activity
20172024
most citedSpeech enhancement with variational autoencoders and alpha-stable distributions

44 citations · 206 across the 28 of their papers we have counts for

collaborators
Showing 2019Show all

11 papers · 1 filter

stat.ML2019★ 21 cited

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

Umut Şimşekli, Mert Gürbüzbalaban, Thanh Huy Nguyen +2

The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the \emph{classical} central…

stat.CO2019

Approximate Bayesian Computation with the Sliced-Wasserstein Distance

Kimia Nadjahi, Valentin De Bortoli, Alain Durmus +2

Approximate Bayesian Computation (ABC) is a popular method for approximate inference in generative models with intractable but easy-to-sample likelihood. It constructs an approxima…

math.OC2019

Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks

Alireza Fallah, Mert Gurbuzbalaban, Asuman Ozdaglar +2

We study distributed stochastic gradient (D-SG) method and its accelerated variant (D-ASG) for solving decentralized strongly convex stochastic optimization problems where the obje…

stat.ML2019★ 11 cited

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

Thanh Huy Nguyen, Umut Şimşekli, Mert Gürbüzbalaban +1

Stochastic gradient descent (SGD) has been widely used in machine learning due to its computational efficiency and favorable generalization properties. Recently, it has been empiri…

stat.ML2019

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

Kimia Nadjahi, Alain Durmus, Umut Şimşekli +1

Minimum expected distance estimation (MEDE) algorithms have been widely used for probabilistic models with intractable likelihood functions and they have become increasingly popula…

cs.CV2019

Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope

Tolga Birdal, Umut Şimşekli

We present an entirely new geometric and probabilistic approach to synchronization of correspondences across multiple sets of objects or images. In particular, we present two algor…