Publications

Accelerating Continuous Variable Coherent Ising Machines via Momentum - R. A. Brown, D. Venturelli, M. Pavone, D. E. Bernal Neira
- Under Review - 2023
We integrate Adam and momentume optimizers with the continuous variable Coherent Ising Machine (CV-CIM) dynamical solver. We show that both optimization techniques can improve the convergence speed and sample diversity of the CV-CIM, while Adam improves the stability of the resulting system

A Copositive Framework for Analysis of Hybrid Ising-Classical Algorithms - R. A. Brown, D. E. Bernal Neira, D. Venturelli, M. Pavone
- SIAM Journal of Optimization - 2023
We present a formal analysis of hybrid algorithms in the context of solving mixed-binary quadratic programs (MBQP) via Ising solvers. We leverage copositive optimization and cutting-plane algorithms to derive an algorithm that provable shifts complexity onto the subroutine handled by the Ising solver.

A Unified View of SDP-based Neural Network Verification through Completely Positive Programming - R. Brown, E. Schmerling, N. Azizan, M. Pavone
- Int. Conf. on Artificial Intelligence and Statistics - 2022
We unify several SDP relaxations for ReLU neural network verification by providing an exact convex formulation as a completely-positive program. This provides a path for relaxations that systematically trade off tightness and efficiency.

On Local Computation for Network-Structured Convex Optimization in Multi-Agent Systems - R. A. Brown, F. Rossi, K. Solovey, M. Tsao, M. T. Wolf, M. Pavone
- IEEE Transactions on Control of Network Systems - 2021
We extend our prior work by providing tighter bounds on the locality of problems through the conjugate-gradient algorithm, allowing the decay results to be applied to all linearly constrained strongly convex optimization problems.

Exploiting Locality and Structure for Distributed Optimization in Multi-Agent Systems - R. A. Brown, F. Rossi, K. Solovey, M. T. Wolf, M. Pavone
- European Control Conference (Best Student Paper Award Finalist) - 2020
We develop a rigorous measure of “locality” that relates the structural properties of a linearly-constrained convex optimization problem to the amount of information that agents should exchange to compute an arbitrarily high-quality approximation of its solution. We leverage the notion of locality to develop a locality-aware distributed optimization algorithm.