88 citations · 94 across the 13 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
math.OC2026
AltGDA Achieves Global Ergodic Convergence in Matrix Games
Tianlong Nan, Garud Iyengar, Christian Kroer +1
Alternating gradient descent-ascent (AltGDA) is a simple and practically effective method for solving finite two-player zero-sum matrix games. However, the theory of AltGDA remains…
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…