On the Convergence of Locally Adaptive and Scalable Diffusion-Based Sampling Methods for Deep Bayesian Neural Network Posteriors
- URL: http://arxiv.org/abs/2403.08609v2
- Date: Thu, 14 Mar 2024 10:01:45 GMT
- Title: On the Convergence of Locally Adaptive and Scalable Diffusion-Based Sampling Methods for Deep Bayesian Neural Network Posteriors
- Authors: Tim Rensmeyer, Oliver Niggemann,
- Abstract summary: Bayesian neural networks are a promising approach for modeling uncertainties in deep neural networks.
generating samples from the posterior distribution of neural networks is a major challenge.
One advance in that direction would be the incorporation of adaptive step sizes into Monte Carlo Markov chain sampling algorithms.
In this paper, we demonstrate that these methods can have a substantial bias in the distribution they sample, even in the limit of vanishing step sizes and at full batch size.
- Score: 2.3265565167163906
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Achieving robust uncertainty quantification for deep neural networks represents an important requirement in many real-world applications of deep learning such as medical imaging where it is necessary to assess the reliability of a neural network's prediction. Bayesian neural networks are a promising approach for modeling uncertainties in deep neural networks. Unfortunately, generating samples from the posterior distribution of neural networks is a major challenge. One significant advance in that direction would be the incorporation of adaptive step sizes, similar to modern neural network optimizers, into Monte Carlo Markov chain sampling algorithms without significantly increasing computational demand. Over the past years, several papers have introduced sampling algorithms with claims that they achieve this property. However, do they indeed converge to the correct distribution? In this paper, we demonstrate that these methods can have a substantial bias in the distribution they sample, even in the limit of vanishing step sizes and at full batch size.
Related papers
- Residual Random Neural Networks [0.0]
Single-layer feedforward neural network with random weights is a recurring motif in the neural networks literature.
We show that one can obtain good classification results even if the number of hidden neurons has the same order of magnitude as the dimensionality of the data samples.
arXiv Detail & Related papers (2024-10-25T22:00:11Z) - Scalable Bayesian Inference in the Era of Deep Learning: From Gaussian Processes to Deep Neural Networks [0.5827521884806072]
Large neural networks trained on large datasets have become the dominant paradigm in machine learning.
This thesis develops scalable methods to equip neural networks with model uncertainty.
arXiv Detail & Related papers (2024-04-29T23:38:58Z) - An Analytic Solution to Covariance Propagation in Neural Networks [10.013553984400488]
This paper presents a sample-free moment propagation technique to accurately characterize the input-output distributions of neural networks.
A key enabler of our technique is an analytic solution for the covariance of random variables passed through nonlinear activation functions.
The wide applicability and merits of the proposed technique are shown in experiments analyzing the input-output distributions of trained neural networks and training Bayesian neural networks.
arXiv Detail & Related papers (2024-03-24T14:08:24Z) - Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs.
We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD.
We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
arXiv Detail & Related papers (2023-10-02T03:25:32Z) - Addressing caveats of neural persistence with deep graph persistence [54.424983583720675]
We find that the variance of network weights and spatial concentration of large weights are the main factors that impact neural persistence.
We propose an extension of the filtration underlying neural persistence to the whole neural network instead of single layers.
This yields our deep graph persistence measure, which implicitly incorporates persistent paths through the network and alleviates variance-related issues.
arXiv Detail & Related papers (2023-07-20T13:34:11Z) - 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) - Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity
on Pruned Neural Networks [79.74580058178594]
We analyze the performance of training a pruned neural network by analyzing the geometric structure of the objective function.
We show that the convex region near a desirable model with guaranteed generalization enlarges as the neural network model is pruned.
arXiv Detail & Related papers (2021-10-12T01:11:07Z) - Scalable Verification of Quantized Neural Networks (Technical Report) [14.04927063847749]
We show that bit-exact implementation of quantized neural networks with bit-vector specifications is PSPACE-hard.
We propose three techniques for making SMT-based verification of quantized neural networks more scalable.
arXiv Detail & Related papers (2020-12-15T10:05:37Z) - Scalable Bayesian neural networks by layer-wise input augmentation [20.279668821097918]
We introduce implicit Bayesian neural networks, a simple and scalable approach for uncertainty representation in deep learning.
We present appropriate input distributions and demonstrate state-of-the-art performance in terms of calibration, robustness and uncertainty characterisation over large-scale, multi-million parameter image classification tasks.
arXiv Detail & Related papers (2020-10-26T11:45:19Z) - ESPN: Extremely Sparse Pruned Networks [50.436905934791035]
We show that a simple iterative mask discovery method can achieve state-of-the-art compression of very deep networks.
Our algorithm represents a hybrid approach between single shot network pruning methods and Lottery-Ticket type approaches.
arXiv Detail & Related papers (2020-06-28T23:09:27Z) - MSE-Optimal Neural Network Initialization via Layer Fusion [68.72356718879428]
Deep neural networks achieve state-of-the-art performance for a range of classification and inference tasks.
The use of gradient combined nonvolutionity renders learning susceptible to novel problems.
We propose fusing neighboring layers of deeper networks that are trained with random variables.
arXiv Detail & Related papers (2020-01-28T18:25:15Z)
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.