Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift

• URL: http://arxiv.org/abs/2306.12306v3
• Date: Tue, 24 Oct 2023 20:03:55 GMT
• Title: Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift
• Authors: Florian Seligmann, Philipp Becker, Michael Volpp, Gerhard Neumann
• Abstract summary: We evaluate modern BDL algorithms on real-world datasets from the WILDS collection containing challenging classification and regression tasks. We compare the algorithms on a wide range of large, convolutional and transformer-based neural network architectures. We provide the first systematic evaluation of BDL for fine-tuning large pre-trained models.
• Score: 19.945634052291542
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bayesian deep learning (BDL) is a promising approach to achieve well-calibrated predictions on distribution-shifted data. Nevertheless, there exists no large-scale survey that evaluates recent SOTA methods on diverse, realistic, and challenging benchmark tasks in a systematic manner. To provide a clear picture of the current state of BDL research, we evaluate modern BDL algorithms on real-world datasets from the WILDS collection containing challenging classification and regression tasks, with a focus on generalization capability and calibration under distribution shift. We compare the algorithms on a wide range of large, convolutional and transformer-based neural network architectures. In particular, we investigate a signed version of the expected calibration error that reveals whether the methods are over- or under-confident, providing further insight into the behavior of the methods. Further, we provide the first systematic evaluation of BDL for fine-tuning large pre-trained models, where training from scratch is prohibitively expensive. Finally, given the recent success of Deep Ensembles, we extend popular single-mode posterior approximations to multiple modes by the use of ensembles. While we find that ensembling single-mode approximations generally improves the generalization capability and calibration of the models by a significant margin, we also identify a failure mode of ensembles when finetuning large transformer-based language models. In this setting, variational inference based approaches such as last-layer Bayes By Backprop outperform other methods in terms of accuracy by a large margin, while modern approximate inference algorithms such as SWAG achieve the best calibration.

Related papers

• A Bayesian Approach to Data Point Selection [24.98069363998565]
  Data point selection (DPS) is becoming a critical topic in deep learning. Existing approaches to DPS are predominantly based on a bi-level optimisation (BLO) formulation. We propose a novel Bayesian approach to DPS.
  arXiv  Detail & Related papers  (2024-11-06T09:04:13Z)
• Amortized Bayesian Multilevel Models [9.831471158899644]
  Multilevel models (MLMs) are a central building block of the Bayesian workflow. MLMs pose significant computational challenges, often rendering their estimation and evaluation intractable within reasonable time constraints. Recent advances in simulation-based inference offer promising solutions for addressing complex probabilistic models using deep generative networks. We explore a family of neural network architectures that leverage the probabilistic factorization of multilevel models to facilitate efficient neural network training and subsequent near-instant posterior inference on unseen data sets.
  arXiv  Detail & Related papers  (2024-08-23T17:11:04Z)
• Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling [7.084307990641011]
  We introduce a novel approach that combines diffusion techniques and implicit priors for variational learning of Bayesian last layer weights. By delivering an explicit and computationally efficient variational lower bound, our method aims to augment the expressive abilities of BLL models.
  arXiv  Detail & Related papers  (2024-08-07T12:59:58Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Provably Efficient UCB-type Algorithms For Learning Predictive State Representations [55.00359893021461]
  The sequential decision-making problem is statistically learnable if it admits a low-rank structure modeled by predictive state representations (PSRs) This paper proposes the first known UCB-type approach for PSRs, featuring a novel bonus term that upper bounds the total variation distance between the estimated and true models. In contrast to existing approaches for PSRs, our UCB-type algorithms enjoy computational tractability, last-iterate guaranteed near-optimal policy, and guaranteed model accuracy.
  arXiv  Detail & Related papers  (2023-07-01T18:35:21Z)
• Bilevel Online Deep Learning in Non-stationary Environment [4.565872584112864]
  Bilevel Online Deep Learning (BODL) framework combines bilevel optimization strategy and online ensemble classifier. When the concept drift is detected, our BODL algorithm can adaptively update the model parameters via bilevel optimization and then circumvent the large drift and encourage positive transfer.
  arXiv  Detail & Related papers  (2022-01-25T11:05:51Z)
• A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer [55.20627066525205]
  We propose a variational Bayesian (VB) approach to learning distributions of latent variables in deep neural network (DNN) models. Our proposed VB approach can obtain good improvements on target devices, and consistently outperforms 13 state-of-the-art knowledge transfer algorithms.
  arXiv  Detail & Related papers  (2021-10-16T15:54:01Z)
• Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration [2.8935588665357077]
  We propose an efficient yet general modelling approach for obtaining well-calibrated, trustworthy probabilities for samples obtained after a domain shift. We introduce a new training strategy combining an entropy-encouraging loss term with an adversarial calibration loss term and demonstrate that this results in well-calibrated and technically trustworthy predictions.
  arXiv  Detail & Related papers  (2020-12-20T13:39:29Z)
• Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
  In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
  arXiv  Detail & Related papers  (2020-03-10T03:10:41Z)
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network [66.26231423824089]
  We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models.
  arXiv  Detail & Related papers  (2020-03-04T12:27:36Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

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.