Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
A Statistical Analysis for Per-Instance Evaluation of Stochastic Optimizers: Avoiding Unreliable Conclusions
Moslem Noori, Elisabetta Valiante, Thomas Van Vaerenbergh +2
A key trait of stochastic optimizers is that multiple runs of the same optimizer in attempting to solve the same problem can produce different results. As a result, their performan…
cs.LG2025
Nonlocal Monte Carlo via Reinforcement Learning
Dmitrii Dobrynin, Masoud Mohseni, John Paul Strachan
Optimizing or sampling complex cost functions of combinatorial optimization problems is a longstanding challenge across disciplines and applications. When employing family of conve…