96 citations
8 papers
Co-SIVI: A Correlated Semi-Implicit Variational Approach for Spatial Models
Sébastien Garneau, Carlos T. P. Zanini, Alexandra M. Schmidt
We propose correlated semi-implicit variational inference (Co-SIVI), a scalable approach for full posterior approximation in large spatial models with exponential-family likelihood…
Expectation consistency for calibration of neural networks
Lucas Clarté, Bruno Loureiro, Florent Krzakala +1
Despite their incredible performance, it is well reported that deep neural networks tend to be overoptimistic about their prediction confidence. Finding effective and efficient cal…
From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks
Luca Arnaboldi, Ludovic Stephan, Florent Krzakala +1
This manuscript investigates the one-pass stochastic gradient descent (SGD) dynamics of a two-layer neural network trained on Gaussian data and labels generated by a similar, thoug…
Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap
Luca Pesce, Bruno Loureiro, Florent Krzakala +1
A simple model to study subspace clustering is the high-dimensional -Gaussian mixture model where the cluster means are sparse vectors. Here we provide an exact asymptotic chara…
Deciphering infant mortality. Part 1: empirical evidence
Sylvie Berrut, Violette Pouillard, Peter Richmond +1
This paper is not (or at least not only) about human infant mortality. In line with reliability theory, "infant" will refer here to the time interval following birth during which t…
Discussion: One-step sparse estimates in nonconcave penalized likelihood models
Peter Bühlmann, Lukas Meier
Discussion of ``One-step sparse estimates in nonconcave penalized likelihood models'' [arXiv:0808.1012]