LGDSGTSTMLOct 22, 2024

Computing Optimal Regularizers for Online Linear Optimization

arXiv:2410.17336v13 citationsh-index: 49COLT
Originality Highly original
AI Analysis

This provides a universal solution for optimizing regret bounds in online learning, though it is incremental as it builds on prior work like Srebro et al., 2011.

The paper tackles the problem of selecting optimal regularizers for Follow-the-Regularized-Leader algorithms in online linear optimization, showing that their algorithm outputs a regularizer guaranteeing regret within a constant factor of the best possible bound for any convex symmetric action and loss sets.

Follow-the-Regularized-Leader (FTRL) algorithms are a popular class of learning algorithms for online linear optimization (OLO) that guarantee sub-linear regret, but the choice of regularizer can significantly impact dimension-dependent factors in the regret bound. We present an algorithm that takes as input convex and symmetric action sets and loss sets for a specific OLO instance, and outputs a regularizer such that running FTRL with this regularizer guarantees regret within a universal constant factor of the best possible regret bound. In particular, for any choice of (convex, symmetric) action set and loss set we prove that there exists an instantiation of FTRL which achieves regret within a constant factor of the best possible learning algorithm, strengthening the universality result of Srebro et al., 2011. Our algorithm requires preprocessing time and space exponential in the dimension $d$ of the OLO instance, but can be run efficiently online assuming a membership and linear optimization oracle for the action and loss sets, respectively (and is fully polynomial time for the case of constant dimension $d$). We complement this with a lower bound showing that even deciding whether a given regularizer is $α$-strongly-convex with respect to a given norm is NP-hard.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes