Umut Simsekli

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