Rethinking Early Stopping: Refine, Then Calibrate

• URL: http://arxiv.org/abs/2501.19195v1
• Date: Fri, 31 Jan 2025 15:03:54 GMT
• Title: Rethinking Early Stopping: Refine, Then Calibrate
• Authors: Eugène Berta, David Holzmüller, Michael I. Jordan, Francis Bach,
• Abstract summary: We show that calibration error and refinement error are not minimized simultaneously during training. We introduce a new metric for early stopping and hyper parameter tuning that makes it possible to minimize refinement error during training. Our method integrates seamlessly with any architecture and consistently improves performance across diverse classification tasks.
• Score: 49.966899634962374
• License:
• Abstract: Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses like cross-entropy, which decompose into two components: calibration error assesses general under/overconfidence, while refinement error measures the ability to distinguish different classes. In this paper, we provide theoretical and empirical evidence that these two errors are not minimized simultaneously during training. Selecting the best training epoch based on validation loss thus leads to a compromise point that is suboptimal for both calibration error and, most importantly, refinement error. To address this, we introduce a new metric for early stopping and hyperparameter tuning that makes it possible to minimize refinement error during training. The calibration error is minimized after training, using standard techniques. Our method integrates seamlessly with any architecture and consistently improves performance across diverse classification tasks.

Related papers

• Calibration by Distribution Matching: Trainable Kernel Calibration Metrics [56.629245030893685]
  We introduce kernel-based calibration metrics that unify and generalize popular forms of calibration for both classification and regression. These metrics admit differentiable sample estimates, making it easy to incorporate a calibration objective into empirical risk minimization. We provide intuitive mechanisms to tailor calibration metrics to a decision task, and enforce accurate loss estimation and no regret decisions.
  arXiv  Detail & Related papers  (2023-10-31T06:19:40Z)
• Scaling of Class-wise Training Losses for Post-hoc Calibration [6.0632746602205865]
  We propose a new calibration method to synchronize the class-wise training losses. We design a new training loss to alleviate the variance of class-wise training losses by using multiple class-wise scaling factors. We validate the proposed framework by employing it in the various post-hoc calibration methods.
  arXiv  Detail & Related papers  (2023-06-19T14:59:37Z)
• Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection [58.789823426981044]
  We propose a novel auxiliary loss formulation that aims to align the class confidence of bounding boxes with the accurateness of predictions. Our results reveal that our train-time loss surpasses strong calibration baselines in reducing calibration error for both in and out-domain scenarios.
  arXiv  Detail & Related papers  (2023-03-25T08:56:21Z)
• Multi-Head Multi-Loss Model Calibration [13.841172927454204]
  We introduce a form of simplified ensembling that bypasses the costly training and inference of deep ensembles. Specifically, each head is trained to minimize a weighted Cross-Entropy loss, but the weights are different among the different branches. We show that the resulting averaged predictions can achieve excellent calibration without sacrificing accuracy in two challenging datasets.
  arXiv  Detail & Related papers  (2023-03-02T09:32:32Z)
• Beyond calibration: estimating the grouping loss of modern neural networks [68.8204255655161]
  Proper scoring rule theory shows that given the calibration loss, the missing piece to characterize individual errors is the grouping loss. We show that modern neural network architectures in vision and NLP exhibit grouping loss, notably in distribution shifts settings.
  arXiv  Detail & Related papers  (2022-10-28T07:04:20Z)
• Class-wise and reduced calibration methods [0.0]
  We show how a reduced calibration method transforms the original problem into a simpler one. Second, we propose class-wise calibration methods, based on building on a phenomenon called neural collapse. Applying the two methods together results in class-wise reduced calibration algorithms, which are powerful tools for reducing the prediction and per-class calibration errors.
  arXiv  Detail & Related papers  (2022-10-07T17:13:17Z)
• Uncertainty Quantification and Deep Ensembles [79.4957965474334]
  We show that deep-ensembles do not necessarily lead to improved calibration properties. We show that standard ensembling methods, when used in conjunction with modern techniques such as mixup regularization, can lead to less calibrated models. This text examines the interplay between three of the most simple and commonly used approaches to leverage deep learning when data is scarce.
  arXiv  Detail & Related papers  (2020-07-17T07:32:24Z)
• Understanding and Mitigating the Tradeoff Between Robustness and Accuracy [88.51943635427709]
  Adversarial training augments the training set with perturbations to improve the robust error. We show that the standard error could increase even when the augmented perturbations have noiseless observations from the optimal linear predictor.
  arXiv  Detail & Related papers  (2020-02-25T08:03:01Z)

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.