
Explicit Regularisation in Gaussian Noise Injections
We study the regularisation induced in neural networks by Gaussian noise...
read it

Quantitative Propagation of Chaos for SGD in Wide Neural Networks
In this paper, we investigate the limiting behavior of a continuoustime...
read it

Hausdorff Dimension, Stochastic Differential Equations, and Generalization in Neural Networks
Despite its success in a wide range of applications, characterizing the ...
read it

The HeavyTail Phenomenon in SGD
In recent years, various notions of capacity and complexity have been pr...
read it

Synchronizing Probability Measures on Rotations via Optimal Transport
We introduce a new paradigm, measure synchronization, for synchronizing ...
read it

Statistical and Topological Properties of Sliced Probability Divergences
The idea of slicing divergences has been proven to be successful when co...
read it

Generalized Sliced Distances for Probability Distributions
Probability metrics have become an indispensable part of modern statisti...
read it

Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under HeavyTailed Gradient Noise
Stochastic gradient descent with momentum (SGDm) is one of the most popu...
read it

On the HeavyTailed Theory of Stochastic Gradient Descent for Deep Neural Networks
The gradient noise (GN) in the stochastic gradient descent (SGD) algorit...
read it

Approximate Bayesian Computation with the SlicedWasserstein Distance
Approximate Bayesian Computation (ABC) is a popular method for approxima...
read it

Supervised Symbolic Music Style Translation Using Synthetic Data
Research on style transfer and domain translation has clearly demonstrat...
read it

First Exit Time Analysis of Stochastic Gradient Descent Under HeavyTailed Gradient Noise
Stochastic gradient descent (SGD) has been widely used in machine learni...
read it

Asymptotic Guarantees for Learning Generative Models with the SlicedWasserstein Distance
Minimum expected distance estimation (MEDE) algorithms have been widely ...
read it

Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope
We present an entirely new geometric and probabilistic approach to synch...
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)...
read it

Speech enhancement with variational autoencoders and alphastable distributions
This paper focuses on singlechannel semisupervised speech enhancement....
read it

Generalized Sliced Wasserstein Distances
The Wasserstein distance and its variations, e.g., the slicedWasserstei...
read it

NonAsymptotic Analysis of Fractional Langevin Monte Carlo for NonConvex Optimization
Recent studies on diffusionbased sampling methods have shown that Lange...
read it

A TailIndex Analysis of Stochastic Gradient Noise in Deep Neural Networks
The gradient noise (GN) in the stochastic gradient descent (SGD) algorit...
read it

SlicedWasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions
By building up on the recent theory that established the connection betw...
read it

Asynchronous Stochastic QuasiNewton MCMC for NonConvex Optimization
Recent studies have illustrated that stochastic gradient Markov Chain Mo...
read it

Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC
We introduce Tempered Geodesic Markov Chain Monte Carlo (TGMCMC) algori...
read it

A Generative Model for NonIntrusive Load Monitoring in Commercial Buildings
In the recent years, there has been an increasing academic and industria...
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...
read it

Learning the Morphology of Brain Signals Using AlphaStable Convolutional Sparse Coding
Neural timeseries data contain a wide variety of prototypical signal wa...
read it

Stochastic QuasiNewton Langevin Monte Carlo
Recently, Stochastic Gradient Markov Chain Monte Carlo (SGMCMC) methods...
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...
read it

Parallel Stochastic Gradient Markov Chain Monte Carlo for Matrix Factorisation Models
For large matrix factorisation problems, we develop a distributed Markov...
read it
Umut Şimşekli
is this you? claim profile