Umut Simsekli

Publication Activity (10 Years)

Years Active: 2010-2024
Publications (10 Years): 113

Top Venues

CoRR

NeurIPS

ICML

ICASSP

Publications

Andrea Bertazzi, Alain Oliviero Durmus, Dario Shariatian, Umut Simsekli, Eric Moulines
Piecewise deterministic generative models. CoRR (2024)
Benjamin Dupuis, Paul Viallard, George Deligiannidis, Umut Simsekli
Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets. CoRR (2024)
Dario Shariatian, Umut Simsekli, Alain Durmus
Denoising Lévy Probabilistic Models. CoRR (2024)
Maxime Haddouche, Paul Viallard, Umut Simsekli, Benjamin Guedj
A PAC-Bayesian Link Between Generalisation and Flat Minima. CoRR (2024)
Paul Viallard, Maxime Haddouche, Umut Simsekli, Benjamin Guedj
Tighter Generalisation Bounds via Interpolation. CoRR (2024)
Umut Simsekli, Mert Gürbüzbalaban, Sinan Yildirim, Lingjiong Zhu
Differential Privacy of Noisy (S)GD under Heavy-Tailed Perturbations. CoRR (2024)
Rayna Andreeva, Benjamin Dupuis, Rik Sarkar, Tolga Birdal, Umut Simsekli
Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms. CoRR (2024)
Fabian Schaipp, Guillaume Garrigos, Umut Simsekli, Robert M. Gower
SGD with Clipping is Secretly Estimating the Median Gradient. CoRR (2024)
Benjamin Dupuis, Umut Simsekli
Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation. CoRR (2024)
Lingjiong Zhu, Mert Gürbüzbalaban, Anant Raj, Umut Simsekli
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent. NeurIPS (2023)
Sarah Sachs, Tim van Erven, Liam Hodgkinson, Rajiv Khanna, Umut Simsekli
Generalization Guarantees via Algorithm-dependent Rademacher Complexity. CoRR (2023)
Paul Viallard, Maxime Haddouche, Umut Simsekli, Benjamin Guedj
Learning via Wasserstein-Based High Probability Generalisation Bounds. NeurIPS (2023)
Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD. CoRR (2023)
Benjamin Dupuis, George Deligiannidis, Umut Simsekli
Generalization Bounds using Data-Dependent Fractal Dimensions. ICML (2023)
Krunoslav Lehman Pavasovic, Alain Durmus, Umut Simsekli
Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent. CoRR (2023)
Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize. Trans. Mach. Learn. Res. 2023 (2023)
Lingjiong Zhu, Mert Gürbüzbalaban, Anant Raj, Umut Simsekli
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent. CoRR (2023)
Yijun Wan, Abdellatif Zaidi, Umut Simsekli
Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD. CoRR (2023)
Anant Raj, Umut Simsekli, Alessandro Rudi
Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models. CoRR (2023)
Paul Viallard, Maxime Haddouche, Umut Simsekli, Benjamin Guedj
Learning via Wasserstein-Based High Probability Generalisation Bounds. CoRR (2023)
Kruno Lehman, Alain Durmus, Umut Simsekli
Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent. NeurIPS (2023)
Sarah Sachs, Tim van Erven, Liam Hodgkinson, Rajiv Khanna, Umut Simsekli
Generalization Guarantees via Algorithm-dependent Rademacher Complexity. COLT (2023)
Bertille Follain, Umut Simsekli, Francis Bach
Nonparametric Linear Feature Learning in Regression Through Regularisation. CoRR (2023)
Anant Raj, Lingjiong Zhu, Mert Gürbüzbalaban, Umut Simsekli
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions. CoRR (2023)
Benjamin Dupuis, George Deligiannidis, Umut Simsekli
Generalization Bounds with Data-dependent Fractal Dimensions. CoRR (2023)
Anant Raj, Umut Simsekli, Alessandro Rudi
Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models. NeurIPS (2023)
Anant Raj, Melih Barsbey, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli
Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares. ALT (2023)
Anant Raj, Lingjiong Zhu, Mert Gürbüzbalaban, Umut Simsekli
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions. ICML (2023)
Soon Hoe Lim, Yijun Wan, Umut Simsekli
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent. NeurIPS (2022)
Liam Hodgkinson, Umut Simsekli, Rajiv Khanna, Michael W. Mahoney
Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers. ICML (2022)
Sejun Park, Umut Simsekli, Murat A. Erdogdu
Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$-Covers. NeurIPS (2022)
Milad Sefidgaran, Amin Gohari, Gaël Richard, Umut Simsekli
Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms. CoRR (2022)
Anant Raj, Melih Barsbey, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli
Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares. CoRR (2022)
Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Kun Yuan, Lingjiong Zhu
Heavy-Tail Phenomenon in Decentralized SGD. CoRR (2022)
Sejun Park, Umut Simsekli, Murat A. Erdogdu
Generalization Bounds for Stochastic Gradient Descent via Localized ε-Covers. CoRR (2022)
Soheil Kolouri, Kimia Nadjahi, Shahin Shahrampour, Umut Simsekli
Generalized Sliced Probability Metrics. ICASSP (2022)
Soon Hoe Lim, Yijun Wan, Umut Simsekli
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent. CoRR (2022)
Milad Sefidgaran, Amin Gohari, Gaël Richard, Umut Simsekli
Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms. COLT (2022)
Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar, Umut Simsekli, Lingjiong Zhu
Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks. J. Mach. Learn. Res. 23 (2022)
Tolga Birdal, Aaron Lou, Leonidas J. Guibas, Umut Simsekli
Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks. CoRR (2021)
Sinan Yildirim, M. Burak Kurutmaz, Melih Barsbey, Umut Simsekli, A. Taylan Cemgil
Bayesian Allocation Model: Marginal Likelihood-Based Model Selection for Count Tensors. IEEE J. Sel. Top. Signal Process. 15 (3) (2021)
Melih Barsbey, Milad Sefidgaran, Murat A. Erdogdu, Gaël Richard, Umut Simsekli
Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks. CoRR (2021)
Antoine Liutkus, Ondrej Cífka, Shih-Lun Wu, Umut Simsekli, Yi-Hsuan Yang, Gaël Richard
Relative Positional Encoding for Transformers with Linear Complexity. CoRR (2021)
Ondrej Cífka, Alexey Ozerov, Umut Simsekli, Gaël Richard
Self-Supervised VQ-VAE for One-Shot Music Style Transfer. ICASSP (2021)
Liam Hodgkinson, Umut Simsekli, Rajiv Khanna, Michael W. Mahoney
Generalization Properties of Stochastic Optimizers via Trajectory Analysis. CoRR (2021)
Alexander Camuto, George Deligiannidis, Murat A. Erdogdu, Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms. NeurIPS (2021)
Tolga Birdal, Aaron Lou, Leonidas J. Guibas, Umut Simsekli
Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks. NeurIPS (2021)
Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu, Chris C. Holmes, Mert Gürbüzbalaban, Umut Simsekli
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections. CoRR (2021)
Melih Barsbey, Milad Sefidgaran, Murat A. Erdogdu, Gaël Richard, Umut Simsekli
Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks. NeurIPS (2021)
Alexander Camuto, George Deligiannidis, Murat A. Erdogdu, Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms. CoRR (2021)
Kimia Nadjahi, Alain Durmus, Pierre E. Jacob, Roland Badeau, Umut Simsekli
Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections. NeurIPS (2021)
Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu, Chris C. Holmes, Mert Gürbüzbalaban, Umut Simsekli
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections. ICML (2021)
Ondrej Cífka, Alexey Ozerov, Umut Simsekli, Gaël Richard
Self-Supervised VQ-VAE For One-Shot Music Style Transfer. CoRR (2021)
Hongjian Wang, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli, Murat A. Erdogdu
Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance. NeurIPS (2021)
Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu
The Heavy-Tail Phenomenon in SGD. ICML (2021)
Antoine Liutkus, Ondrej Cífka, Shih-Lun Wu, Umut Simsekli, Yi-Hsuan Yang, Gaël Richard
Relative Positional Encoding for Transformers with Linear Complexity. ICML (2021)
Kimia Nadjahi, Alain Durmus, Pierre E. Jacob, Roland Badeau, Umut Simsekli
Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections. CoRR (2021)
Umut Simsekli, Ozan Sener, George Deligiannidis, Murat A. Erdogdu
Hausdorff Dimension, Stochastic Differential Equations, and Generalization in Neural Networks. CoRR (2020)
Umut Simsekli, Ozan Sener, George Deligiannidis, Murat A. Erdogdu
Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks. NeurIPS (2020)
Alexander Camuto, Matthew Willetts, Umut Simsekli, Stephen J. Roberts, Chris C. Holmes
Explicit Regularisation in Gaussian Noise Injections. NeurIPS (2020)
Kimia Nadjahi, Valentin De Bortoli, Alain Durmus, Roland Badeau, Umut Simsekli
Approximate Bayesian Computation with the Sliced-Wasserstein Distance. ICASSP (2020)
Simon Henriet, Benoit Fuentes, Umut Simsekli, Gaël Richard
Matrix Factorization for High Frequency Non Intrusive Load Monitoring: Definitions and Algorithms. NILM@SenSys (2020)
Kimia Nadjahi, Alain Durmus, Lénaïc Chizat, Soheil Kolouri, Shahin Shahrampour, Umut Simsekli
Statistical and Topological Properties of Sliced Probability Divergences. NeurIPS (2020)
Alexander Camuto, Matthew Willetts, Umut Simsekli, Stephen J. Roberts, Chris C. Holmes
Explicit Regularisation in Gaussian Noise Injections. CoRR (2020)
Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Shahin Shahrampour
Generalized Sliced Distances for Probability Distributions. CoRR (2020)
Valentin De Bortoli, Alain Durmus, Xavier Fontaine, Umut Simsekli
Quantitative Propagation of Chaos for SGD in Wide Neural Networks. CoRR (2020)
Ondrej Cífka, Umut Simsekli, Gaël Richard
Groove2Groove: One-Shot Music Style Transfer With Supervision From Synthetic Data. IEEE ACM Trans. Audio Speech Lang. Process. 28 (2020)
Kimia Nadjahi, Alain Durmus, Lénaïc Chizat, Soheil Kolouri, Shahin Shahrampour, Umut Simsekli
Statistical and Topological Properties of Sliced Probability Divergences. CoRR (2020)
Tolga Birdal, Michael Arbel, Umut Simsekli, Leonidas J. Guibas
Synchronizing Probability Measures on Rotations via Optimal Transport. CVPR (2020)
Valentin De Bortoli, Alain Durmus, Xavier Fontaine, Umut Simsekli
Quantitative Propagation of Chaos for SGD in Wide Neural Networks. NeurIPS (2020)
Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu
The Heavy-Tail Phenomenon in SGD. CoRR (2020)
Umut Simsekli, Lingjiong Zhu, Yee Whye Teh, Mert Gürbüzbalaban
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise. CoRR (2020)
Umut Simsekli, Lingjiong Zhu, Yee Whye Teh, Mert Gürbüzbalaban
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise. ICML (2020)
Tolga Birdal, Michael Arbel, Umut Simsekli, Leonidas J. Guibas
Synchronizing Probability Measures on Rotations via Optimal Transport. CoRR (2020)
Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar, Umut Simsekli, Lingjiong Zhu
Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks. CoRR (2019)
Thanh Huy Nguyen, Umut Simsekli, Gaël Richard
Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization. ICML (2019)
Ondrej Cífka, Umut Simsekli, Gaël Richard
Supervised Symbolic Music Style Translation Using Synthetic Data. CoRR (2019)
Antoine Liutkus, Umut Simsekli, Szymon Majewski, Alain Durmus, Fabian-Robert Stöter
Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions. ICML (2019)
Kimia Nadjahi, Alain Durmus, Umut Simsekli, Roland Badeau
Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance. CoRR (2019)
Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Roland Badeau, Gustavo K. Rohde
Generalized Sliced Wasserstein Distances. NeurIPS (2019)
Simon Leglaive, Umut Simsekli, Antoine Liutkus, Laurent Girin, Radu Horaud
Speech enhancement with variational autoencoders and alpha-stable distributions. CoRR (2019)
Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks. CoRR (2019)
Umut Simsekli, Mert Gürbüzbalaban, Thanh Huy Nguyen, Gaël Richard, Levent Sagun
On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks. CoRR (2019)
Ondrej Cífka, Umut Simsekli, Gaël Richard
Supervised Symbolic Music Style Translation Using Synthetic Data. ISMIR (2019)
Tolga Birdal, Umut Simsekli
Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope. CVPR (2019)
Tolga Birdal, Umut Simsekli
Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope. CoRR (2019)
Thanh Huy Nguyen, Umut Simsekli, Mert Gürbüzbalaban, Gaël Richard
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise. CoRR (2019)
Thanh Huy Nguyen, Umut Simsekli, Gaël Richard
Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization. CoRR (2019)
Simon Leglaive, Umut Simsekli, Antoine Liutkus, Laurent Girin, Radu Horaud
Speech Enhancement with Variational Autoencoders and Alpha-stable Distributions. ICASSP (2019)
Kamer Kaya, Figen Öztoprak, S. Ilker Birbil, A. Taylan Cemgil, Umut Simsekli, Nurdan Kuru, Hazal Koptagel, M. Kaan Öztürk
A framework for parallel second order incremental optimization algorithms for solving partially separable problems. Comput. Optim. Appl. 72 (3) (2019)
Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Roland Badeau, Gustavo K. Rohde
Generalized Sliced Wasserstein Distances. CoRR (2019)
Ali Taylan Cemgil, Mehmet Burak Kurutmaz, Sinan Yildirim, Melih Barsbey, Umut Simsekli
Bayesian Allocation Model: Inference by Sequential Monte Carlo for Nonnegative Tensor Factorizations and Topic Models using Polya Urns. CoRR (2019)
Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks. ICML (2019)
Simon Henriet, Umut Simsekli, Sergio Dos Santos, Benoit Fuentes, Gaël Richard
Independent-Variation Matrix Factorization With Application to Energy Disaggregation. IEEE Signal Process. Lett. 26 (11) (2019)
Kimia Nadjahi, Alain Durmus, Umut Simsekli, Roland Badeau
Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance. NeurIPS (2019)
Thanh Huy Nguyen, Umut Simsekli, Mert Gürbüzbalaban, Gaël Richard
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise. NeurIPS (2019)
Thanh Huy Nguyen, Umut Simsekli, Gaël Richard, Ali Taylan Cemgil
Efficient Bayesian Model Selection in PARAFAC via Stochastic Thermodynamic Integration. IEEE Signal Process. Lett. 25 (5) (2018)
Umut Simsekli, Çagatay Yildiz, Thanh Huy Nguyen, A. Taylan Cemgil, Gaël Richard
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization. ICML (2018)
Simon Henriet, Umut Simsekli, Benoit Fuentes, Gaël Richard
A Generative Model for Non-Intrusive Load Monitoring in Commercial Buildings. CoRR (2018)
Tolga Birdal, Umut Simsekli, Mustafa Onur Eken, Slobodan Ilic
Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC. NeurIPS (2018)

Umut Simsekli.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Umut Simsekli