Duality and Policy Evaluation in Distributionally Robust Bayesian Diffusion Control

• URL: http://arxiv.org/abs/2506.19294v2
• Date: Mon, 30 Jun 2025 22:38:52 GMT
• Title: Duality and Policy Evaluation in Distributionally Robust Bayesian Diffusion Control
• Authors: Jose Blanchet, Jiayi Cheng, Hao Liu, Yang Liu,
• Abstract summary: We consider a diffusion control problem of expected terminal numerical utility.<n>The controller imposes a prior distribution on the unknown drift of an underlying diffusion.<n>In practice, the prior will generally be incorrectly specified, and the degree of model misspecification can have a significant impact on policy performance.<n>We introduce a distributionally robust Bayesian control (DRBC) formulation in which the controller plays a game against an adversary who selects a prior in divergence neighborhood of a baseline prior.
• Score: 8.863520091178335
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider a Bayesian diffusion control problem of expected terminal utility maximization. The controller imposes a prior distribution on the unknown drift of an underlying diffusion. The Bayesian optimal control, tracking the posterior distribution of the unknown drift, can be characterized explicitly. However, in practice, the prior will generally be incorrectly specified, and the degree of model misspecification can have a significant impact on policy performance. To mitigate this and reduce overpessimism, we introduce a distributionally robust Bayesian control (DRBC) formulation in which the controller plays a game against an adversary who selects a prior in divergence neighborhood of a baseline prior. The adversarial approach has been studied in economics and efficient algorithms have been proposed in static optimization settings. We develop a strong duality result for our DRBC formulation. Combining these results together with tools from stochastic analysis, we are able to derive a loss that can be efficiently trained (as we demonstrate in our numerical experiments) using a suitable neural network architecture. As a result, we obtain an effective algorithm for computing the DRBC optimal strategy. The methodology for computing the DRBC optimal strategy is greatly simplified, as we show, in the important case in which the adversary chooses a prior from a Kullback-Leibler distributional uncertainty set.

Related papers

• Distributionally Robust Optimization with Adversarial Data Contamination [36.409282287280185]
  We focus on optimizing Wasserstein-1 DRO objectives for generalized linear models with convex Lipschitz loss functions.<n>Our primary contribution lies in a novel modeling framework that integrates robustness against training data contamination with robustness against distributional shifts.<n>This work establishes the first rigorous guarantees, supported by efficient computation, for learning under the dual challenges of data contamination and distributional shifts.
  arXiv  Detail & Related papers  (2025-07-14T18:34:10Z)
• BAPE: Learning an Explicit Bayes Classifier for Long-tailed Visual Recognition [78.70453964041718]
  Current deep learning algorithms usually solve for the optimal classifier by emphimplicitly estimating the posterior probabilities.<n>This simple methodology has been proven effective for meticulously balanced academic benchmark datasets.<n>However, it is not applicable to the long-tailed data distributions in the real world.<n>This paper presents a novel approach (BAPE) that provides a more precise theoretical estimation of the data distributions.
  arXiv  Detail & Related papers  (2025-06-29T15:12:50Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Risk-Controlling Model Selection via Guided Bayesian Optimization [35.53469358591976]
  We find a configuration that adheres to user-specified limits on certain risks while being useful with respect to other conflicting metrics. Our method identifies a set of optimal configurations residing in a designated region of interest. We demonstrate the effectiveness of our approach on a range of tasks with multiple desiderata, including low error rates, equitable predictions, handling spurious correlations, managing rate and distortion in generative models, and reducing computational costs.
  arXiv  Detail & Related papers  (2023-12-04T07:29:44Z)
• Boosted Control Functions: Distribution generalization and invariance in confounded models [10.503777692702952]
  We introduce a strong notion of invariance that allows for distribution generalization even in the presence of nonlinear, non-identifiable structural functions.<n>We propose the ControlTwicing algorithm to estimate the Boosted Control Function (BCF) using flexible machine-learning techniques.
  arXiv  Detail & Related papers  (2023-10-09T15:43:46Z)
• Equation Discovery with Bayesian Spike-and-Slab Priors and Efficient Kernels [57.46832672991433]
  We propose a novel equation discovery method based on Kernel learning and BAyesian Spike-and-Slab priors (KBASS) We use kernel regression to estimate the target function, which is flexible, expressive, and more robust to data sparsity and noises. We develop an expectation-propagation expectation-maximization algorithm for efficient posterior inference and function estimation.
  arXiv  Detail & Related papers  (2023-10-09T03:55:09Z)
• A Distributionally Robust Approach to Regret Optimal Control using the Wasserstein Distance [1.8876415010297893]
  We show that causal linear disturbance feedback controllers are designed to minimize the worst-case expected regret. We derive a reformulation of the minimax regret optimal control problem as a tractable semidefinite program. We compare the minimax regret optimal control design method with the distributionally robust optimal control approach.
  arXiv  Detail & Related papers  (2023-04-13T19:10:06Z)
• Stochastic optimal well control in subsurface reservoirs using reinforcement learning [0.0]
  We present a case study of model-free reinforcement learning framework to solve optimal control for a predefined parameter uncertainty distribution. In principle, RL algorithms are capable of learning optimal action policies to maximize a numerical reward signal. We present numerical results using two state-of-the-art RL algorithms, proximal policy optimization (PPO) and advantage actor-critic (A2C) on two subsurface flow test cases.
  arXiv  Detail & Related papers  (2022-07-07T17:34:23Z)
• Stochastic Control through Approximate Bayesian Input Inference [23.65155934960922]
  Optimal control under uncertainty is a prevailing challenge in control, due to the difficulty in producing tractable solutions for the optimization problem. By framing the control problem as one of input estimation, advanced approximate inference techniques can be used to handle the statistical approximations in a principled and practical manner.
  arXiv  Detail & Related papers  (2021-05-17T09:27:12Z)
• Probabilistic robust linear quadratic regulators with Gaussian processes [73.0364959221845]
  Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design. We present a novel controller synthesis for linearized GP dynamics that yields robust controllers with respect to a probabilistic stability margin.
  arXiv  Detail & Related papers  (2021-05-17T08:36:18Z)
• An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction [84.49035467829819]
  We show that it is possible to better manage this trade-off by optimizing a bound on the Information Bottleneck (IB) objective. Our fully unsupervised approach jointly learns an explainer that predicts sparse binary masks over sentences, and an end-task predictor that considers only the extracted rationale.
  arXiv  Detail & Related papers  (2020-05-01T23:26:41Z)
• Distributionally Robust Bayesian Optimization [121.71766171427433]
  We present a novel distributionally robust Bayesian optimization algorithm (DRBO) for zeroth-order, noisy optimization. Our algorithm provably obtains sub-linear robust regret in various settings. We demonstrate the robust performance of our method on both synthetic and real-world benchmarks.
  arXiv  Detail & Related papers  (2020-02-20T22:04:30Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.