Random matrix analysis to balance between supervised and unsupervised learning under the low density separation assumption

V Feofanov, M Tiomoko… - … Conference on Machine …, 2023 - proceedings.mlr.press
We propose a theoretical framework to analyze semi-supervised classification under the low
density separation assumption in a high-dimensional regime. In particular, we introduce …

Enhancing Multivariate Time Series Forecasting via Multi-Task Learning and Random Matrix Theory

R Ilbert, M Tiomoko, C Louart, V Feofanov… - … Workshop on Time …, 2024 - openreview.net
We present a novel approach to multivariate time series forecasting by framing it as a multi-
task learning problem. We propose an optimization strategy that enhances single-channel …

Random matrix theory and concentration of the measure theory for the study of high dimension data processing.

C Louart - 2023 - theses.hal.science
The main objective of this thesis is to introduce a probabilistic framework taken from the
theory of concentration of measure to study of machine learning algorithms. The …

A Concentration of Measure Framework to study convex problems and other implicit formulation problems in machine learning

C Louart - arXiv preprint arXiv:2010.09877, 2020 - arxiv.org
This paper provides a framework to show the concentration of solutions $ Y^* $ to convex
minimizing problem where the objective function $\phi (X)(Y) $ depends on some random …