Publications related to On the performance of random reshuffling in stochastic learning

Stochastic gradient descent with finite samples sizes

Ali H. Sayed, Stefan Vlaski, Bicheng Ying, Kun Yuan

The minimization of empirical risks over finite sample sizes is an important problem in large-scale machine learning. A variety of algorithms has been proposed in the literature to alleviate the computational burden per iteration at the expense of converge ...

IEEE2016

Attributing Aliasing Artifacts in Dirty Intensity Fields to their Parent Source

Matthieu Martin Jean-André Simeoni

Estimating intensity fields of stochastic phenomenons is of crucial interest in many scientific applications. Typical experimental setups involve an acquisition system, that subsequently filters and samples the probed intensity field. This equivalently def ...

2016

Theory of representation learning in cortical neural networks

Carlos Stein Naves de Brito

Our brain continuously self-organizes to construct and maintain an internal representation of the world based on the information arriving through sensory stimuli. Remarkably, cortical areas related to different sensory modalities appear to share the same f ...

EPFL2016

Influence of loading history on mechanical properties of biomaterials

Tom Charles Maurice Walet

It is known that the mechanical response to load or displacement of a biological tissue can highly vary from one cycle to the next. Therefore, in order to establish a reference state for repeating data measurements, tissues are subjected to a preliminary s ...

2016

Fast rates by transferring from auxiliary hypotheses

Ilja Kuzborskij

In this work we consider the learning setting where, in addition to the training set, the learner receives a collection of auxiliary hypotheses originating from other tasks. We focus on a broad class of ERM-based linear algorithms that can be instantiated ...

2016

Random sampling of bandlimited signals on graphs

Pierre Vandergheynst, Rémi Gribonval, Gilles Puy, Nicolas Tremblay

We study the problem of sampling

k

-bandlimited signals on graphs. We propose two sampling strategies that consist in selecting a small subset of nodes at random. The first strategy is non-adaptive, \ie, independent of the graph structure, and its perform ...

2015

Stochastic Spectral Descent for Restricted Boltzmann Machines.

Volkan Cevher

Restricted Boltzmann Machines (RBMs) are widely used as building blocks for deep learning models. Learning typically proceeds by using stochastic gradient descent, and the gradients are estimated with sampling methods. However, the gradient estimation is a ...

2015

Linear Bayesian Reinforcement Learning

Christos Dimitrakakis, Nikolaos Tziortziotis

This paper proposes a simple linear Bayesian approach to reinforcement learning. We show that with an appropriate basis, a Bayesian linear Gaussian model is sufficient for accurately estimating the system dynamics, and in particular when we allow for corre ...

2013

Adaptive conformational sampling based on replicas

Jérémy Curuksu

Computer simulations of biomolecules such as molecular dynamics simulations are limited by the time scale of conformational rearrangements. Several sampling techniques are available to search the multi-minima free energy landscape but most efficient, time- ...

Springer-Verlag2012

On Sampling a High-Dimensional Bandlimited Field on a Union of Shifted Lattices

Martin Vetterli, Jayakrishnan Unnikrishnan

We study the problem of sampling a high-dimensional bandlimited field on a union of shifted lattices under certain assumptions motivated by some practical sampling applications. Under these assumptions, we show that simple necessary and sufficient conditio ...

Ieee2012

On the performance of random reshuffling in stochastic learning

Graph Chatbot

Chat with Graph Search

Stochastic gradient descent with finite samples sizes

Attributing Aliasing Artifacts in Dirty Intensity Fields to their Parent Source

Theory of representation learning in cortical neural networks

Influence of loading history on mechanical properties of biomaterials

Fast rates by transferring from auxiliary hypotheses

Random sampling of bandlimited signals on graphs

Stochastic Spectral Descent for Restricted Boltzmann Machines.

Linear Bayesian Reinforcement Learning

Adaptive conformational sampling based on replicas

On Sampling a High-Dimensional Bandlimited Field on a Union of Shifted Lattices

Theory of representation learning in cortical neural networks

Random sampling of bandlimited signals on graphs

Stochastic gradient descent with finite samples sizes

Stochastic Spectral Descent for Restricted Boltzmann Machines.

Adaptive conformational sampling based on replicas

Linear Bayesian Reinforcement Learning

Attributing Aliasing Artifacts in Dirty Intensity Fields to their Parent Source

Influence of loading history on mechanical properties of biomaterials

On Sampling a High-Dimensional Bandlimited Field on a Union of Shifted Lattices

Fast rates by transferring from auxiliary hypotheses