GPU-Accelerated First-Order Method with Randomized Sampling for Binary Integer Programs
We present a scalable, GPU-accelerated algorithmic framework for large binary integer programs that operates end-to-end with minimal synchronization overhead. The proposed method combines a first-order routine that guides search in the continuous relaxation with a randomized, feasibility-aware sampling module that generates batched binary candidates. We establish a residual convergence guarantee for the first-order component in … Read more