Umut Şimşekli

Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope

We present an entirely new geometric and probabilistic approach to synch...
04/11/2019 ∙ by Tolga Birdal, et al. ∙ 16 ∙ share

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

Stochastic gradient descent (SGD) has been widely used in machine learni...
06/21/2019 ∙ by Thanh Huy Nguyen, et al. ∙ 12 ∙ share

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

Stochastic gradient descent with momentum (SGDm) is one of the most popu...
02/13/2020 ∙ by Umut Şimşekli, et al. ∙ 5 ∙ share

read it
Synchronizing Probability Measures on Rotations via Optimal Transport

We introduce a new paradigm, measure synchronization, for synchronizing ...
04/01/2020 ∙ by Tolga Birdal, et al. ∙ 3 ∙ share

read it
Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC

We introduce Tempered Geodesic Markov Chain Monte Carlo (TG-MCMC) algori...
05/31/2018 ∙ by Tolga Birdal, et al. ∙ 2 ∙ share

read it
Fractional Langevin Monte Carlo: Exploring Lévy Driven Stochastic Differential Equations for Markov Chain Monte Carlo

Along with the recent advances in scalable Markov Chain Monte Carlo meth...
06/12/2017 ∙ by Umut Şimşekli, et al. ∙ 0 ∙ share

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

Neural time-series data contain a wide variety of prototypical signal wa...
05/22/2017 ∙ by Mainak Jas, et al. ∙ 0 ∙ share

read it
Stochastic Quasi-Newton Langevin Monte Carlo

Recently, Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) methods...
02/10/2016 ∙ by Umut Şimşekli, et al. ∙ 0 ∙ share

read it
HAMSI: A Parallel Incremental Optimization Algorithm Using Quadratic Approximations for Solving Partially Separable Problems

We propose HAMSI (Hessian Approximated Multiple Subsets Iteration), whic...
09/05/2015 ∙ by Kamer Kaya, et al. ∙ 0 ∙ share

read it
Parallel Stochastic Gradient Markov Chain Monte Carlo for Matrix Factorisation Models

For large matrix factorisation problems, we develop a distributed Markov...
06/03/2015 ∙ by Umut Şimşekli, et al. ∙ 0 ∙ share

read it
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization

Recent studies have illustrated that stochastic gradient Markov Chain Mo...
06/07/2018 ∙ by Umut Şimşekli, et al. ∙ 0 ∙ share

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

By building up on the recent theory that established the connection betw...
06/21/2018 ∙ by Umut Şimşekli, et al. ∙ 0 ∙ share

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

The gradient noise (GN) in the stochastic gradient descent (SGD) algorit...
01/18/2019 ∙ by Umut Şimşekli, et al. ∙ 0 ∙ share

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

Recent studies on diffusion-based sampling methods have shown that Lange...
01/22/2019 ∙ by Thanh Huy Nguyen, et al. ∙ 0 ∙ share

read it
Generalized Sliced Wasserstein Distances

The Wasserstein distance and its variations, e.g., the sliced-Wasserstei...
02/01/2019 ∙ by Soheil Kolouri, et al. ∙ 0 ∙ share

read it
Speech enhancement with variational autoencoders and alpha-stable distributions

This paper focuses on single-channel semi-supervised speech enhancement....
02/08/2019 ∙ by Simon Leglaive, et al. ∙ 0 ∙ share

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

Minimum expected distance estimation (MEDE) algorithms have been widely ...
06/11/2019 ∙ by Kimia Nadjahi, et al. ∙ 0 ∙ share

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

We introduce a dynamic generative model, Bayesian allocation model (BAM)...
03/11/2019 ∙ by Ali Taylan Cemgil, et al. ∙ 0 ∙ share

read it
Supervised Symbolic Music Style Translation Using Synthetic Data

Research on style transfer and domain translation has clearly demonstrat...
07/04/2019 ∙ by Ondřej Cífka, et al. ∙ 0 ∙ share

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

The gradient noise (GN) in the stochastic gradient descent (SGD) algorit...
11/29/2019 ∙ by Umut Şimşekli, et al. ∙ 0 ∙ share

read it
Generalized Sliced Distances for Probability Distributions

Probability metrics have become an indispensable part of modern statisti...
02/28/2020 ∙ by Soheil Kolouri, et al. ∙ 0 ∙ share

read it
Approximate Bayesian Computation with the Sliced-Wasserstein Distance

Approximate Bayesian Computation (ABC) is a popular method for approxima...
10/28/2019 ∙ by Kimia Nadjahi, et al. ∙ 0 ∙ share

read it
Statistical and Topological Properties of Sliced Probability Divergences

The idea of slicing divergences has been proven to be successful when co...
03/12/2020 ∙ by Kimia Nadjahi, et al. ∙ 0 ∙ share

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

In the recent years, there has been an increasing academic and industria...
02/26/2018 ∙ by Simon Henriet, et al. ∙ 0 ∙ share

read it

Umut Şimşekli

Featured Co-authors

Yee Whye Teh

Leonidas Guibas

Alexandre Gramfort

Radu Horaud

Soheil Kolouri

Slobodan Ilic

Shahin Shahrampour

Alain Durmus

Tolga Birdal

Laurent Girin

Gustavo K. Rohde

Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope

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

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

Synchronizing Probability Measures on Rotations via Optimal Transport

Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC

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

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

Stochastic Quasi-Newton Langevin Monte Carlo

HAMSI: A Parallel Incremental Optimization Algorithm Using Quadratic Approximations for Solving Partially Separable Problems

Parallel Stochastic Gradient Markov Chain Monte Carlo for Matrix Factorisation Models

Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization

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

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

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

Generalized Sliced Wasserstein Distances

Speech enhancement with variational autoencoders and alpha-stable distributions

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

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

Supervised Symbolic Music Style Translation Using Synthetic Data

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

Generalized Sliced Distances for Probability Distributions

Approximate Bayesian Computation with the Sliced-Wasserstein Distance

Statistical and Topological Properties of Sliced Probability Divergences

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