Information Bottleneck: Exact Analysis of (Quantized) Neural Networks

• URL: http://arxiv.org/abs/2106.12912v1
• Date: Thu, 24 Jun 2021 11:13:08 GMT
• Title: Information Bottleneck: Exact Analysis of (Quantized) Neural Networks
• Abstract summary: The information bottleneck (IB) principle has been suggested as a way to analyze deep neural networks. Separate fitting and compression phases during training have been reported. Our study shows that the initial IB results were not artifacts of binning when computing the MI.
• Score: 16.199954215341833
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The information bottleneck (IB) principle has been suggested as a way to analyze deep neural networks. The learning dynamics are studied by inspecting the mutual information (MI) between the hidden layers and the input and output. Notably, separate fitting and compression phases during training have been reported. This led to some controversy including claims that the observations are not reproducible and strongly dependent on the type of activation function used as well as on the way the MI is estimated. Our study confirms that different ways of binning when computing the MI lead to qualitatively different results, either supporting or refusing IB conjectures. To resolve the controversy, we study the IB principle in settings where MI is non-trivial and can be computed exactly. We monitor the dynamics of quantized neural networks, that is, we discretize the whole deep learning system so that no approximation is required when computing the MI. This allows us to quantify the information flow without measurement errors. In this setting, we observed a fitting phase for all layers and a compression phase for the output layer in all experiments; the compression in the hidden layers was dependent on the type of activation function. Our study shows that the initial IB results were not artifacts of binning when computing the MI. However, the critical claim that the compression phase may not be observed for some networks also holds true.

Related papers

• Geometric and Information Compression of Representations in Deep Learning [17.830589700881507]
  Deep neural networks transform input data into latent representations that support a wide range of downstream tasks.<n>A central open question is whether low mutual information (MI) between inputs and representations necessarily implies geometrically compressed latent spaces.<n>We investigate this question using class-wise clustering as a measure of geometric compression and theoretically sound MI estimation.
  arXiv  Detail & Related papers  (2026-06-19T16:49:50Z)
• Information Plane Analysis of Binary Neural Networks [6.259398755176288]
  We perform IP analyses on binary neural networks (BNNs) where activations are discrete and MI is finite.<n>We train BNNs to investigate the existence of late-stage compression phases and the relationship between compressed representations and generalisation performance.
  arXiv  Detail & Related papers  (2026-05-05T11:08:18Z)
• Unlearnable phases of matter [0.0]
  We show that autoregressive neural networks fail to learn global properties of distributions characterized by locally indistinguishable (LI) states.<n>By introducing a restricted statistical query model, we prove that nontrivial phases with long-range CMI, such as strong-to-weak spontaneous symmetry breaking phases, are hard to learn.
  arXiv  Detail & Related papers  (2026-02-11T19:00:01Z)
• Mutual Information Preserving Neural Network Pruning [3.7414804164475983]
  We introduce Mutual Information Preserving Pruning (MIPP), a structured activation-based pruning technique applicable before or after training. MIPP consistently outperforms state-of-the-art methods, regardless of whether pruning is performed before or after training.
  arXiv  Detail & Related papers  (2024-10-31T18:50:15Z)
• Average gradient outer product as a mechanism for deep neural collapse [26.939895223897572]
  Deep Neural Collapse (DNC) refers to the surprisingly rigid structure of the data representations in the final layers of Deep Neural Networks (DNNs) In this work, we introduce a data-dependent setting where DNC forms due to feature learning through the average gradient outer product (AGOP) We show that the right singular vectors and values of the weights can be responsible for the majority of within-class variability collapse for neural networks trained in the feature learning regime.
  arXiv  Detail & Related papers  (2024-02-21T11:40:27Z)
• Understanding and Leveraging the Learning Phases of Neural Networks [7.1169582271841625]
  The learning dynamics of deep neural networks are not well understood. We comprehensively analyze the learning dynamics by investigating a layer's reconstruction ability of the input and prediction performance. We show the existence of three phases using common datasets and architectures such as ResNet and VGG.
  arXiv  Detail & Related papers  (2023-12-11T23:20:58Z)
• Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy [55.014926694758195]
  Entropy and mutual information in neural networks provide rich information on the learning process. We leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. We show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data.
  arXiv  Detail & Related papers  (2023-12-04T01:32:42Z)
• 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)
• Learning Linear Causal Representations from Interventions under General Nonlinear Mixing [52.66151568785088]
  We prove strong identifiability results given unknown single-node interventions without access to the intervention targets. This is the first instance of causal identifiability from non-paired interventions for deep neural network embeddings.
  arXiv  Detail & Related papers  (2023-06-04T02:32:12Z)
• Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression [37.69303106863453]
  The Information Bottleneck (IB) principle offers an information-theoretic framework for analyzing the training process of deep neural networks (DNNs) In this paper, we introduce a framework for conducting IB analysis of general NNs. We also perform IB analysis on a close-to-real-scale, which reveals new features of the MI dynamics.
  arXiv  Detail & Related papers  (2023-05-13T21:44:32Z)
• Information Bottleneck-Based Hebbian Learning Rule Naturally Ties Working Memory and Synaptic Updates [0.0]
  We take an alternate approach that avoids back-propagation and its associated issues entirely. Recent work in deep learning proposed independently training each layer of a network via the information bottleneck (IB) We show that this modulatory signal can be learned by an auxiliary circuit with working memory like a reservoir.
  arXiv  Detail & Related papers  (2021-11-24T17:38:32Z)
• On the Variance of the Fisher Information for Deep Learning [79.71410479830222]
  The Fisher information matrix (FIM) has been applied to the realm of deep learning. The exact FIM is either unavailable in closed form or too expensive to compute. We investigate two such estimators based on two equivalent representations of the FIM.
  arXiv  Detail & Related papers  (2021-07-09T04:46:50Z)
• The Causal Neural Connection: Expressiveness, Learnability, and Inference [125.57815987218756]
  An object called structural causal model (SCM) represents a collection of mechanisms and sources of random variation of the system under investigation. In this paper, we show that the causal hierarchy theorem (Thm. 1, Bareinboim et al., 2020) still holds for neural models. We introduce a special type of SCM called a neural causal model (NCM), and formalize a new type of inductive bias to encode structural constraints necessary for performing causal inferences.
  arXiv  Detail & Related papers  (2021-07-02T01:55:18Z)
• Understanding Self-supervised Learning with Dual Deep Networks [74.92916579635336]
  We propose a novel framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks. We prove that in each SGD update of SimCLR with various loss functions, the weights at each layer are updated by a emphcovariance operator. To further study what role the covariance operator plays and which features are learned in such a process, we model data generation and augmentation processes through a emphhierarchical latent tree model (HLTM)
  arXiv  Detail & Related papers  (2020-10-01T17:51:49Z)

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.