Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration

• URL: http://arxiv.org/abs/2503.18025v1
• Date: Sun, 23 Mar 2025 10:52:36 GMT
• Title: Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration
• Authors: Alexandre Perez-Lebel, Gael Varoquaux, Sanmi Koyejo, Matthieu Doutreligne, Marine Le Morvan,
• Abstract summary: 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.
• Score: 52.70324949884702
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Probabilistic classifiers are central for making informed decisions under uncertainty. Based on the maximum expected utility principle, optimal decision rules can be derived using the posterior class probabilities and misclassification costs. Yet, in practice only learned approximations of the oracle posterior probabilities are available. In this work, we quantify the excess risk (a.k.a. regret) incurred using approximate posterior probabilities in batch binary decision-making. We provide analytical expressions for miscalibration-induced regret ($R^{\mathrm{CL}}$), as well as tight and informative upper and lower bounds on the regret of calibrated classifiers ($R^{\mathrm{GL}}$). These expressions allow us to identify regimes where recalibration alone addresses most of the regret, and regimes where the regret is dominated by the grouping loss, which calls for post-training beyond recalibration. Crucially, both $R^{\mathrm{CL}}$ and $R^{\mathrm{GL}}$ can be estimated in practice using a calibration curve and a recent grouping loss estimator. On NLP experiments, we show that these quantities identify when the expected gain of more advanced post-training is worth the operational cost. Finally, we highlight the potential of multicalibration approaches as efficient alternatives to costlier fine-tuning approaches.

Related papers

• 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)
• Distributionally Robust Optimization with Bias and Variance Reduction [9.341215359733601]
  We show that Prospect, a gradient-based algorithm, enjoys linear convergence for smooth regularized losses. We also show that Prospect can converge 2-3$times$ faster than baselines such as gradient-based methods.
  arXiv  Detail & Related papers  (2023-10-21T00:03:54Z)
• Minimum-Risk Recalibration of Classifiers [9.31067660373791]
  We introduce the concept of minimum-risk recalibration within the framework of mean-squared-error decomposition. We show that transferring a calibrated classifier requires significantly fewer target samples compared to recalibrating from scratch.
  arXiv  Detail & Related papers  (2023-05-18T11:27:02Z)
• Decision-Making under Miscalibration [14.762226638396209]
  ML-based predictions are used to inform consequential decisions about individuals. We formalize a natural (distribution-free) solution concept: given anticipated miscalibration of $alpha$, we propose using the threshold $j$ that minimizes the worst-case regret. We provide closed form expressions for $j$ when miscalibration is measured using both expected and maximum calibration error. We validate our theoretical findings on real data, demonstrating that there are natural cases in which making decisions using $j$ improves the clinical utility.
  arXiv  Detail & Related papers  (2022-03-18T10:44:11Z)
• Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration [118.26862029820447]
  We introduce a new notion -- emphdecision calibration -- that requires the predicted distribution and true distribution to be indistinguishable'' to a set of downstream decision-makers. Decision calibration improves decision-making on skin lesions and ImageNet classification with modern neural network.
  arXiv  Detail & Related papers  (2021-07-12T20:17:28Z)
• Reward Biased Maximum Likelihood Estimation for Reinforcement Learning [13.820705458648233]
  Reward-Biased Maximum Likelihood Estimate (RBMLE) for adaptive control of Markov chains was proposed. We show that it has a regret of $mathcalO( log T)$ over a time horizon of $T$ steps, similar to state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2020-11-16T06:09:56Z)
• Large-Scale Methods for Distributionally Robust Optimization [53.98643772533416]
  We prove that our algorithms require a number of evaluations gradient independent of training set size and number of parameters. Experiments on MNIST and ImageNet confirm the theoretical scaling of our algorithms, which are 9--36 times more efficient than full-batch methods.
  arXiv  Detail & Related papers  (2020-10-12T17:41:44Z)
• Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss [145.54544979467872]
  We consider online learning for episodically constrained Markov decision processes (CMDPs) We propose a new emphupper confidence primal-dual algorithm, which only requires the trajectories sampled from the transition model. Our analysis incorporates a new high-probability drift analysis of Lagrange multiplier processes into the celebrated regret analysis of upper confidence reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-02T05:02:23Z)

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.