collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Pruning Deep Neural Networks via the Marchenko--Pastur Distribution

Leonid Berlyand, Theo Bourdais, Houman Owhadi +1

We study a Marchenko--Pastur (MP) random-matrix approach to pruning deep neural networks with very small post-pruning fine-tuning budgets. The main practical contribution is accura…

cs.LG2025

Operator Learning at Machine Precision

Aras Bacho, Aleksei G. Sorokin, Xianjin Yang +6

Neural operator learning methods have garnered significant attention in scientific computing for their ability to approximate infinite-dimensional operators. However, increasing th…

cs.LG2025

Codiscovering graphical structure and functional relationships within data: A Gaussian Process framework for connecting the dots

Théo Bourdais, Pau Batlle, Xianjin Yang +3

Most problems within and beyond the scientific domain can be framed into one of the following three levels of complexity of function approximation. Type 1: Approximate an unknown f…

cs.LG2025

Pruning Deep Neural Networks via a Combination of the Marchenko-Pastur Distribution and Regularization

Leonid Berlyand, Theo Bourdais, Houman Owhadi +1

Deep neural networks (DNNs) have brought significant advancements in various applications in recent years, such as image recognition, speech recognition, and natural language proce…

cs.LG2025

Minimal Variance Model Aggregation: A principled, non-intrusive, and versatile integration of black box models

Théo Bourdais, Houman Owhadi

Whether deterministic or stochastic, models can be viewed as functions designed to approximate a specific quantity of interest. We introduce Minimal Empirical Variance Aggregation…