TP-VR-OPT achieves O(√(d E[S_T])) prediction-adaptive regret in two-point bandit convex optimization, with a matching Ω(√E[S_T]) lower bound up to √d, while single-point feedback cannot benefit from predictions.
Online learning with a hint,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bandit Convex Optimization with Gradient Prediction Adaptivity
TP-VR-OPT achieves O(√(d E[S_T])) prediction-adaptive regret in two-point bandit convex optimization, with a matching Ω(√E[S_T]) lower bound up to √d, while single-point feedback cannot benefit from predictions.