Related papers: Robust Bayesian Optimization via Tempered Posteriors

Robust Bayesian Optimization via Tempered Posteriors

URL: http://arxiv.org/abs/2601.07094v1
Date: Sun, 11 Jan 2026 23:34:24 GMT
Title: Robust Bayesian Optimization via Tempered Posteriors
Authors: Jiguang Li, Hengrui Luo,
Abstract summary: We develop a robust GP-based BO via tempered posterior updates to mitigate overconfidence under local misspecifications.<n>We show that tempering yields sharper worst-case regret guarantees than the standard posterior $(=1)$, with the most favorable guarantees occurring near the classical EI choice.
Score: 1.6042394978941517
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Bayesian optimization (BO) iteratively fits a Gaussian process (GP) surrogate to accumulated evaluations and selects new queries via an acquisition function such as expected improvement (EI). In practice, BO often concentrates evaluations near the current incumbent, causing the surrogate to become overconfident and to understate predictive uncertainty in the region guiding subsequent decisions. We develop a robust GP-based BO via tempered posterior updates, which downweight the likelihood by a power $α\in (0,1]$ to mitigate overconfidence under local misspecification. We establish cumulative regret bounds for tempered BO under a family of generalized improvement rules, including EI, and show that tempering yields strictly sharper worst-case regret guarantees than the standard posterior $(α=1)$, with the most favorable guarantees occurring near the classical EI choice. Motivated by our theoretic findings, we propose a prequential procedure for selecting $α$ online: it decreases $α$ when realized prediction errors exceed model-implied uncertainty and returns $α$ toward one as calibration improves. Empirical results demonstrate that tempering provides a practical yet theoretically grounded tool for stabilizing BO surrogates under localized sampling.

Related papers

Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features [9.140494844209336]
We propose a robust Bayesian formulation of random feature (RF) regression that accounts explicitly for prior and likelihood misspecification.<n>We derive explicit and tractable bounds for the resulting lower and upper posterior predictive envelopes.
arXiv Detail & Related papers (2026-02-22T10:50:04Z)
Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences [51.56484100374058]
We study stopping rules for gradient descent (SGD) for convex optimization.<n>We develop an anytime-valid, data-dependent upper confidence sequence for the weighted average suboptimality of projected SGD.<n>These are the first rigorous, time-uniform performance guarantees and finitetime $varepsilon$-optimality certificates.
arXiv Detail & Related papers (2025-12-15T09:26:45Z)
Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration [52.70324949884702]
We quantify the excess risk incurred using approximate posterior probabilities in batch binary decision-making.<n>We identify regimes where recalibration alone addresses most of the regret, and regimes where the regret is dominated by the grouping loss.<n>On NLP experiments, we show that these quantities identify when the expected gain of more advanced post-training is worth the operational cost.
arXiv Detail & Related papers (2025-03-23T10:52:36Z)
Robust Bayesian Optimization via Localized Online Conformal Prediction [37.549297668783254]
We introduce localized online conformal prediction-based Bayesian optimization (LOCBO)<n>LOCBO calibrates the GP model through localized online conformal prediction (CP)<n>We provide theoretical performance guarantees for LOCBO's iterates that hold for the unobserved objective function.
arXiv Detail & Related papers (2024-11-26T12:45:54Z)
Regret Analysis for Randomized Gaussian Process Upper Confidence Bound [9.967062483758632]
This paper analyzes the randomized variant of GP-UCB called improved randomized GP-UCB.<n>We show that GP-UCB using a constant confidence parameter can incur linearly growing expected cumulative regret.
arXiv Detail & Related papers (2024-09-02T06:49:29Z)
Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
arXiv Detail & Related papers (2023-12-07T15:55:58Z)
U-Calibration: Forecasting for an Unknown Agent [29.3181385170725]
We show that optimizing forecasts for a single scoring rule cannot guarantee low regret for all possible agents. We present a new metric for evaluating forecasts that we call U-calibration, equal to the maximal regret of the sequence of forecasts.
arXiv Detail & Related papers (2023-06-30T23:05:26Z)
Autoregressive Bandits [58.46584210388307]
We propose a novel online learning setting, Autoregressive Bandits, in which the observed reward is governed by an autoregressive process of order $k$. We show that, under mild assumptions on the reward process, the optimal policy can be conveniently computed. We then devise a new optimistic regret minimization algorithm, namely, AutoRegressive Upper Confidence Bound (AR-UCB), that suffers sublinear regret of order $widetildemathcalO left( frac(k+1)3/2sqrtnT (1-G
arXiv Detail & Related papers (2022-12-12T21:37:36Z)
Sample-Efficient Optimisation with Probabilistic Transformer Surrogates [66.98962321504085]
This paper investigates the feasibility of employing state-of-the-art probabilistic transformers in Bayesian optimisation. We observe two drawbacks stemming from their training procedure and loss definition, hindering their direct deployment as proxies in black-box optimisation. We introduce two components: 1) a BO-tailored training prior supporting non-uniformly distributed points, and 2) a novel approximate posterior regulariser trading-off accuracy and input sensitivity to filter favourable stationary points for improved predictive performance.
arXiv Detail & Related papers (2022-05-27T11:13:17Z)
Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability [48.62272919754204]
We study generalization in Bayesian RL under the probably approximately correct (PAC) framework. Our main contribution is showing that by adding regularization, the optimal policy becomes stable in an appropriate sense.
arXiv Detail & Related papers (2021-09-24T07:48:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.