arXiv:2607. 08789v1 Announce Type: new Abstract: Bayesian and multiplicative-weights updates reweight experts, models, or actions from sequential feedback.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
The paper introduces a two-player zero-sum repeated game between a learner and nature that simultaneously captures Bayesian updating and an exact decomposition of exponential-weights regret. The game’s terminal payoff reflects the maximum gain a comparator can achieve given a fixed relative entropy from the prior, while the one-step constraint limits nature’s move by an information budget. The resulting regret splits into three precise components—per-round information loss, an additive retempering drift, and the comparator’s information relative to the prior—providing a unified framework that explains concentration phenomena, large-deviation bounds, and various learning methods such as bandits, posterior sampling, aggregation, and boosting.
arXiv:2609.37932v1 Announce Type: new Abstract: Systems operating in dynamic environments require timely updates to sustain performance. For resource-intensive systems such as machine learning models...
arXiv:2601. 07094v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) iteratively fits a Gaussian process (GP) surrogate to accumulated evaluations and selects new queries via an acquisition function.
The paper analyzes Bayesian linear bandits with isotropic Gaussian parameters, independent Gaussian arms, and Gaussian reward noise when the time horizon scales with the dimension. It derives explicit limits for the normalized posterior uncertainty and parameter overlaps, yielding exact regret curves for several policies—including Thompson sampling, posterior‑mean greedy selection, and scaled‑covariance variants. The results show that posterior‑mean greedy selection achieves the optimal Bayes regret, while Thompson sampling incurs a strictly larger leading regret whose ratio to greedy lies between one and two, approaching two for long horizons.
The paper introduces a straightforward framework that transforms dynamic regret minimization into switching regret minimization by constructing an unbiased random sequence for any comparator sequence. Using this reduction, the authors derive dynamic regret bounds for strongly convex and exp-concave losses of “~O(T^{1/3}P_T^{2/3})” and for general convex losses of “O(√{T(1+P_T)})”, matching known minimax optimal results. The approach leverages off-the-shelf switching regret algorithms and controlled variance to achieve these bounds.
arXiv:2602.10727v3 Announce Type: replace Abstract: Rising Multi-Armed Bandits (RMABs) model sequential decision problems where each arm's expected reward improves with repeated pulls. In such proble...