activity
20172022
most citedSpeech enhancement with variational autoencoders and alpha-stable distributions

44 citations · 199 across the 14 of their papers we have counts for

collaborators
Showing stat.MLShow all

14 papers · 1 filter

stat.ML20221 cited

Generalization Bounds for Stochastic Gradient Descent via Localized -Covers

Sejun Park, Umut Şimşekli, Murat A. Erdogdu

In this paper, we propose a new covering technique localized for the trajectories of SGD. This localization provides an algorithm-specific complexity measured by the covering numbe…

stat.ML202112 cited

Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks

Melih Barsbey, Milad Sefidgaran, Murat A. Erdogdu +2

Neural network compression techniques have become increasingly popular as they can drastically reduce the storage and computation requirements for very large networks. Recent empir…

stat.ML2021

Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections

Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu +3

Gaussian noise injections (GNIs) are a family of simple and widely-used regularisation methods for training neural networks, where one injects additive or multiplicative Gaussian n…

stat.ML202013 cited

Quantitative Propagation of Chaos for SGD in Wide Neural Networks

Valentin De Bortoli, Alain Durmus, Xavier Fontaine +1

In this paper, we investigate the limiting behavior of a continuous-time counterpart of the Stochastic Gradient Descent (SGD) algorithm applied to two-layer overparameterized neura…

stat.ML2020

Explicit Regularisation in Gaussian Noise Injections

Alexander Camuto, Matthew Willetts, Umut Şimşekli +2

We study the regularisation induced in neural networks by Gaussian noise injections (GNIs). Though such injections have been extensively studied when applied to data, there have be…

stat.ML20203 cited

Generalized Sliced Distances for Probability Distributions

Soheil Kolouri, Kimia Nadjahi, Umut Simsekli +1

Probability metrics have become an indispensable part of modern statistics and machine learning, and they play a quintessential role in various applications, including statistical…