A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Multitask Online Mirror Descent
[article]
2022
arXiv
pre-print
We introduce and analyze MT-OMD, a multitask generalization of Online Mirror Descent (OMD) which operates by sharing updates between tasks. We prove that the regret of MT-OMD is of order √(1 + σ^2(N-1))√(T), where σ^2 is the task variance according to the geometry induced by the regularizer, N is the number of tasks, and T is the time horizon. Whenever tasks are similar, that is σ^2 ≤ 1, our method improves upon the √(NT) bound obtained by running independent OMDs on each task. We further
arXiv:2106.02393v3
fatcat:nwzuhlr3ofhydiolalcqmznrie