Action-BED: Task-Driven Bayesian Experimental Design with Singly Intractable Objectives

• URL: http://arxiv.org/abs/2606.23662v1
• Date: Mon, 22 Jun 2026 17:48:07 GMT
• Title: Action-BED: Task-Driven Bayesian Experimental Design with Singly Intractable Objectives
• Abstract summary: We show that an expected future loss (EFL) on downstream actions can provide a simple and naturally task-driven framework for design policies.<n>We then show that all such EFLs can be rearranged into singly intractable objectives that can be jointly optimised with respect to both the design policy and a downstream action policy.
• Score: 12.963546988204875
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bayesian experimental design (BED) has traditionally been based on maximising expected uncertainty reductions from prior to posterior. A major shortfall of this approach is that it leads to doubly intractable objectives that are difficult to optimise, while customising them to particular downstream tasks of interest can also be difficult. Following first principles decision theory, we demonstrate that BED can alternatively be formulated in terms of an expected future loss (EFL) on downstream actions, providing a simple and naturally task-driven framework. Critically, we then show that all such EFLs can be rearranged into singly intractable objectives that can be jointly optimised with respect to both the design policy and a downstream action policy using stochastic gradients, an approach we refer to as ACTION-BED. This formulation further sidesteps the need for any explicit posterior or marginal likelihood estimation and is naturally implicit, requiring only the ability to sample from the joint model over model parameters and data, and evaluate the downstream loss function. It thus allows design policies to be learned more effectively, efficiently, and simply than existing methods, while providing easy customisation to different downstream tasks and losses.

Related papers

• UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning [4.276809570692494]
  We introduce a model-based approach that actively directs exploration by jointly reasoning over uncertainties in the reward, dynamics, and value functions.<n>Our method, Uncertainty-Balanced Preference Planning (UBP2), uses ensembles of reward, dynamics, and value function models to evaluate candidate trajectories.<n>Under standard assumptions, we establish sublinear regret guarantees for both finite-horizon and infinite-horizon settings.
  arXiv  Detail & Related papers  (2026-06-17T17:54:32Z)
• SDM: A Powerful Tool for Evaluating Model Robustness [7.8217298436598846]
  We propose a novel and powerful gradient-based attack method named Sequential Difference Maximization (SDM)<n>SDM achieves stronger attack performance and exhibits superior cost-effectiveness.
  arXiv  Detail & Related papers  (2026-05-19T16:10:24Z)
• Possibilistic Predictive Uncertainty for Deep Learning [75.00607359322863]
  We introduce Dirichlet-approximated possibilistic posterior predictions (DAPPr)<n>DAPPr is a principled framework leveraging possibility theory.<n>This projection-and-approximation strategy yields a simple training objective with closed-form solutions.
  arXiv  Detail & Related papers  (2026-05-01T12:14:01Z)
• Goal-Oriented Influence-Maximizing Data Acquisition for Learning and Optimization [28.53710231018475]
  We propose an active acquisition algorithm that avoids explicit posterior inference while remaining uncertainty-aware through inverse curvature.<n>GOIMDA selects inputs by maximizing their expected influence on a user-specified goal functional.<n>We show theoretically that, for generalized linear models, GOIMDA approximates predictive-entropy minimization up to a correction term accounting for goal alignment and prediction bias.
  arXiv  Detail & Related papers  (2026-02-23T07:57:11Z)
• Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning [59.11663802446183]
  Flow and diffusion generative models can be adapted to optimize task-specific objectives while preserving prior information.<n>We introduce Flow Density Control (FDC), a simple algorithm that reduces this complex problem to a specific sequence of simpler fine-tuning tasks.<n>We derive convergence guarantees for the proposed scheme under realistic assumptions by leveraging recent understanding of mirror flows.
  arXiv  Detail & Related papers  (2025-11-27T17:19:01Z)
• Explicit Preference Optimization: No Need for an Implicit Reward Model [18.225409932618657]
  Direct preference optimization (DPO) and its offshoots circumvent the need for a separate reward training step.<n>We show that DPO-based objectives are nonetheless subject to sub-optimal regularization and counter-intuitive artifacts.
  arXiv  Detail & Related papers  (2025-06-09T07:11:01Z)
• Aligning Latent Spaces with Flow Priors [72.24305287508474]
  This paper presents a novel framework for aligning learnable latent spaces to arbitrary target distributions by leveraging flow-based generative models as priors.<n> Notably, the proposed method eliminates computationally expensive likelihood evaluations and avoids ODE solving during optimization.
  arXiv  Detail & Related papers  (2025-06-05T16:59:53Z)
• Online Decision-Focused Learning [74.3205104323777]
  Decision-focused learning (DFL) is an increasingly popular paradigm for training models whose predictive outputs are used in decision-making tasks.<n>In this paper, we regularize the objective function to make it different and investigate how to overcome nonoptimality function.<n>We also showcase the effectiveness of our algorithms on a knapsack experiment, where they outperform two standard benchmarks.
  arXiv  Detail & Related papers  (2025-05-19T10:40:30Z)
• Directed Exploration in Reinforcement Learning from Linear Temporal Logic [59.707408697394534]
  Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning.<n>We show that the synthesized reward signal remains fundamentally sparse, making exploration challenging.<n>We show how better exploration can be achieved by further leveraging the specification and casting its corresponding Limit Deterministic B"uchi Automaton (LDBA) as a Markov reward process.
  arXiv  Detail & Related papers  (2024-08-18T14:25:44Z)
• Score Function Gradient Estimation to Widen the Applicability of Decision-Focused Learning [17.962860438133312]
  Decision-focused learning (DFL) paradigm overcomes limitation by training to directly minimize a task loss, e.g. regret. We propose an alternative method that makes no such assumptions, it combines smoothing with score function estimation which works on any task loss. Experiments show that it typically requires more epochs, but that it is on par with specialized methods and performs especially well for the difficult case of problems with uncertainty in the constraints, in terms of solution quality, scalability, or both.
  arXiv  Detail & Related papers  (2023-07-11T12:32:13Z)
• Learning (Local) Surrogate Loss Functions for Predict-Then-Optimize Problems [58.954414264760956]
  Decision-Focused Learning (DFL) is a paradigm for tailoring a predictive model to a downstream optimisation task. We present an approach to learn faithful task-specific surrogates which (a) only requires access to a black-box oracle that can solve the optimisation problem and is thus generalizable, and (b) can be convex by gradients and so can be easily optimized over.
  arXiv  Detail & Related papers  (2022-03-30T05:46:54Z)
• Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse [34.39887495671287]
  We propose an objective function which simultaneously minimizes the gap between the achieved (resulting) and desired recourse invalidation rates. We develop novel theoretical results to characterize the recourse invalidation rates corresponding to any given instance. Experimental evaluation with multiple real world datasets demonstrates the efficacy of the proposed framework.
  arXiv  Detail & Related papers  (2022-03-13T21:39:24Z)
• 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)

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.