video thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization

Published on Feb 4, 20251667 Views

We develop a family of accelerated stochastic algorithms that optimize sums of convex functions. Our algorithms improve upon the fastest running time for empirical risk minimization (ERM), and in part

Related categories