//
sign in
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
Also, a shoutout to this amazing paper by @tonysf.bsky.social and collaborators, which is well worth reading: arxiv.org/abs/2502.07529
2mo
In this work, we study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new stochastic family of algorithms that uses the LMO to adapt to the geom...
arxiv.org
Training Deep Learning Models with Norm-Constrained LMOs
Gabriel Peyré