Generalization Certificates for Adversarially Robust Bayesian Linear Regression

• URL: http://arxiv.org/abs/2502.14298v1
• Date: Thu, 20 Feb 2025 06:25:30 GMT
• Title: Generalization Certificates for Adversarially Robust Bayesian Linear Regression
• Authors: Mahalakshmi Sabanayagam, Russell Tsuchida, Cheng Soon Ong, Debarghya Ghoshdastidar,
• Abstract summary: Adversarial robustness of machine learning models is critical to ensuring reliable performance under data perturbations. Recent progress has been on point estimators, and this paper considers distributional predictors. Experiments on real and synthetic datasets demonstrate the superior robustness of the derived adversarially robust posterior over Bayes posterior.
• Score: 16.3368950151084
• License:
• Abstract: Adversarial robustness of machine learning models is critical to ensuring reliable performance under data perturbations. Recent progress has been on point estimators, and this paper considers distributional predictors. First, using the link between exponential families and Bregman divergences, we formulate an adversarial Bregman divergence loss as an adversarial negative log-likelihood. Using the geometric properties of Bregman divergences, we compute the adversarial perturbation for such models in closed-form. Second, under such losses, we introduce \emph{adversarially robust posteriors}, by exploiting the optimization-centric view of generalized Bayesian inference. Third, we derive the \emph{first} rigorous generalization certificates in the context of an adversarial extension of Bayesian linear regression by leveraging the PAC-Bayesian framework. Finally, experiments on real and synthetic datasets demonstrate the superior robustness of the derived adversarially robust posterior over Bayes posterior, and also validate our theoretical guarantees.

Related papers

• Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference [9.940560505044122]
  We propose a method to improve the efficiency and accuracy of amortized Bayesian inference. We estimate the marginal likelihood based on approximate representations of the joint model.
  arXiv  Detail & Related papers  (2023-10-06T17:41:41Z)
• Causality-oriented robustness: exploiting general additive interventions [3.871660145364189]
  In this paper, we focus on causality-oriented robustness and propose Distributional Robustness via Invariant Gradients (DRIG) In a linear setting, we prove that DRIG yields predictions that are robust among a data-dependent class of distribution shifts. We extend our approach to the semi-supervised domain adaptation setting to further improve prediction performance.
  arXiv  Detail & Related papers  (2023-07-18T16:22:50Z)
• Adversarial robustness of amortized Bayesian inference [3.308743964406687]
  Amortized Bayesian inference is to initially invest computational cost in training an inference network on simulated data. We show that almost unrecognizable, targeted perturbations of the observations can lead to drastic changes in the predicted posterior and highly unrealistic posterior predictive samples. We propose a computationally efficient regularization scheme based on penalizing the Fisher information of the conditional density estimator.
  arXiv  Detail & Related papers  (2023-05-24T10:18:45Z)
• Explicit Tradeoffs between Adversarial and Natural Distributional Robustness [48.44639585732391]
  In practice, models need to enjoy both types of robustness to ensure reliability. In this work, we show that in fact, explicit tradeoffs exist between adversarial and natural distributional robustness.
  arXiv  Detail & Related papers  (2022-09-15T19:58:01Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning [123.3472310767721]
  Prediction credibility measures are fundamental in statistics and machine learning. These measures should account for the wide variety of models used in practice. The framework developed in this work expresses the credibility as a risk-fit trade-off.
  arXiv  Detail & Related papers  (2020-11-24T19:52:38Z)
• Adversarial Robustness of Supervised Sparse Coding [34.94566482399662]
  We consider a model that involves learning a representation while at the same time giving a precise generalization bound and a robustness certificate. We focus on the hypothesis class obtained by combining a sparsity-promoting encoder coupled with a linear encoder. We provide a robustness certificate for end-to-end classification.
  arXiv  Detail & Related papers  (2020-10-22T22:05:21Z)
• CASTLE: Regularization via Auxiliary Causal Graph Discovery [89.74800176981842]
  We introduce Causal Structure Learning (CASTLE) regularization and propose to regularize a neural network by jointly learning the causal relationships between variables. CASTLE efficiently reconstructs only the features in the causal DAG that have a causal neighbor, whereas reconstruction-based regularizers suboptimally reconstruct all input features.
  arXiv  Detail & Related papers  (2020-09-28T09:49:38Z)
• $\beta$-Cores: Robust Large-Scale Bayesian Data Summarization in the Presence of Outliers [14.918826474979587]
  The quality of classic Bayesian inference depends critically on whether observations conform with the assumed data generating model. We propose a variational inference method that, in a principled way, can simultaneously scale to large datasets. We illustrate the applicability of our approach in diverse simulated and real datasets, and various statistical models.
  arXiv  Detail & Related papers  (2020-08-31T13:47:12Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization [56.69671152009899]
  We show that deep ensembles provide an effective mechanism for approximate Bayesian marginalization. We also propose a related approach that further improves the predictive distribution by marginalizing within basins of attraction.
  arXiv  Detail & Related papers  (2020-02-20T15:13:27Z)

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.