3 papers
cs.LG2019
Asymptotic Bayes risk for Gaussian mixture in a semi-supervised setting
Marc Lelarge, Leo Miolane
Semi-supervised learning (SSL) uses unlabeled data for training and has been shown to greatly improve performance when compared to a supervised approach on the labeled data availab…
math.ST2018
The distribution of the Lasso: Uniform control over sparse balls and adaptive parameter tuning
Léo Miolane, Andrea Montanari
The Lasso is a popular regression method for high-dimensional problems in which the number of parameters , is larger than the number of samples: . A useful…
math.PR2018
Phase transitions in spiked matrix estimation: information-theoretic analysis
Léo Miolane
We study here the so-called spiked Wigner and Wishart models, where one observes a low-rank matrix perturbed by some Gaussian noise. These models encompass many classical statistic…