arXiv Machine Learning By Ian D'Ambrosio (Nth Research Collective)

A Constant-Competitive Algorithm for Dynamic Mixture-of-Experts Serving

Read the original on arXiv Machine Learning →

arXiv:2608. 16947v1 Announce Type: cross Abstract: Huang, Lou, and Xiao introduced Dynamic Mixture-of-Experts Serving and gave an O(sqrt(log k))-competitive randomized algorithm for its integral primal problem, where k is the number of replica GPUs beyond the mandatory copy of each expert.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Statistics ML
Sep 10

A positive resolution of the gap-entropy conjecture

arXiv:2609.10529v1 Announce Type: cross Abstract: We prove the gap-entropy conjecture for fixed-confidence best-arm identification with independent unit-variance Gaussian arms, means in $[0,1]$, and...

By P. M. Aronow, Nathan Kallus, Patrick Lopatto