A Closer Look at the Calibration of Differentially Private Learners

• URL: http://arxiv.org/abs/2210.08248v1
• Date: Sat, 15 Oct 2022 10:16:18 GMT
• Title: A Closer Look at the Calibration of Differentially Private Learners
• Authors: Hanlin Zhang, Xuechen Li, Prithviraj Sen, Salim Roukos, Tatsunori Hashimoto
• Abstract summary: We study the calibration of classifiers trained with differentially private descent gradient (DP-SGD) Our analysis identifies per-example gradient clipping in DP-SGD as a major cause of miscalibration. We show that differentially private variants of post-processing calibration methods such as temperature scaling and Platt scaling are surprisingly effective.
• Score: 33.715727551832785
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We systematically study the calibration of classifiers trained with differentially private stochastic gradient descent (DP-SGD) and observe miscalibration across a wide range of vision and language tasks. Our analysis identifies per-example gradient clipping in DP-SGD as a major cause of miscalibration, and we show that existing approaches for improving calibration with differential privacy only provide marginal improvements in calibration error while occasionally causing large degradations in accuracy. As a solution, we show that differentially private variants of post-processing calibration methods such as temperature scaling and Platt scaling are surprisingly effective and have negligible utility cost to the overall model. Across 7 tasks, temperature scaling and Platt scaling with DP-SGD result in an average 3.1-fold reduction in the in-domain expected calibration error and only incur at most a minor percent drop in accuracy.

Related papers

• Feature Clipping for Uncertainty Calibration [24.465567005078135]
  Modern deep neural networks (DNNs) often suffer from overconfidence, leading to miscalibration. We propose a novel post-hoc calibration method called feature clipping (FC) to address this issue. FC involves clipping feature values to a specified threshold, effectively increasing entropy in high calibration error samples.
  arXiv  Detail & Related papers  (2024-10-16T06:44:35Z)
• FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler [29.93307421620845]
  Federated learning (FedCal) uses client-specific scalers for local and global calibration. Experiments demonstrate FedCal significantly outperforms the best-performing baseline, reducing global calibration error by 47.66% on average.
  arXiv  Detail & Related papers  (2024-05-24T11:33:58Z)
• 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)
• PseudoCal: A Source-Free Approach to Unsupervised Uncertainty Calibration in Domain Adaptation [87.69789891809562]
  Unsupervised domain adaptation (UDA) has witnessed remarkable advancements in improving the accuracy of models for unlabeled target domains. The calibration of predictive uncertainty in the target domain, a crucial aspect of the safe deployment of UDA models, has received limited attention. We propose PseudoCal, a source-free calibration method that exclusively relies on unlabeled target data.
  arXiv  Detail & Related papers  (2023-07-14T17:21:41Z)
• On Calibrating Semantic Segmentation Models: Analyses and An Algorithm [51.85289816613351]
  We study the problem of semantic segmentation calibration. Model capacity, crop size, multi-scale testing, and prediction correctness have impact on calibration. We propose a simple, unifying, and effective approach, namely selective scaling.
  arXiv  Detail & Related papers  (2022-12-22T22:05:16Z)
• Sample-dependent Adaptive Temperature Scaling for Improved Calibration [95.7477042886242]
  Post-hoc approach to compensate for neural networks being wrong is to perform temperature scaling. We propose to predict a different temperature value for each input, allowing us to adjust the mismatch between confidence and accuracy. We test our method on the ResNet50 and WideResNet28-10 architectures using the CIFAR10/100 and Tiny-ImageNet datasets.
  arXiv  Detail & Related papers  (2022-07-13T14:13:49Z)
• Soft Calibration Objectives for Neural Networks [40.03050811956859]
  We propose differentiable losses to improve calibration based on a soft (continuous) version of the binning operation underlying popular calibration-error estimators. When incorporated into training, these soft calibration losses achieve state-of-the-art single-model ECE across multiple datasets with less than 1% decrease in accuracy.
  arXiv  Detail & Related papers  (2021-07-30T23:30:20Z)
• Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration [57.568461777747515]
  We introduce a novel calibration method, Parametrized Temperature Scaling (PTS) We demonstrate that the performance of accuracy-preserving state-of-the-art post-hoc calibrators is limited by their intrinsic expressive power. We show with extensive experiments that our novel accuracy-preserving approach consistently outperforms existing algorithms across a large number of model architectures, datasets and metrics.
  arXiv  Detail & Related papers  (2021-02-24T10:18:30Z)
• Localized Calibration: Metrics and Recalibration [133.07044916594361]
  We propose a fine-grained calibration metric that spans the gap between fully global and fully individualized calibration. We then introduce a localized recalibration method, LoRe, that improves the LCE better than existing recalibration methods.
  arXiv  Detail & Related papers  (2021-02-22T07:22:12Z)

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.