Umut Simsekli

According to our database, Umut Simsekli authored at least 100 papers between 2010 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Differential Privacy of Noisy (S)GD under Heavy-Tailed Perturbations.

Umut Simsekli, Mert Gürbüzbalaban, Sinan Yildirim, Lingjiong Zhu

CoRR, 2024

SGD with Clipping is Secretly Estimating the Median Gradient.

Fabian Schaipp, Guillaume Garrigos, Umut Simsekli, Robert M. Gower

CoRR, 2024

A PAC-Bayesian Link Between Generalisation and Flat Minima.

Maxime Haddouche, Paul Viallard, Umut Simsekli, Benjamin Guedj

CoRR, 2024

Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation.

Benjamin Dupuis, Umut Simsekli

CoRR, 2024

Tighter Generalisation Bounds via Interpolation.

Paul Viallard, Maxime Haddouche, Umut Simsekli, Benjamin Guedj

CoRR, 2024

2023

Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent.

Krunoslav Lehman Pavasovic, Alain Durmus, Umut Simsekli

CoRR, 2023

Nonparametric Linear Feature Learning in Regression Through Regularisation.

Bertille Follain, Umut Simsekli, Francis Bach

CoRR, 2023

Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD.

Yijun Wan, Abdellatif Zaidi, Umut Simsekli

CoRR, 2023

Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD.

Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu

CoRR, 2023

Generalization Bounds with Data-dependent Fractal Dimensions.

Benjamin Dupuis, George Deligiannidis, Umut Simsekli

CoRR, 2023

Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent.

Lingjiong Zhu, Mert Gürbüzbalaban, Anant Raj, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Learning via Wasserstein-Based High Probability Generalisation Bounds.

Paul Viallard, Maxime Haddouche, Umut Simsekli, Benjamin Guedj

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models.

Anant Raj, Umut Simsekli, Alessandro Rudi

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent.

Kruno Lehman, Alain Durmus, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions.

Anant Raj, Lingjiong Zhu, Mert Gürbüzbalaban, Umut Simsekli

Proceedings of the International Conference on Machine Learning, 2023

Generalization Bounds using Data-Dependent Fractal Dimensions.

Benjamin Dupuis, George Deligiannidis, Umut Simsekli

Proceedings of the International Conference on Machine Learning, 2023

Generalization Guarantees via Algorithm-dependent Rademacher Complexity.

Sarah Sachs, Tim van Erven, Liam Hodgkinson, Rajiv Khanna, Umut Simsekli

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares.

Anant Raj, Melih Barsbey, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli

Proceedings of the International Conference on Algorithmic Learning Theory, 2023

2022

Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks.

Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar, Umut Simsekli, Lingjiong Zhu

J. Mach. Learn. Res., 2022

Generalization Bounds for Stochastic Gradient Descent via Localized ε-Covers.

Sejun Park, Umut Simsekli, Murat A. Erdogdu

CoRR, 2022

Heavy-Tail Phenomenon in Decentralized SGD.

Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Kun Yuan, Lingjiong Zhu

CoRR, 2022

Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$-Covers.

Sejun Park, Umut Simsekli, Murat A. Erdogdu

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent.

Soon Hoe Lim, Yijun Wan, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers.

Liam Hodgkinson, Umut Simsekli, Rajiv Khanna, Michael W. Mahoney

Proceedings of the International Conference on Machine Learning, 2022

Generalized Sliced Probability Metrics.

Soheil Kolouri, Kimia Nadjahi, Shahin Shahrampour, Umut Simsekli

Proceedings of the IEEE International Conference on Acoustics, 2022

Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms.

Milad Sefidgaran, Amin Gohari, Gaël Richard, Umut Simsekli

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

Bayesian Allocation Model: Marginal Likelihood-Based Model Selection for Count Tensors.

Sinan Yildirim, M. Burak Kurutmaz, Melih Barsbey, Umut Simsekli, A. Taylan Cemgil

IEEE J. Sel. Top. Signal Process., 2021

Generalization Properties of Stochastic Optimizers via Trajectory Analysis.

Liam Hodgkinson, Umut Simsekli, Rajiv Khanna, Michael W. Mahoney

CoRR, 2021

Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance.

Hongjian Wang, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli, Murat A. Erdogdu

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections.

Kimia Nadjahi, Alain Durmus, Pierre E. Jacob, Roland Badeau, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms.

Alexander Camuto, George Deligiannidis, Murat A. Erdogdu, Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks.

Tolga Birdal, Aaron Lou, Leonidas J. Guibas, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks.

Melih Barsbey, Milad Sefidgaran, Murat A. Erdogdu, Gaël Richard, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Relative Positional Encoding for Transformers with Linear Complexity.

Antoine Liutkus, Ondrej Cífka, Shih-Lun Wu, Umut Simsekli, Yi-Hsuan Yang, Gaël Richard

Proceedings of the 38th International Conference on Machine Learning, 2021

The Heavy-Tail Phenomenon in SGD.

Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu

Proceedings of the 38th International Conference on Machine Learning, 2021

Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections.

Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu, Chris C. Holmes, Mert Gürbüzbalaban, Umut Simsekli

Proceedings of the 38th International Conference on Machine Learning, 2021

Self-Supervised VQ-VAE for One-Shot Music Style Transfer.

Ondrej Cífka, Alexey Ozerov, Umut Simsekli, Gaël Richard

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Groove2Groove: One-Shot Music Style Transfer With Supervision From Synthetic Data.

Ondrej Cífka, Umut Simsekli, Gaël Richard

IEEE ACM Trans. Audio Speech Lang. Process., 2020

Hausdorff Dimension, Stochastic Differential Equations, and Generalization in Neural Networks.

Umut Simsekli, Ozan Sener, George Deligiannidis, Murat A. Erdogdu

CoRR, 2020

Generalized Sliced Distances for Probability Distributions.

Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Shahin Shahrampour

CoRR, 2020

Matrix Factorization for High Frequency Non Intrusive Load Monitoring: Definitions and Algorithms.

Simon Henriet, Benoit Fuentes, Umut Simsekli, Gaël Richard

Proceedings of the NILM '20, 2020

Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks.

Umut Simsekli, Ozan Sener, George Deligiannidis, Murat A. Erdogdu

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Statistical and Topological Properties of Sliced Probability Divergences.

Kimia Nadjahi, Alain Durmus, Lénaïc Chizat, Soheil Kolouri, Shahin Shahrampour, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Explicit Regularisation in Gaussian Noise Injections.

Alexander Camuto, Matthew Willetts, Umut Simsekli, Stephen J. Roberts, Chris C. Holmes

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Quantitative Propagation of Chaos for SGD in Wide Neural Networks.

Valentin De Bortoli, Alain Durmus, Xavier Fontaine, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise.

Umut Simsekli, Lingjiong Zhu, Yee Whye Teh, Mert Gürbüzbalaban

Proceedings of the 37th International Conference on Machine Learning, 2020

Approximate Bayesian Computation with the Sliced-Wasserstein Distance.

Kimia Nadjahi, Valentin De Bortoli, Alain Durmus, Roland Badeau, Umut Simsekli

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Synchronizing Probability Measures on Rotations via Optimal Transport.

Tolga Birdal, Michael Arbel, Umut Simsekli, Leonidas J. Guibas

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Independent-Variation Matrix Factorization With Application to Energy Disaggregation.

Simon Henriet, Umut Simsekli, Sergio Dos Santos, Benoit Fuentes, Gaël Richard

IEEE Signal Process. Lett., 2019

On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks.

Umut Simsekli, Mert Gürbüzbalaban, Thanh Huy Nguyen, Gaël Richard, Levent Sagun

CoRR, 2019

Bayesian Allocation Model: Inference by Sequential Monte Carlo for Nonnegative Tensor Factorizations and Topic Models using Polya Urns.

Ali Taylan Cemgil, Mehmet Burak Kurutmaz, Sinan Yildirim, Melih Barsbey, Umut Simsekli

CoRR, 2019

A framework for parallel second order incremental optimization algorithms for solving partially separable problems.

Kamer Kaya, Figen Öztoprak, S. Ilker Birbil, A. Taylan Cemgil, Umut Simsekli, Nurdan Kuru, Hazal Koptagel, M. Kaan Öztürk

Comput. Optim. Appl., 2019

First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise.

Thanh Huy Nguyen, Umut Simsekli, Mert Gürbüzbalaban, Gaël Richard

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance.

Kimia Nadjahi, Alain Durmus, Umut Simsekli, Roland Badeau

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Generalized Sliced Wasserstein Distances.

Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Roland Badeau, Gustavo K. Rohde

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Supervised Symbolic Music Style Translation Using Synthetic Data.

Ondrej Cífka, Umut Simsekli, Gaël Richard

Proceedings of the 20th International Society for Music Information Retrieval Conference, 2019

A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks.

Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban

Proceedings of the 36th International Conference on Machine Learning, 2019

Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization.

Thanh Huy Nguyen, Umut Simsekli, Gaël Richard

Proceedings of the 36th International Conference on Machine Learning, 2019

Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions.

Antoine Liutkus, Umut Simsekli, Szymon Majewski, Alain Durmus, Fabian-Robert Stöter

Proceedings of the 36th International Conference on Machine Learning, 2019

Speech Enhancement with Variational Autoencoders and Alpha-stable Distributions.

Simon Leglaive, Umut Simsekli, Antoine Liutkus, Laurent Girin, Radu Horaud

Proceedings of the IEEE International Conference on Acoustics, 2019

Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope.

Tolga Birdal, Umut Simsekli

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

2018

Efficient Bayesian Model Selection in PARAFAC via Stochastic Thermodynamic Integration.

Thanh Huy Nguyen, Umut Simsekli, Gaël Richard, Ali Taylan Cemgil

IEEE Signal Process. Lett., 2018

Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions.

Umut Simsekli, Antoine Liutkus, Szymon Majewski, Alain Durmus

CoRR, 2018

A Generative Model for Non-Intrusive Load Monitoring in Commercial Buildings.

Simon Henriet, Umut Simsekli, Benoit Fuentes, Gaël Richard

CoRR, 2018

Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC.

Tolga Birdal, Umut Simsekli, Mustafa Onur Eken, Slobodan Ilic

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization.

Umut Simsekli, Çagatay Yildiz, Thanh Huy Nguyen, A. Taylan Cemgil, Gaël Richard

Proceedings of the 35th International Conference on Machine Learning, 2018

Alpha-Stable Low-Rank Plus Residual Decomposition for Speech Enhancement.

Umut Simsekli, Halil Erdogan, Simon Leglaive, Antoine Liutkus, Roland Badeau, Gaël Richard

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Multichannel Audio Modeling with Elliptically Stable Tensor Decomposition.

Mathieu Fontaine, Fabian-Robert Stöter, Antoine Liutkus, Umut Simsekli, Romain Serizel, Roland Badeau

Proceedings of the Latent Variable Analysis and Signal Separation, 2018

2017

Synthetic dataset generation for non-intrusive load monitoring in commercial buildings.

Simon Henriet, Umut Simsekli, Gaël Richard, Benoit Fuentes

Proceedings of the 4th ACM International Conference on Systems for Energy-Efficient Built Environments, 2017

Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding.

Mainak Jas, Tom Dupré la Tour, Umut Simsekli, Alexandre Gramfort

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for Markov Chain Monte Carlo.

Umut Simsekli

Proceedings of the 34th International Conference on Machine Learning, 2017

Parallelized Stochastic Gradient Markov Chain Monte Carlo algorithms for non-negative matrix factorization.

Umut Simsekli, Alain Durmus, Roland Badeau, Gaël Richard, Eric Moulines, A. Taylan Cemgil

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Alpha-stable multichannel audio source separation.

Simon Leglaive, Umut Simsekli, Antoine Liutkus, Roland Badeau, Gaël Richard

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo.

Alain Durmus, Umut Simsekli, Eric Moulines, Roland Badeau, Gaël Richard

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Stochastic Quasi-Newton Langevin Monte Carlo.

Umut Simsekli, Roland Badeau, A. Taylan Cemgil, Gaël Richard

Proceedings of the 33nd International Conference on Machine Learning, 2016

Stochastic thermodynamic integration: Efficient Bayesian model selection via stochastic gradient MCMC.

Umut Simsekli, Roland Badeau, Gaël Richard, Ali Taylan Cemgil

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Tensor fusion: Learning in heterogeneous and distributed data (Tensör tümleştirme: Ayrı cinsten ve dağıtık verilerde öğrenme)

Umut Simsekli

PhD thesis, 2015

Alpha-Stable Matrix Factorization.

Umut Simsekli, Antoine Liutkus, Ali Taylan Cemgil

IEEE Signal Process. Lett., 2015

Non-negative tensor factorization models for Bayesian audio processing.

Umut Simsekli, Tuomas Virtanen, Ali Taylan Cemgil

Digit. Signal Process., 2015

HAMSI: Distributed Incremental Optimization Algorithm Using Quadratic Approximations for Partially Separable Problems.

Umut Simsekli, Hazal Koptagel, Figen Öztoprak, S. Ilker Birbil, Ali Taylan Cemgil

CoRR, 2015

Learning mixed divergences in coupled matrix and tensor factorization models.

Umut Simsekli, Ali Taylan Cemgil, Beyza Ermis

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

A unified probabilistic framework for robust decoding of linear barcodes.

Umut Simsekli, Tolga Birdal

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Section-level modeling of musical audio for linking performances to scores in Turkish makam music.

Andre Holzapfel, Umut Simsekli, Sertan Sentürk, Ali Taylan Cemgil

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Extraction of Temporal Patterns in Multi-rate and Multi-modal Datasets.

Antoine Liutkus, Umut Simsekli, A. Taylan Cemgil

Proceedings of the Latent Variable Analysis and Signal Separation, 2015

2014

Non-negative source-filter dynamical system for speech enhancement.

Umut Simsekli, Jonathan Le Roux, John R. Hershey

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

Hierarchical and coupled non-negative dynamical systems with application to audio modeling.

Umut Simsekli, Jonathan Le Roux, John R. Hershey

Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2013

A factorization based recommender system for online services.

Umut Simsekli, Tolga Birdal, Emre Koc, Ali Taylan Cemgil

Proceedings of the 21st Signal Processing and Communications Applications Conference, 2013

Learning the beta-Divergence in Tweedie Compound Poisson Matrix Factorization Models.

Umut Simsekli, Ali Taylan Cemgil, Yusuf Kenan Yilmaz

Proceedings of the 30th International Conference on Machine Learning, 2013

Optimal weight learning for Coupled Tensor Factorization with mixed divergences.

Umut Simsekli, Beyza Ermis, A. Taylan Cemgil, Evrim Acar

Proceedings of the 21st European Signal Processing Conference, 2013

2012

Combined perception and control for timing in robotic music performances.

Umut Simsekli, Orhan Sonmez, Baris Kurt, Ali Taylan Cemgil

EURASIP J. Audio Speech Music. Process., 2012

Coupled tensor factorization models for polyphonic music transcription.

Umut Simsekli, Yusuf Kenan Yilmaz, Ali Taylan Cemgil

Proceedings of the 20th Signal Processing and Communications Applications Conference, 2012

SVD-based polyphonic music transcription.

Ismail Ari, Umut Simsekli, Ali Taylan Cemgil, Lale Akarun

Proceedings of the 20th Signal Processing and Communications Applications Conference, 2012

Markov Chain Monte Carlo inference for probabilistic latent tensor factorization.

Umut Simsekli, A. Taylan Cemgil

Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing, 2012

Score guided audio restoration via generalised coupled tensor factorisation.

Umut Simsekli, Yusuf Kenan Yilmaz, Ali Taylan Cemgil

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Score guided musical source separation using Generalized Coupled Tensor Factorization.

Umut Simsekli, A. Taylan Cemgil

Proceedings of the 20th European Signal Processing Conference, 2012

Large scale polyphonic music transcription using randomized matrix decompositions.

Ismail An, Umut Simsekli, Ali Taylan Cemgil, Lale Akarun

Proceedings of the 20th European Signal Processing Conference, 2012

2011

Real-Time Recognition of Percussive Sounds by a Model-Based Method.

Umut Simsekli, Antti Jylhä, Cumhur Erkut, Ali Taylan Cemgil

EURASIP J. Adv. Signal Process., 2011

Probabilistic latent tensor factorization framework for audio modeling.

Ali Taylan Cemgil, Umut Simsekli, Yusuf Cem Sübakan

Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2011

Generalised Coupled Tensor Factorisation.

Yusuf Kenan Yilmaz, Ali Taylan Cemgil, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

2010

Automatic Music Genre Classification Using Bass Lines.

Umut Simsekli

Proceedings of the 20th International Conference on Pattern Recognition, 2010