3 papers
math.OC2026
Data-Driven Analysis of First-Order Methods via Distributionally Robust Optimization
Jisun Park, Vinit Ranjan, Bartolomeo Stellato
We consider the problem of analyzing the probabilistic performance of first-order methods when solving convex optimization problems drawn from an unknown distribution only accessib…
cs.LG2026
Distributionally-Robust Learning to Optimize
Vinit Ranjan, Jisun Park, Bartolomeo Stellato
We propose a distributionally robust approach to learning hyperparameters for first-order methods in convex optimization. Given a dataset of problem instances, we minimize a Wasser…
cs.SE2025
AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
Ori Press, Brandon Amos, Haoyu Zhao +21
Despite progress in language model (LM) capabilities, evaluations have thus far focused on models' performance on tasks that humans have previously solved, including in programming…