Tag
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 note presents a research moment where Codex helped find a new rare-switching rule for private linear bandits, using the generalized Rayleigh quotient to overcome the failure of determinant-based monotonicity due to Gaussian noise.