From the 1 of 9 linked papers with an AI index.
9 papers
Mesoscopic Rectangular Spikes under Subspace Local Laws: Outlier Values and Singular Subspaces
Yitzchak Shmalo
A rectangular data matrix is often modelled as noise plus a signal of low rank. When that rank is fixed the picture is classical: a signal direction must exceed a critical strength…
Extreme least singular values of random row submatrices with bounded-density subgaussian entries
Xiufan Yang, Shu Wen, Yitzchak Shmalo
Let be a centered real subgaussian random variable with positive variance and a bounded Lebesgue density, and let have independent entries dist…
Randomly initialized autoencoders: fixed points and edge-of-chaos
Leonid Berlyand, Roman Sarapin, Yitzchak Shmalo +2
In this paper we study autoencoders, a special class of deep neural nets (DNNs) whose performance can be characterized via their fixed points. This perspective naturally raises que…
The storage capacity of the Ising perceptron: verification of the outstanding numerical conditions
Yitzchak Shmalo
The paper gives a rigorous computer‑assisted proof that the storage capacity of the zero‑margin Ising perceptron converges to the constant α≈0.8330786 predicted by Krauth and Mézar…
A law of robustness for two-layer neural networks with arbitrary weights
Yitzchak Shmalo
Bubeck, Li and Nagaraj conjectured that, for generic data, any two-layer neural network with neurons that fits noisy labels must have Lipschitz constant at least of order $…
Extreme least singular values of Gaussian row submatrices and a phase retrieval stability problem
Yitzchak Shmalo
Let and . If has independent standard Gaussian entries and $N_m/m\toÎ…