activity
20122026
most citedPlug-and-Play Methods Provably Converge with Properly Trained Denoisers

101 citations · 142 across the 9 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

math.OC2026

A Domain-Specific Harness for End-to-End Automation of Optimization Research

Heechang Kim, Ernest K. Ryu, Shuvomoy Das Gupta

We present AutoOPT, a domain-specific harness for end-to-end automation of optimization research. AutoOPT organizes the discovery of optimal first-order methods into four stages: n…