DeepAI

Université de Liège

∙ Liège , Belgium ∙ 0 followers

The University of Liège, in Liège, Wallonia, Belgium, is a major public university in the French Community of Belgium.

Featured Researchers

Damien Ernst
31 publications
Bamdev Mishra
30 publications
Vincent Francois-Lavet
18 publications
Marcel Ausloos
15 publications
Louis Wehenkel
14 publications
Antonio Sutera
7 publications
Joeri Hermans
6 publications
Yvik Swan
6 publications
Raphael Fonteneau
5 publications
Francis Maes
3 publications
B. Mishra
2 publications

∙ 07/22/2012

Optimal discovery with probabilistic expert advice: finite time analysis and macroscopic optimality

We consider an original problem that arises from the issue of security a...

Sébastien Bubeck, et al. ∙

∙ 07/18/2018

Intriguing yet simple skewness - kurtosis relation in economic and demographic data distributions; pointing to preferential attachment processes

In this paper, we propose that relations between high order moments of d...

Marcel Ausloos, et al. ∙

∙ 05/24/2018

Dynamic Chain Graph Models for Ordinal Time Series Data

This paper introduces sparse dynamic chain graph models for network infe...

Pariya Behrouzi, et al. ∙

∙ 05/21/2018

The Adaptive sampling revisited

The problem of estimating the number n of distinct keys of a large colle...

Guy Louchard, et al. ∙

∙ 05/04/2018

Regularity of solutions of the Stein equation and rates in the multivariate central limit theorem

Consider the multivariate Stein equation Δ f - x·∇ f = h(x) - E h(Z), wh...

Thomas Gallouët, et al. ∙

∙ 01/01/2018

Chance-Constrained Outage Scheduling using a Machine Learning Proxy

Outage scheduling aims at defining, over a horizon of several months to ...

Gal Dalal, et al. ∙

∙ 11/30/2017

Benford's law first significant digit and distribution distances for testing the reliability of financial reports in developing countries

We discuss a common suspicion about reported financial data, in 10 indus...

Jing Shi, et al. ∙

∙ 10/10/2011

Closed-Loop Learning of Visual Control Policies

In this paper we present a general, flexible framework for learning mapp...

S. R. Jodogne, et al. ∙

∙ 10/10/2012

An anisotropy preserving metric for DTI processing

Statistical analysis of Diffusion Tensor Imaging (DTI) data requires a c...

Anne Collard, et al. ∙

∙ 12/19/2011

Scenario trees and policy selection for multistage stochastic programming using machine learning

We propose a hybrid algorithmic strategy for complex stochastic optimiza...

Boris Defourny, et al. ∙

∙ 10/06/2017

Accumulated Gradient Normalization

This work addresses the instability in asynchronous data parallel optimi...

Joeri Hermans, et al. ∙

∙ 04/07/2015

Heterogeneous Tensor Decomposition for Clustering via Manifold Optimization

Tensors or multiarray data are generalizations of matrices. Tensor clust...

Yanfeng Sun, et al. ∙

∙ 04/24/2013

Low-rank optimization for distance matrix completion

This paper addresses the problem of low-rank distance matrix completion....

B. Mishra, et al. ∙

∙ 06/30/2014

Simple connectome inference from partial correlation statistics in calcium imaging

In this work, we propose a simple yet effective solution to the problem ...

Antonio Sutera, et al. ∙

∙ 07/22/2012

Meta-Learning of Exploration/Exploitation Strategies: The Multi-Armed Bandit Case

The exploration/exploitation (E/E) dilemma arises naturally in many subf...

Francis Maes, et al. ∙

∙ 05/30/2015

Efficient combination of pairswise feature networks

This paper presents a novel method for the reconstruction of a neural ne...

Pau Bellot, et al. ∙

∙ 09/14/2015

Benchmarking for Bayesian Reinforcement Learning

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maxi...

Michael Castronovo, et al. ∙

∙ 12/07/2015

How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies

Using deep neural nets as function approximator for reinforcement learni...

Vincent Francois-Lavet, et al. ∙

∙ 11/30/2016

Unit Commitment using Nearest Neighbor as a Short-Term Proxy

We devise the Unit Commitment Nearest Neighbor (UCNN) algorithm to be us...

Gal Dalal, et al. ∙