8 papers
The sharp SAT/UNSAT phase transition in random ellipsoid fitting
Theodor Misiakiewicz, Garrett G. Wen
Let be independent standard Gaussian vectors in . An \emph{ellipsoid fit} is a matrix such that for every , so t…
Dynamical mean-field limit and replica-symmetric free energy for the orthogonally-invariant SK model
Zhou Fan, Theodor Misiakiewicz, Leda Wang +1
We study a class of diffusion processes on interacting through a symmetric matrix . When eigenvectors of are Haar-uniform on the orth…
Positive Distribution Shift as a Framework for Understanding Tractable Learning
Marko Medvedev, Idan Attias, Elisabetta Cornacchia +3
We study a setting where the goal is to learn a target function f(x) with respect to a target distribution D(x), but training is done on i.i.d. samples from a different training di…
Statistical-Computational Trade-offs in Learning Multi-Index Models via Harmonic Analysis
Hugo Latourelle-Vigeant, Theodor Misiakiewicz
We study the problem of learning multi-index models (MIMs), where the label depends on the input only through an unknown -dimensional…
When does Gaussian equivalence fail and how to fix it: Non-universal behavior of random features with quadratic scaling
Garrett G. Wen, Hong Hu, Yue M. Lu +2
A major effort in modern high-dimensional statistics has been devoted to the analysis of linear predictors trained on nonlinear feature embeddings via empirical risk minimization (…
Learning single-index models via harmonic decomposition
Nirmit Joshi, Hugo Koubbi, Theodor Misiakiewicz +1
We study the problem of learning single-index models, where the label depends on the input only through an unknown one-dimensio…