2 problems

0 votes0 replies0 views
Alex-GDA last-iterate convergence conjecture for convex-concave objectives
Let $f$ be a convex-concave objective function with $(L_x,L_y,L_{xy})$ -Lipschitz gradients, and let Alex-GDA denote the extrapolated alternating gradient descent-ascent method. Ale…
Conjectureopenalternating-updates last-iterate-convergence minimax-optimizationarXiv posted 2 days ago
0 votes0 replies0 views
Alt-GDA convergence lower-bound conjecture for non-quadratic objectives
Let ${\mathcal F}(\mu_x,\mu_y,L_x,L_y,L_{xy})$ denote the function class considered for the alternating gradient descent-ascent method, and let $\kappa_x$ , $\kappa_y$ , and…
Conjectureopenalternating-updates convergence-lower-bounds minimax-optimizationarXiv posted 2 days ago

Alex-GDA last-iterate convergence conjecture for convex-concave objectives