIPS 2021
On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness
COLT 2021
On Empirical Risk Minimization with Dependent and Heavy-Tailed Data
NIPS 2021
Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance
NIPS 2021
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms
NIPS 2021
Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks
NIPS 2021
On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method
NIPS 2020
Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks
NIPS 2020
Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond
NIPS 2019
Global Non-convex Optimization with Discretized Diffusions
NIPS 2018
Inference in Graphical Models via Semidefinite Programming Hierarchies
NIPS 2017
Robust Estimation of Neural Signals in Calcium Imaging
NIPS 2017
Scaled Least Squares Estimator for GLMs in Large-Scale Problems
NIPS 2016
Convergence rates of sub-sampled Newton methods
NIPS 2015
Newton-Stein Method: A Second Order Method for GLMs via Stein's Lemma
NIPS 2015
Estimating LASSO Risk and Noise Level
NIPS 2013