activity
20152026
most citedA Robust Spectral Algorithm for Overcomplete Tensor Decomposition

14 citations · 38 across the 13 of their papers we have counts for

collaborators
Showing cs.DSShow all

13 papers · 1 filter

cs.DS2026

Easy, robust approximate message passing for planted spike models

Misha Ivkov, Tselil Schramm

We present a simple and efficient algorithm for robust approximate message passing (AMP) in the spiked matrix setting. In particular, let be a sufficiently small cons…

cs.DS2024

Fast, robust approximate message passing

Misha Ivkov, Tselil Schramm

We give a fast, spectral procedure for implementing approximate-message passing (AMP) algorithms robustly. For any quadratic optimization problem over symmetric matrices with i…

cs.DS2024

Discrepancy Algorithms for the Binary Perceptron

Shuangping Li, Tselil Schramm, Kangjie Zhou

The binary perceptron problem asks us to find a sign vector in the intersection of independently chosen random halfspaces with intercept . We analyze the performance of the can…

cs.DS2023

Semidefinite programs simulate approximate message passing robustly

Misha Ivkov, Tselil Schramm

Approximate message passing (AMP) is a family of iterative algorithms that generalize matrix power iteration. AMP algorithms are known to optimally solve many average-case optimiza…

cs.DS2021

The SDP value of random 2CSPs

Amulya Musipatla, Ryan O'Donnell, Tselil Schramm +1

We consider a very wide class of models for sparse random Boolean 2CSPs; equivalently, degree-2 optimization problems over~. For each model , we identify…

cs.DS20217 cited

Robust Regression Revisited: Acceleration and Improved Estimation Rates

Arun Jambulapati, Jerry Li, Tselil Schramm +1

We study fast algorithms for statistical regression problems under the strong contamination model, where the goal is to approximately optimize a generalized linear model (GLM) give…