Umut Şimşekli

Explicit Regularisation in Gaussian Noise Injections

We study the regularisation induced in neural networks by Gaussian noise...
07/14/2020 ∙ by Alexander Camuto, et al. ∙ 0 ∙ share

read it
Quantitative Propagation of Chaos for SGD in Wide Neural Networks

In this paper, we investigate the limiting behavior of a continuous-time...
07/13/2020 ∙ by Valentin De Bortoli, et al. ∙ 0 ∙ share

read it
Hausdorff Dimension, Stochastic Differential Equations, and Generalization in Neural Networks

Despite its success in a wide range of applications, characterizing the ...
06/16/2020 ∙ by Umut Şimşekli, et al. ∙ 1 ∙ share

read it
The Heavy-Tail Phenomenon in SGD

In recent years, various notions of capacity and complexity have been pr...
06/08/2020 ∙ by Mert Gurbuzbalaban, et al. ∙ 0 ∙ 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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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

Umut Şimşekli

Featured Co-authors