Tag
This paper studies predictive flow matching under distribution drift, proposing DyProd-FM which refits on dyadic historical prefixes and uses a sleeping Prod master to achieve minimax-optimal dynamic regret under both relative velocity risk variation and target-law variation, without requiring convexity or curvature assumptions.
This paper proposes a meta-learning framework for online convex optimization with indicator switching costs, achieving minimax-optimal dynamic regret bounds without prior knowledge of comparator variations.
This paper proposes a unified misspecification-reduction viewpoint for non-stationary linear bandits with round-specific feasible decision sets, achieving optimal dynamic regret without the restrictive orthogonal-structure assumption.
This paper studies piecewise-stationary low-rank linear contextual bandits, proposes the SPSC algorithm that achieves dynamic regret scaling with the intrinsic rank instead of the ambient dimension, and characterizes the identification boundary for subspace recovery under scalar feedback.