Title | ||
---|---|---|
Uniform regret bounds over Rd for the sequential linear regression problem with the square loss. |
Abstract | ||
---|---|---|
We consider the setting of online linear regression for arbitrary deterministic sequences, with the square loss. We are interested in regret bounds that hold uniformly over all vectors in $u ∈ R^d$. Vovk (2001) showed a d ln T lower bound on this uniform regret. We exhibit forecasters with closed-form regret bounds that match this d ln T quantity. To the best of our knowledge, earlier works only provided closed-form regret bounds of 2d ln T + O(1). |
Year | Venue | Field |
---|---|---|
2018 | ALT | Discrete mathematics,Mathematical optimization,Regret,Upper and lower bounds,Mathematics,Linear regression |
DocType | Volume | Citations |
Journal | abs/1805.11386 | 0 |
PageRank | References | Authors |
0.34 | 2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pierre Gaillard | 1 | 79 | 10.89 |
Sebastien Gerchinovitz | 2 | 8 | 2.24 |
Malo Huard | 3 | 0 | 0.34 |
Gilles Stoltz | 4 | 351 | 31.53 |