-
Stumping along a Summary for Exploration & Exploitation Challenge 2011
International audience -
Batch and online learning algorithms for Nonconvex Neyman-Pearson classification
International audience -
Shift & 2D Rotation Invariant Sparse Coding for Multivariate Signals
International audience -
Minimax Number of Strata for Online Stratified Sampling given Noisy Samples
We consider the problem of online stratified sampling for Monte Carlo integration of a function given a finite budget of $n$ noisy evaluations to the function. More... -
Learning networks : a field guide to teaching and learning online
Excerpts available on Google Books (see link below). For integral book, go to publisher's website : http://mitpress.mit.edu/catalog/item/default.asp?ttype=2&tid=7592 -
Learning with stochastic inputs and adversarial outputs
International audience -
An Adaptive Incremental Clustering Method Based on the Growing Neural Gas Alg...
International audience -
Confusion-Based Online Learning and a Passive-Aggressive Scheme
International audience -
Bandits Games and Clustering Foundations
This thesis takes place within the machine learning theory. In particular it focuses on three sub-domains, stochastic optimization, online learning and clustering.... -
A Stream-Based Semi-Supervised Active Learning Approach for Document Classifi...
International audience -
Multivariate Temporal Dictionary Learning for EEG
International audience -
Empirical Bernstein Inequality for Martingales : Application to Online Learning
In this article we present a new empirical Bernstein inequality for bounded martingale difference sequences. This inequality refines the one by Freedman [1975] and is... -
Online Learning with Multiple Operator-valued Kernels
We consider the problem of learning a vector-valued function f in an online learning setting. The function f is assumed to lie in a reproducing Hilbert space of... -
GT2FC : An online Growing interval Type-2 self-learning Fuzzy Classifier
International audience -
ILClass: Error-Driven Antecedent Learning For Evolving Takagi-Sugeno Classifi...
International audience -
On Some Unsupervised Learning Problems for Highly Dependent Time Series
This thesis is devoted to the theoretical analysis of unsupervised learning problems involving highly dependent time-series. Two fundamental problems are considered,... -
Online Matrix Completion Through Nuclear Norm Regularisation
Corrected a typo in the affiliation -
Decomposition and dictionary learning for 3D trajectories
International audience
