| 2025 | ALT | A PAC-Bayesian Link Between Generalisation and Flat Minima. | Maxime Haddouche, Paul Viallard, Umut Simsekli, Benjamin Guedj |
| 2025 | ICLR | Heavy-Tailed Diffusion with Denoising Levy Probabilistic Models. | Dario Shariatian, Umut Simsekli, Alain Oliviero Durmus |
| 2025 | ICML | The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training. | Fabian Schaipp, Alexander Hgele, Adrien B. Taylor, Umut Simsekli, Francis Bach |
| 2024 | ICML | Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation. | Benjamin Dupuis, Umut Simsekli |
| 2024 | ICML | Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD. | Yijun Wan, Melih Barsbey, Abdellatif Zaidi, Umut Simsekli |
| 2023 | ALT | Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares. | Anant Raj, Melih Barsbey, Mert Grbzbalaban, Lingjiong Zhu, Umut Simsekli |
| 2023 | COLT | Generalization Guarantees via Algorithm-dependent Rademacher Complexity. | Sarah Sachs, Tim van Erven, Liam Hodgkinson, Rajiv Khanna, Umut Simsekli |
| 2023 | ICML | Generalization Bounds using Data-Dependent Fractal Dimensions. | Benjamin Dupuis, George Deligiannidis, Umut Simsekli |
| 2023 | ICML | Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions. | Anant Raj, Lingjiong Zhu, Mert Grbzbalaban, Umut Simsekli |
| 2022 | COLT | Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms. | Milad Sefidgaran, Amin Gohari, Gal Richard, Umut Simsekli |
| 2022 | ICASSP | Generalized Sliced Probability Metrics. | Soheil Kolouri, Kimia Nadjahi, Shahin Shahrampour, Umut Simsekli |
| 2022 | ICML | Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers. | Liam Hodgkinson, Umut Simsekli, Rajiv Khanna, Michael W. Mahoney |
| 2021 | ICASSP | Self-Supervised VQ-VAE for One-Shot Music Style Transfer. | Ondrej Cfka, Alexey Ozerov, Umut Simsekli, Gal Richard |
| 2021 | ICML | Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections. | Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu, Chris C. Holmes, Mert Grbzbalaban, Umut Simsekli |
| 2021 | ICML | The Heavy-Tail Phenomenon in SGD. | Mert Grbzbalaban, Umut Simsekli, Lingjiong Zhu |
| 2021 | ICML | Relative Positional Encoding for Transformers with Linear Complexity. | Antoine Liutkus, Ondrej Cfka, Shih-Lun Wu, Umut Simsekli, Yi-Hsuan Yang, Gal Richard |
| 2020 | CVPR | Synchronizing Probability Measures on Rotations via Optimal Transport. | Tolga Birdal, Michael Arbel, Umut Simsekli, Leonidas J. Guibas |
| 2020 | ICASSP | Approximate Bayesian Computation with the Sliced-Wasserstein Distance. | Kimia Nadjahi, Valentin De Bortoli, Alain Durmus, Roland Badeau, Umut Simsekli |
| 2020 | ICML | Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise. | Umut Simsekli, Lingjiong Zhu, Yee Whye Teh, Mert Grbzbalaban |
| 2020 | SENSYS | Matrix Factorization for High Frequency Non Intrusive Load Monitoring: Definitions and Algorithms. | Simon Henriet, Benoit Fuentes, Umut Simsekli, Gal Richard |
| 2019 | CVPR | Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope. | Tolga Birdal, Umut Simsekli |
| 2019 | ICASSP | Speech Enhancement with Variational Autoencoders and Alpha-stable Distributions. | Simon Leglaive, Umut Simsekli, Antoine Liutkus, Laurent Girin, Radu Horaud |
| 2019 | ICML | Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions. | Antoine Liutkus, Umut Simsekli, Szymon Majewski, Alain Durmus, Fabian-Robert Stter |
| 2019 | ICML | Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization. | Thanh Huy Nguyen, Umut Simsekli, Gal Richard |
| 2019 | ICML | A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks. | Umut Simsekli, Levent Sagun, Mert Grbzbalaban |
| 2018 | ICASSP | Alpha-Stable Low-Rank Plus Residual Decomposition for Speech Enhancement. | Umut Simsekli, Halil Erdogan, Simon Leglaive, Antoine Liutkus, Roland Badeau, Gal Richard |
| 2018 | ICML | Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization. | Umut Simsekli, agatay Yildiz, Thanh Huy Nguyen, A. Taylan Cemgil, Gal Richard |
| 2017 | ICASSP | Alpha-stable multichannel audio source separation. | Simon Leglaive, Umut Simsekli, Antoine Liutkus, Roland Badeau, Gal Richard |
| 2017 | ICASSP | Parallelized Stochastic Gradient Markov Chain Monte Carlo algorithms for non-negative matrix factorization. | Umut Simsekli, Alain Durmus, Roland Badeau, Gal Richard, Eric Moulines, A. Taylan Cemgil |
| 2017 | ICML | Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for Markov Chain Monte Carlo. | Umut Simsekli |
| 2017 | SENSYS | Synthetic dataset generation for non-intrusive load monitoring in commercial buildings. | Simon Henriet, Umut Simsekli, Gal Richard, Benoit Fuentes |
| 2016 | ICASSP | Stochastic thermodynamic integration: Efficient Bayesian model selection via stochastic gradient MCMC. | Umut Simsekli, Roland Badeau, Gal Richard, Ali Taylan Cemgil |
| 2016 | ICML | Stochastic Quasi-Newton Langevin Monte Carlo. | Umut Simsekli, Roland Badeau, A. Taylan Cemgil, Gal Richard |
| 2015 | ICASSP | Section-level modeling of musical audio for linking performances to scores in Turkish makam music. | Andre Holzapfel, Umut Simsekli, Sertan Sentrk, Ali Taylan Cemgil |
| 2015 | ICASSP | A unified probabilistic framework for robust decoding of linear barcodes. | Umut Simsekli, Tolga Birdal |
| 2015 | ICASSP | Learning mixed divergences in coupled matrix and tensor factorization models. | Umut Simsekli, Ali Taylan Cemgil, Beyza Ermis |
| 2014 | ICASSP | Non-negative source-filter dynamical system for speech enhancement. | Umut Simsekli, Jonathan Le Roux, John R. Hershey |
| 2013 | ICML | Learning the beta-Divergence in Tweedie Compound Poisson Matrix Factorization Models. | Umut Simsekli, Ali Taylan Cemgil, Yusuf Kenan Yilmaz |
| 2012 | ICASSP | Score guided audio restoration via generalised coupled tensor factorisation. | Umut Simsekli, Yusuf Kenan Yilmaz, Ali Taylan Cemgil |
| 2010 | ICPR | Automatic Music Genre Classification Using Bass Lines. | Umut Simsekli |