works on

From the 1 of 35 linked papers with an AI index.

activity
20242026
collaborators

35 papers

cs.LG2026

Stochastic Autoregressive Learning

Ilan Doron-Arad, Idan Mehalel, Elchanan Mossel

Motivated by LLMs, which generate outputs by iteratively sampling from next-token distributions, we introduce a PAC-learning model for binary stochastic autoregressive learning. Th…

cs.DS2026

Recovering Assignments with One-Sided Noise

Cassandra Marcussen, Elchanan Mossel, Colin Sandon

We study the query complexity of recovering a planted assignment from a random constraint-satisfaction instance with one-sided noise. We consider the following 1-CNF recovery probl…

cs.DS2026

Learning and Testing Convex Functions

Renato Ferreira Pinto, Cassandra Marcussen, Elchanan Mossel +1

The paper investigates how to learn and test real-valued convex functions under the Gaussian distribution, providing algorithms with explicit sample‑complexity bounds assuming the…

cs.CG2026

Denoising Distances in Metric Measure Spaces

Han Huang, Pakawut Jiradilok, Elchanan Mossel

Recent work studied the problem of finding clusters and denoising pairwise distances from noisy distances of points sampled on a manifold. We study the same problems in more genera…

cs.CC2026

Depth Lower Bounds for ReLU Networks with Binary Inputs

Neil Krishnan, Elchanan Mossel

We study the role of depth in ReLU networks with discrete (Boolean) inputs and real-valued outputs, complementing two established lines of work. For Boolean inputs, striking depth…

math.PR2026

Multiplayer Games of War

Axel Adjei, Neil Krishnan, Elchanan Mossel

A recent paper by Bhatia, Chin, Mani, and Mossel (2026) defined stochastic processes modeling the game of War for {\em two players} with cards. That paper showed that these mod…