Improving robustness and calibration in ensembles with diversity regularization

• URL: http://arxiv.org/abs/2201.10908v1
• Date: Wed, 26 Jan 2022 12:51:11 GMT
• Title: Improving robustness and calibration in ensembles with diversity regularization
• Authors: Hendrik Alexander Mehrtens, Camila Gonz\'alez, Anirban Mukhopadhyay
• Abstract summary: We introduce a new diversity regularizer for classification tasks that uses out-of-distribution samples. We show that regularizing diversity can have a significant impact on calibration and robustness, as well as out-of-distribution detection.
• Score: 1.069533806668766
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Calibration and uncertainty estimation are crucial topics in high-risk environments. We introduce a new diversity regularizer for classification tasks that uses out-of-distribution samples and increases the overall accuracy, calibration and out-of-distribution detection capabilities of ensembles. Following the recent interest in the diversity of ensembles, we systematically evaluate the viability of explicitly regularizing ensemble diversity to improve calibration on in-distribution data as well as under dataset shift. We demonstrate that diversity regularization is highly beneficial in architectures, where weights are partially shared between the individual members and even allows to use fewer ensemble members to reach the same level of robustness. Experiments on CIFAR-10, CIFAR-100, and SVHN show that regularizing diversity can have a significant impact on calibration and robustness, as well as out-of-distribution detection.

Related papers

• Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance [60.68771286221115]
  We show the interplay between sharpness and diversity within deep ensembles. We introduce SharpBalance, a training approach that balances sharpness and diversity within ensembles. Empirically, we show that SharpBalance not only effectively improves the sharpness-diversity trade-off, but also significantly improves ensemble performance.
  arXiv  Detail & Related papers  (2024-07-17T20:31:26Z)
• Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift [44.708914058803224]
  We establish a new model-agnostic optimization framework for out-of-distribution generalization via multicalibration. We propose MC-Pseudolabel, a post-processing algorithm to achieve both extended multicalibration and out-of-distribution generalization.
  arXiv  Detail & Related papers  (2024-06-02T08:11:35Z)
• Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration [0.6906005491572401]
  We show that Information Bottleneck-based IRM achieves consistent calibration across different environments. Our empirical evidence indicates that models exhibiting consistent calibration across environments are also well-calibrated.
  arXiv  Detail & Related papers  (2024-01-31T02:08:43Z)
• DynED: Dynamic Ensemble Diversification in Data Stream Classification [2.990411348977783]
  We present a novel ensemble construction and maintenance approach based on MMR (Maximal Marginal Relevance) The experimental results on both four real and 11 synthetic datasets demonstrate that the proposed approach provides a higher average mean accuracy compared to the five state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-08-21T15:56:05Z)
• A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning [63.20009081099896]
  We provide a unifying framework for the design and analysis of multicalibrated predictors. We exploit connections to game dynamics to achieve state-of-the-art guarantees for a diverse set of multicalibration learning problems.
  arXiv  Detail & Related papers  (2023-02-21T18:24:17Z)
• RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness [94.69774317059122]
  We show that the effectiveness of the well celebrated Mixup can be further improved if instead of using it as the sole learning objective, it is utilized as an additional regularizer to the standard cross-entropy loss. This simple change not only provides much improved accuracy but also significantly improves the quality of the predictive uncertainty estimation of Mixup.
  arXiv  Detail & Related papers  (2022-06-29T09:44:33Z)
• Robust Calibration with Multi-domain Temperature Scaling [86.07299013396059]
  We develop a systematic calibration model to handle distribution shifts by leveraging data from multiple domains. Our proposed method -- multi-domain temperature scaling -- uses the robustness in the domains to improve calibration under distribution shift.
  arXiv  Detail & Related papers  (2022-06-06T17:32:12Z)
• Low-Degree Multicalibration [16.99099840073075]
  Low-Degree Multicalibration defines a hierarchy of increasingly-powerful multi-group fairness notions. We show that low-degree multicalibration can be significantly more efficient than full multicalibration. Our work presents compelling evidence that low-degree multicalibration represents a sweet spot, pairing computational and sample efficiency with strong fairness and accuracy guarantees.
  arXiv  Detail & Related papers  (2022-03-02T17:24:55Z)
• A Unified Framework for Multi-distribution Density Ratio Estimation [101.67420298343512]
  Binary density ratio estimation (DRE) provides the foundation for many state-of-the-art machine learning algorithms. We develop a general framework from the perspective of Bregman minimization divergence. We show that our framework leads to methods that strictly generalize their counterparts in binary DRE.
  arXiv  Detail & Related papers  (2021-12-07T01:23:20Z)
• Trusted Multi-View Classification [76.73585034192894]
  We propose a novel multi-view classification method, termed trusted multi-view classification. It provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed algorithm jointly utilizes multiple views to promote both classification reliability and robustness.
  arXiv  Detail & Related papers  (2021-02-03T13:30:26Z)

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.