IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023 · 20 citations · 20 references
ComputingComputer ScienceData ScienceMachine LearningPredictive AnalyticsUncertainty QuantificationMeta-learningPredictive ModelingConformal CalibrationConformal PredictionCross-validationFew-shot LearningMeta-learning TheoryMeta-training
Conventional frequentist learning is known to yield poorly calibrated models that fail to reliably quantify the uncertainty of their decisions. Bayesian learning can improve calibration, but formal guarantees apply only under restrictive assumptions about correct model specification. Conformal prediction (CP) offers a general framework for the design of set predictors with calibration guarantees that hold regardless of the underlying data generation mechanism. However, when training data are limited, CP tends to produce large, and hence uninformative, predicted sets. This paper introduces a novel meta-learning solution that aims at reducing the set prediction size. Unlike prior work, the proposed meta-learning scheme, referred to as meta-XB, i) builds on cross-validation-based CP, rather than the less efficient validation-based CP; and ii) preserves formal per-task calibration guarantees, rather than less stringent task-marginal guarantees. Finally, meta-XB is extended to adaptive non-conformal scores, which are shown empirically to further enhance marginal per-input calibration.
20
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2015 · 18.8K citations
Roger Koenker, Gilbert W. Bassett · Econometrica · 1978 · 12.9K citations
Information Theory, Inference, and Learning Algorithms
Kybernetes · 2004 · 5.1K citations