Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents

• URL: http://arxiv.org/abs/2502.02561v1
• Date: Tue, 04 Feb 2025 18:37:10 GMT
• Title: Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents
• Authors: Shayan Kiyani, George Pappas, Aaron Roth, Hamed Hassani,
• Abstract summary: We develop decision-theoretic foundations that connect uncertainty using prediction sets with risk-averse decision-making. We experimentally demonstrate the significant advantages of Risk-Averse (RAC) in applications such as medical diagnosis and recommendation systems.
• Score: 24.938391962245877
• License:
• Abstract: A fundamental question in data-driven decision making is how to quantify the uncertainty of predictions in ways that can usefully inform downstream action. This interface between prediction uncertainty and decision-making is especially important in risk-sensitive domains, such as medicine. In this paper, we develop decision-theoretic foundations that connect uncertainty quantification using prediction sets with risk-averse decision-making. Specifically, we answer three fundamental questions: (1) What is the correct notion of uncertainty quantification for risk-averse decision makers? We prove that prediction sets are optimal for decision makers who wish to optimize their value at risk. (2) What is the optimal policy that a risk averse decision maker should use to map prediction sets to actions? We show that a simple max-min decision policy is optimal for risk-averse decision makers. Finally, (3) How can we derive prediction sets that are optimal for such decision makers? We provide an exact characterization in the population regime and a distribution free finite-sample construction. Answering these questions naturally leads to an algorithm, Risk-Averse Calibration (RAC), which follows a provably optimal design for deriving action policies from predictions. RAC is designed to be both practical-capable of leveraging the quality of predictions in a black-box manner to enhance downstream utility-and safe-adhering to a user-defined risk threshold and optimizing the corresponding risk quantile of the user's downstream utility. Finally, we experimentally demonstrate the significant advantages of RAC in applications such as medical diagnosis and recommendation systems. Specifically, we show that RAC achieves a substantially improved trade-off between safety and utility, offering higher utility compared to existing methods while maintaining the safety guarantee.

Related papers

• Optimal Policy Learning with Observational Data in Multi-Action Scenarios: Estimation, Risk Preference, and Potential Failures [0.0]
  This paper deals with optimal policy learning with observational data. It is organized in three parts, where I discuss respectively: estimation, risk preference, and potential failures.
  arXiv  Detail & Related papers  (2024-03-29T15:55:06Z)
• Information-Theoretic Safe Bayesian Optimization [59.758009422067005]
  We consider a sequential decision making task, where the goal is to optimize an unknown function without evaluating parameters that violate an unknown (safety) constraint. Most current methods rely on a discretization of the domain and cannot be directly extended to the continuous case. We propose an information-theoretic safe exploration criterion that directly exploits the GP posterior to identify the most informative safe parameters to evaluate.
  arXiv  Detail & Related papers  (2024-02-23T14:31:10Z)
• 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)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• Conformal Contextual Robust Optimization [21.2737854880866]
  Data-driven approaches to predict probabilistic decision-making problems seek to mitigate the risk of uncertainty region mis robustness in safety-critical settings. We propose a Conformal-Then-Predict (CPO) framework for. probability-then-optimize decision-making problems.
  arXiv  Detail & Related papers  (2023-10-16T01:58:27Z)
• Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions [80.34972679938483]
  We introduce Conformal Decision Theory, a framework for producing safe autonomous decisions despite imperfect machine learning predictions. Decisions produced by our algorithms are safe in the sense that they come with provable statistical guarantees of having low risk. Experiments demonstrate the utility of our approach in robot motion planning around humans, automated stock trading, and robot manufacturing.
  arXiv  Detail & Related papers  (2023-10-09T17:59:30Z)
• Algorithmic Assistance with Recommendation-Dependent Preferences [2.864550757598007]
  We consider the effect and design of algorithmic recommendations when they affect choices. We show that recommendation-dependent preferences create inefficiencies where the decision-maker is overly responsive to the recommendation.
  arXiv  Detail & Related papers  (2022-08-16T09:24:47Z)
• Off-Policy Evaluation with Policy-Dependent Optimization Response [90.28758112893054]
  We develop a new framework for off-policy evaluation with a textitpolicy-dependent linear optimization response. We construct unbiased estimators for the policy-dependent estimand by a perturbation method. We provide a general algorithm for optimizing causal interventions.
  arXiv  Detail & Related papers  (2022-02-25T20:25:37Z)
• Bayesian Persuasion for Algorithmic Recourse [28.586165301962485]
  In some situations, the underlying predictive model is deliberately kept secret to avoid gaming. This opacity forces the decision subjects to rely on incomplete information when making strategic feature modifications. We capture such settings as a game of Bayesian persuasion, in which the decision-maker sends a signal, e.g., an action recommendation, to a decision subject to incentivize them to take desirable actions.
  arXiv  Detail & Related papers  (2021-12-12T17:18:54Z)
• When Does Uncertainty Matter?: Understanding the Impact of Predictive Uncertainty in ML Assisted Decision Making [68.19284302320146]
  We carry out user studies to assess how people with differing levels of expertise respond to different types of predictive uncertainty. We found that showing posterior predictive distributions led to smaller disagreements with the ML model's predictions. This suggests that posterior predictive distributions can potentially serve as useful decision aids which should be used with caution and take into account the type of distribution and the expertise of the human.
  arXiv  Detail & Related papers  (2020-11-12T02:23:53Z)
• Fast, Optimal, and Targeted Predictions using Parametrized Decision Analysis [0.0]
  We develop a class of parametrized actions for Bayesian decision analysis that produce optimal, scalable, and simple targeted predictions. Predictions are constructed for physical activity data from the National Health and Nutrition Examination Survey.
  arXiv  Detail & Related papers  (2020-06-23T15:55:47Z)

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.