Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions
Elisabetta Cornacchia, Dan Mikulincer, Elchanan Mossel
The problem of learning single index and multi index models has gained significant interest as a fundamental task in high-dimensional statistics. Many recent works have analysed gr…
cs.LG2025
Learning High-Degree Parities: The Crucial Role of the Initialization
Emmanuel Abbe, Elisabetta Cornacchia, Jan HÄ zÅa +1
Parities have become a standard benchmark for evaluating learning algorithms. Recent works show that regular neural networks trained by gradient descent can efficiently learn degre…