
Accumulated Gradient Normalization
This work addresses the instability in asynchronous data parallel optimi...
read it

Unit Commitment using Nearest Neighbor as a ShortTerm Proxy
We devise the Unit Commitment Nearest Neighbor (UCNN) algorithm to be us...
read it

How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies
Using deep neural nets as function approximator for reinforcement learni...
read it

Benchmarking for Bayesian Reinforcement Learning
In the Bayesian Reinforcement Learning (BRL) setting, agents try to maxi...
read it

Efficient combination of pairswise feature networks
This paper presents a novel method for the reconstruction of a neural ne...
read it

MetaLearning of Exploration/Exploitation Strategies: The MultiArmed Bandit Case
The exploration/exploitation (E/E) dilemma arises naturally in many subf...
read it

Simple connectome inference from partial correlation statistics in calcium imaging
In this work, we propose a simple yet effective solution to the problem ...
read it

Lowrank optimization for distance matrix completion
This paper addresses the problem of lowrank distance matrix completion....
read it

Heterogeneous Tensor Decomposition for Clustering via Manifold Optimization
Tensors or multiarray data are generalizations of matrices. Tensor clust...
read it

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...
read it

Scenario trees and policy selection for multistage stochastic programming using machine learning
We propose a hybrid algorithmic strategy for complex stochastic optimiza...
read it

An anisotropy preserving metric for DTI processing
Statistical analysis of Diffusion Tensor Imaging (DTI) data requires a c...
read it

ClosedLoop Learning of Visual Control Policies
In this paper we present a general, flexible framework for learning mapp...
read it

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...
read it

ChanceConstrained Outage Scheduling using a Machine Learning Proxy
Outage scheduling aims at defining, over a horizon of several months to ...
read it

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...
read it

The Adaptive sampling revisited
The problem of estimating the number n of distinct keys of a large colle...
read it

Dynamic Chain Graph Models for Ordinal Time Series Data
This paper introduces sparse dynamic chain graph models for network infe...
read it

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