← Authors

Umut Simsekli

49 papers · 2011–2025 · 7 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (7) 🐝 Cross-Pollinator (12) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (14) πŸ—ΊοΈ Taxonomy Completionist (11) 🧭 Keyword Pioneer 🏠 Conference Loyalist (24) 🀝 Dynamic Duo (10) πŸ”¬ Deep Specialist (16) πŸ† Keyword Champion (3) πŸ”₯ Unstoppable (10) πŸš€ Conference Pioneer ⚑ Prolific Year (6) πŸ—ƒοΈ Keyword Collector (173) πŸ’Ž Century Club (49) πŸ“ˆ Trend Setter

Conferences

NIPS (24) ICML (17) COLT (2) CVPR (2) JMLR (2) ALT (1) ICLR (1)

Top co-authors

Mert Gurbuzbalaban (10) Lingjiong Zhu (8) Alain Durmus (8) GaΓ«l RICHARD (8) Roland Badeau (5) Tolga Birdal (5) Murat A Erdogdu (5) George Deligiannidis (4) Kimia Nadjahi (4) Benjamin Dupuis (4)

Keywords

stochastic gradient descent (17) generalization bound (13) neural network (6) stochastic differential equation (6) markov chain monte carlo (6) wasserstein distance (6) heavy-tailed distribution (6) optimal transport (5) langevin dynamics (5) neural network optimization (4) stochastic gradient (4) heavy-tailed noise (4) fractal dimension (4) non-convex optimization (4) generative modeling (3) alpha-stable distribution (3) topological data analysis (3) mutual information (3) random projection (2) bayesian inference (2)

Papers

Heavy-Tailed Diffusion with Denoising Levy Probabilistic Models ICLR 2025
A PAC-Bayesian Link Between Generalisation and Flat Minima ALT 2025
The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training ICML 2025
Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation ICML 2024
Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms NIPS 2024
Piecewise deterministic generative models NIPS 2024
Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets JMLR 2024
Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD ICML 2024
Generalization Bounds using Data-Dependent Fractal Dimensions ICML 2023
Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent NIPS 2023
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent NIPS 2023
Learning via Wasserstein-Based High Probability Generalisation Bounds NIPS 2023
Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models NIPS 2023
Generalization Guarantees via Algorithm-dependent Rademacher Complexity COLT 2023
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions ICML 2023
Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms COLT 2022
Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$-Covers NIPS 2022
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent NIPS 2022
Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers ICML 2022
Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks JMLR 2022
Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks NIPS 2021
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections ICML 2021
The Heavy-Tail Phenomenon in SGD ICML 2021
Relative Positional Encoding for Transformers with Linear Complexity ICML 2021
Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks NIPS 2021
Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections NIPS 2021
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms NIPS 2021
Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance NIPS 2021
Synchronizing Probability Measures on Rotations via Optimal Transport CVPR 2020
Quantitative Propagation of Chaos for SGD in Wide Neural Networks NIPS 2020
Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks NIPS 2020
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise ICML 2020
Explicit Regularisation in Gaussian Noise Injections NIPS 2020
Statistical and Topological Properties of Sliced Probability Divergences NIPS 2020
Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope CVPR 2019
Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance NIPS 2019
Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions ICML 2019
Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization ICML 2019
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks ICML 2019
Generalized Sliced Wasserstein Distances NIPS 2019
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise NIPS 2019
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization ICML 2018
Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC NIPS 2018
Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for Markov Chain Monte Carlo ICML 2017
Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding NIPS 2017
Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo NIPS 2016
Stochastic Quasi-Newton Langevin Monte Carlo ICML 2016
Learning the beta-Divergence in Tweedie Compound Poisson Matrix Factorization Models ICML 2013
Generalised Coupled Tensor Factorisation NIPS 2011