paper

Algorithmic and Minimax Complexities in Kernel Bandits

paperactiveprovisionalalgorithmic-and-minimax-complexities-in-kernel-bandits-41405204·1 events·first seen 7d ago

Aliases: Algorithmic and Minimax Complexities in Kernel Bandits

Co-occurring entities

More like this (12)

Minimax Density Invariant Risk Minimization Regret Minimization with Adaptive Opponents in Repeated Games Second-Order Path Kernel Interpolation Formulas in Machine Learning Bayesian Multiobjective Optimization Bayesian Optimization Game-Theoretic Equilibria Pareto Optimal Policy Optimization Private Stochastic Convex Optimization ELBO variance minimization reward-induced maximum likelihood differentiable convex optimization

Recent events (1)

4arXiv · cs.LG·7d ago·source ↗

Unified MAIR framework bridges GP-UCB and DEC approaches in kernel bandits

A new arXiv preprint unifies two major theoretical frameworks for frequentist RKHS bandits — Gaussian-process upper confidence bound (GP-UCB) and decision-estimation-coefficient (DEC) methods — under a common algorithmic-information language called MAIR. The paper generalizes both the GP-UCB analysis and the MAMS algorithm, proposes a safeguarded master algorithm combining their advantages, and demonstrates that algorithmic complexity can be more informative than class-wide minimax certificates in overparameterized models. The work clarifies a foundational distinction between algorithmic information and minimax coefficients in bandit theory.

Evaluation and Benchmarking GP-UCB MAMS Algorithmic and Minimax Complexities in Kernel Bandits