← Authors

Mert Gurbuzbalaban

23 papers · 2017–2024 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (31) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (7) 🀝 Dynamic Duo (13) πŸ”¬ Deep Specialist (13) πŸ’Ž Century Club (23) πŸ—ƒοΈ Keyword Collector (102) ⚑ Prolific Year (6) πŸ”₯ Unstoppable (6)

Conferences

NIPS (10) ICML (6) JMLR (4) AISTATS (2) ALT (1)

Top co-authors

Lingjiong Zhu (13) Umut Simsekli (10) Necdet Serhat Aybat (4) Asuman Ozdaglar (3) Yuanhan Hu (3) Anant Raj (3) Yassine Laguel (2) Murat A Erdogdu (2) Xuefeng GAO (2) Alireza Fallah (2)

Keywords

stochastic gradient descent (14) heavy-tailed distribution (5) stochastic optimization (4) langevin dynamics (4) stochastic gradient (4) generalization bound (3) accelerated gradient (3) convergence rate (3) convex optimization (3) algorithmic stability (3) non-convex optimization (3) markov chain monte carlo (3) wasserstein distance (3) stochastic differential equation (3) neural network optimization (2) decentralized optimization (2) generalization error (2) bayesian inference (2) minimax optimization (2) variance reduction (2)

Papers

Penalized Overdamped and Underdamped Langevin Monte Carlo Algorithms for Constrained Sampling JMLR 2024
High-probability complexity bounds for stochastic non-convex minimax optimization NIPS 2024
High Probability and Risk-Averse Guarantees for a Stochastic Accelerated Primal-Dual Method JMLR 2024
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent NIPS 2023
Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares ALT 2023
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions ICML 2023
Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks JMLR 2022
SAPD+: An Accelerated Stochastic Method for Nonconvex-Concave Minimax Problems NIPS 2022
Fractional moment-preserving initialization schemes for training deep neural networks AISTATS 2021
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms NIPS 2021
Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance NIPS 2021
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections ICML 2021
The Heavy-Tail Phenomenon in SGD ICML 2021
Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo JMLR 2021
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method NIPS 2020
Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization NIPS 2020
DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate AISTATS 2020
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise ICML 2020
Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances ICML 2019
A Universally Optimal Multistage Accelerated Stochastic Gradient Method NIPS 2019
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise NIPS 2019
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks ICML 2019
When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent NIPS 2017