A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry

• URL: http://arxiv.org/abs/2401.00611v1
• Date: Sun, 31 Dec 2023 23:57:05 GMT
• Title: A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry
• Authors: Tim Z. Xiao, Weiyang Liu, Robert Bamler
• Abstract summary: We show that the role of permutations can be meaningfully quantified by a number of transpositions metric. We then show that the recently proposed rebasin method allows us to summarize HMC samples into a compact representation. We show that this compact representation allows us to compare trained BNNs directly in weight space across sampling methods and variational inference.
• Score: 22.229664343428055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bayesian neural networks (BNNs) are a principled approach to modeling predictive uncertainties in deep learning, which are important in safety-critical applications. Since exact Bayesian inference over the weights in a BNN is intractable, various approximate inference methods exist, among which sampling methods such as Hamiltonian Monte Carlo (HMC) are often considered the gold standard. While HMC provides high-quality samples, it lacks interpretable summary statistics because its sample mean and variance is meaningless in neural networks due to permutation symmetry. In this paper, we first show that the role of permutations can be meaningfully quantified by a number of transpositions metric. We then show that the recently proposed rebasin method allows us to summarize HMC samples into a compact representation that provides a meaningful explicit uncertainty estimate for each weight in a neural network, thus unifying sampling methods with variational inference. We show that this compact representation allows us to compare trained BNNs directly in weight space across sampling methods and variational inference, and to efficiently prune neural networks trained without explicit Bayesian frameworks by exploiting uncertainty estimates from HMC.

Related papers

• A Framework for Variational Inference of Lightweight Bayesian Neural Networks with Heteroscedastic Uncertainties [0.31457219084519006]
  We show that both the heteroscedastic aleatoric and epistemic variance can be embedded into the variances of learned BNN parameters. We introduce a relatively simple framework for sampling-free variational inference suitable for lightweight BNNs.
  arXiv  Detail & Related papers  (2024-02-22T13:24:43Z)
• Collapsed Inference for Bayesian Deep Learning [36.1725075097107]
  We introduce a novel collapsed inference scheme that performs Bayesian model averaging using collapsed samples. A collapsed sample represents uncountably many models drawn from the approximate posterior. Our proposed use of collapsed samples achieves a balance between scalability and accuracy.
  arXiv  Detail & Related papers  (2023-06-16T08:34:42Z)
• Piecewise Deterministic Markov Processes for Bayesian Neural Networks [20.865775626533434]
  Inference on modern Bayesian Neural Networks (BNNs) often relies on a variational inference treatment, imposing violated assumptions of independence and the form of the posterior. New Piecewise Deterministic Markov Process (PDMP) samplers permit subsampling, though introduce a model specific inhomogenous Poisson Process (IPPs) which is difficult to sample from. This work introduces a new generic and adaptive thinning scheme for sampling from IPPs, and demonstrates how this approach can accelerate the application of PDMPs for inference in BNNs.
  arXiv  Detail & Related papers  (2023-02-17T06:38:16Z)
• Bayesian deep learning framework for uncertainty quantification in high dimensions [6.282068591820945]
  We develop a novel deep learning method for uncertainty quantification in partial differential equations based on Bayesian neural network (BNN) and Hamiltonian Monte Carlo (HMC) A BNN efficiently learns the posterior distribution of the parameters in deep neural networks by performing Bayesian inference on the network parameters. The posterior distribution is efficiently sampled using HMC to quantify uncertainties in the system.
  arXiv  Detail & Related papers  (2022-10-21T05:20:06Z)
• Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing [58.401504709365284]
  We present a weight similarity measure that can quantify the weight similarity of non-volution neural networks. We first normalize the weights of neural networks by a chain normalization rule, which is used to introduce weight-training representation learning. We extend traditional hypothesis-testing method to validate the hypothesis on the weight similarity of neural networks.
  arXiv  Detail & Related papers  (2022-08-08T19:11:03Z)
• Variational Neural Networks [88.24021148516319]
  We propose a method for uncertainty estimation in neural networks called Variational Neural Network (VNN) VNN generates parameters for the output distribution of a layer by transforming its inputs with learnable sub-layers. In uncertainty quality estimation experiments, we show that VNNs achieve better uncertainty quality than Monte Carlo Dropout or Bayes By Backpropagation methods.
  arXiv  Detail & Related papers  (2022-07-04T15:41:02Z)
• NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks [151.03112356092575]
  We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
  arXiv  Detail & Related papers  (2022-02-07T12:30:45Z)
• Training on Test Data with Bayesian Adaptation for Covariate Shift [96.3250517412545]
  Deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. We derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters. We show that our method improves both accuracy and uncertainty estimation.
  arXiv  Detail & Related papers  (2021-09-27T01:09:08Z)
• What Are Bayesian Neural Network Posteriors Really Like? [63.950151520585024]
  We show that Hamiltonian Monte Carlo can achieve significant performance gains over standard and deep ensembles. We also show that deep distributions are similarly close to HMC as standard SGLD, and closer than standard variational inference.
  arXiv  Detail & Related papers  (2021-04-29T15:38:46Z)
• Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise [51.080620762639434]
  We propose a more efficient parameterization of the posterior approximation for sampling-free variational inference. Our approach yields competitive results for standard regression problems and scales well to large-scale image classification tasks.
  arXiv  Detail & Related papers  (2021-03-15T16:16:18Z)

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.