Nonlocal optimization of binary neural networks

• URL: http://arxiv.org/abs/2204.01935v1
• Date: Tue, 5 Apr 2022 02:14:53 GMT
• Title: Nonlocal optimization of binary neural networks
• Authors: Amir Khoshaman, Giuseppe Castiglione, Christopher Srinivasa
• Abstract summary: We explore training Binary Neural Networks (BNNs) as a discrete variable inference problem over a factor graph. We propose algorithms to overcome the intractability of their current formulation. Compared to traditional gradient methods for BNNs, our results indicate that both BP and SP find better configurations of the parameters in the BNN.
• Score: 0.8379286663107844
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We explore training Binary Neural Networks (BNNs) as a discrete variable inference problem over a factor graph. We study the behaviour of this conversion in an under-parameterized BNN setting and propose stochastic versions of Belief Propagation (BP) and Survey Propagation (SP) message passing algorithms to overcome the intractability of their current formulation. Compared to traditional gradient methods for BNNs, our results indicate that both stochastic BP and SP find better configurations of the parameters in the BNN.

Related papers

• ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters [0.0]
  In this paper, we introduce a third advantage of very low-precision neural networks: improved fault-tolerance. We investigate the impact of memory faults on state-of-the-art binary neural networks (BNNs) through comprehensive analysis. We propose a technique to improve BNN dependability by restricting the range of float parameters through a novel deliberately uniform quantization.
  arXiv  Detail & Related papers  (2024-07-06T05:31:11Z)
• 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)
• BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming [8.162867143465382]
  We introduce BNN-DP, an efficient framework for analysis of adversarial robustness of Bayesian Neural Networks. We show that BNN-DP outperforms state-of-the-art methods by up to four orders of magnitude in both tightness of the bounds and computational efficiency.
  arXiv  Detail & Related papers  (2023-06-19T07:19:15Z)
• Tackling covariate shift with node-based Bayesian neural networks [26.64657196802115]
  Node-based BNNs induce uncertainty by multiplying each hidden node with latent random variables, while learning a point-estimate of the weights. In this paper, we interpret these latent noise variables as implicit representations of simple and domain-agnostic data perturbations during training.
  arXiv  Detail & Related papers  (2022-06-06T08:56:19Z)
• Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer [77.78479877473899]
  We design a spatial-temporal-fusion BNN for efficiently scaling BNNs to large models. Compared to vanilla BNNs, our approach can greatly reduce the training time and the number of parameters, which contributes to scale BNNs efficiently.
  arXiv  Detail & Related papers  (2021-12-12T17:13:14Z)
• 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)
• Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification [10.727102755903616]
  We aim for efficient deep BNNs amenable to complex computer vision architectures. We achieve this by leveraging variational autoencoders (VAEs) to learn the interaction and the latent distribution of the parameters at each network layer. Our approach, Latent-Posterior BNN (LP-BNN), is compatible with the recent BatchEnsemble method, leading to highly efficient (in terms of computation and memory during both training and testing) ensembles.
  arXiv  Detail & Related papers  (2020-12-04T19:50:09Z)
• Improving predictions of Bayesian neural nets via local linearization [79.21517734364093]
  We argue that the Gauss-Newton approximation should be understood as a local linearization of the underlying Bayesian neural network (BNN) Because we use this linearized model for posterior inference, we should also predict using this modified model instead of the original one. We refer to this modified predictive as "GLM predictive" and show that it effectively resolves common underfitting problems of the Laplace approximation.
  arXiv  Detail & Related papers  (2020-08-19T12:35:55Z)
• Belief Propagation Neural Networks [103.97004780313105]
  We introduce belief propagation neural networks (BPNNs) BPNNs operate on factor graphs and generalize Belief propagation (BP) We show that BPNNs converges 1.7x faster on Ising models while providing tighter bounds. On challenging model counting problems, BPNNs compute estimates 100's of times faster than state-of-the-art handcrafted methods.
  arXiv  Detail & Related papers  (2020-07-01T07:39:51Z)
• Bayesian Graph Neural Networks with Adaptive Connection Sampling [62.51689735630133]
  We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) The proposed framework not only alleviates over-smoothing and over-fitting tendencies of deep GNNs, but also enables learning with uncertainty in graph analytic tasks with GNNs.
  arXiv  Detail & Related papers  (2020-06-07T07:06:35Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)

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.