Liam O'Carroll — accepted AI-conference papers

2025

Isotropic Noise in Stochastic and Quantum Convex Optimization

Annie Marsden, Liam O'Carroll, Aaron Sidford, Chenyi Zhang

NeurIPS 2025poster

We consider the problem of minimizing a $d$-dimensional Lipschitz convex function using a stochastic gradient oracle. We introduce and motivate a setting where the noise of the stochastic gradient is isotropic in that it is bounded in every direction with high probability. We then develop an algorit…

Cited by 0 Source ↗Scholar ↗

2022

The Burer-Monteiro SDP method can fail even above the Barvinok-Pataki bound

Liam O'Carroll, Vaidehi Srinivas, Aravindan Vijayaraghavan

NeurIPS 2022accept

The most widely used technique for solving large-scale semidefinite programs (SDPs) in practice is the non-convex Burer-Monteiro method, which explicitly maintains a low-rank SDP solution for memory efficiency. There has been much recent interest in obtaining a better theoretical understanding of th…

Cited by 9 Source ↗PDF ↗code ↗Scholar ↗