2018/06/05 by Jonathan Weed, Weed, Jonathan · 5 citations
Computer Science · Engineering · Mathematics · #Advanced Optimization Algorithms Research #Bayesian Modeling and Causal Inference #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Optimization and Mathematical Programming #cs.LG #math.OC #stat.ML
paper · pdf · doi:10.48550/arxiv.1806.01879
To appear at Conference on Learning Theory (COLT), 2018
arxiv created 2018/06/05 · openalex publication_date 2018/06/05 · arxiv updated 2018/06/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Solving linear programs by using entropic penalization has recently attracted new interest in the optimization community, since this strategy forms the basis for the fastest-known algorithms for the optimal transport problem, with many applications in modern large-scale machine learning. Crucial to these applications has been an analysis of how quickly solutions to the penalized program approach true optima to the original linear program. More than 20 years ago, Cominetti and San Martín showed that this convergence is exponentially fast; however, their proof is asymptotic and does not give any indication of how accurately the entropic program approximates the original program for any particular choice of the penalization parameter. We close this long-standing gap in the literature regarding entropic penalization by giving a new proof of the exponential convergence, valid for any linear program. Our proof is non-asymptotic, yields explicit constants, and has the virtue of being extremely simple. We provide matching lower bounds and show that the entropic approach does not lead to a near-linear time approximation scheme for the linear assignment problem.