Learning Pareto-Efficient Decisions with Confidence

• URL: http://arxiv.org/abs/2110.09864v1
• Date: Tue, 19 Oct 2021 11:32:17 GMT
• Title: Learning Pareto-Efficient Decisions with Confidence
• Authors: Sofia Ek, Dave Zachariah, Petre Stoica
• Abstract summary: The paper considers the problem of multi-objective decision support when outcomes are uncertain. This enables quantifying trade-offs between decisions in terms of tail outcomes that are relevant in safety-critical applications.
• Score: 21.915057426589748
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The paper considers the problem of multi-objective decision support when outcomes are uncertain. We extend the concept of Pareto-efficient decisions to take into account the uncertainty of decision outcomes across varying contexts. This enables quantifying trade-offs between decisions in terms of tail outcomes that are relevant in safety-critical applications. We propose a method for learning efficient decisions with statistical confidence, building on results from the conformal prediction literature. The method adapts to weak or nonexistent context covariate overlap and its statistical guarantees are evaluated using both synthetic and real data.

Related papers

• Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework [54.40508478482667]
  We present a comprehensive framework to disentangle, quantify, and mitigate uncertainty in perception and plan generation. We propose methods tailored to the unique properties of perception and decision-making. We show that our uncertainty disentanglement framework reduces variability by up to 40% and enhances task success rates by 5% compared to baselines.
  arXiv  Detail & Related papers  (2024-11-03T17:32:00Z)
• Predictive Performance Comparison of Decision Policies Under Confounding [32.21041697921289]
  We propose a method to compare the predictive performance of decision policies under a variety of modern identification approaches. Key to our method is the insight that there are regions of uncertainty that we can safely ignore in the policy comparison.
  arXiv  Detail & Related papers  (2024-04-01T01:27:07Z)
• Measuring Classification Decision Certainty and Doubt [61.13511467941388]
  We propose intuitive scores, which we call certainty and doubt, to assess and compare the quality and uncertainty of predictions in (multi-)classification decision machine learning problems.
  arXiv  Detail & Related papers  (2023-03-25T21:31:41Z)
• RISE: Robust Individualized Decision Learning with Sensitive Variables [1.5293427903448025]
  A naive baseline is to ignore sensitive variables in learning decision rules, leading to significant uncertainty and bias. We propose a decision learning framework to incorporate sensitive variables during offline training but not include them in the input of the learned decision rule during model deployment.
  arXiv  Detail & Related papers  (2022-11-12T04:31:38Z)
• On the Complexity of Adversarial Decision Making [101.14158787665252]
  We show that the Decision-Estimation Coefficient is necessary and sufficient to obtain low regret for adversarial decision making. We provide new structural results that connect the Decision-Estimation Coefficient to variants of other well-known complexity measures.
  arXiv  Detail & Related papers  (2022-06-27T06:20:37Z)
• Explainability's Gain is Optimality's Loss? -- How Explanations Bias Decision-making [0.0]
  Explanations help to facilitate communication between the algorithm and the human decision-maker. Feature-based explanations' semantics of causal models induce leakage from the decision-maker's prior beliefs. Such differences can lead to sub-optimal and biased decision outcomes.
  arXiv  Detail & Related papers  (2022-06-17T11:43:42Z)
• The Statistical Complexity of Interactive Decision Making [126.04974881555094]
  We provide a complexity measure, the Decision-Estimation Coefficient, that is proven to be both necessary and sufficient for sample-efficient interactive learning. A unified algorithm design principle, Estimation-to-Decisions (E2D), transforms any algorithm for supervised estimation into an online algorithm for decision making.
  arXiv  Detail & Related papers  (2021-12-27T02:53:44Z)
• Reliable Off-policy Evaluation for Reinforcement Learning [53.486680020852724]
  In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy. We propose a novel framework that provides robust and optimistic cumulative reward estimates using one or multiple logged data.
  arXiv  Detail & Related papers  (2020-11-08T23:16:19Z)
• Inverse Active Sensing: Modeling and Understanding Timely Decision-Making [111.07204912245841]
  We develop a framework for the general setting of evidence-based decision-making under endogenous, context-dependent time pressure. We demonstrate how it enables modeling intuitive notions of surprise, suspense, and optimality in decision strategies.
  arXiv  Detail & Related papers  (2020-06-25T02:30:45Z)
• Learning Robust Decision Policies from Observational Data [21.05564340986074]
  It is of interest to learn robust policies that reduce the risk of outcomes with high costs. We develop a method for learning policies that reduce tails of the cost distribution at a specified level.
  arXiv  Detail & Related papers  (2020-06-03T16:02:57Z)

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.