Deep learning and the information bottleneck principle
Naftali Tishby,Noga Zaslavsky +1 more
- pp 1-5
TLDR
It is argued that both the optimal architecture, number of layers and features/connections at each layer, are related to the bifurcation points of the information bottleneck tradeoff, namely, relevant compression of the input layer with respect to the output layer.Abstract:
Deep Neural Networks (DNNs) are analyzed via the theoretical framework of the information bottleneck (IB) principle. We first show that any DNN can be quantified by the mutual information between the layers and the input and output variables. Using this representation we can calculate the optimal information theoretic limits of the DNN and obtain finite sample generalization bounds. The advantage of getting closer to the theoretical limit is quantifiable both by the generalization bound and by the network's simplicity. We argue that both the optimal architecture, number of layers and features/connections at each layer, are related to the bifurcation points of the information bottleneck tradeoff, namely, relevant compression of the input layer with respect to the output layer. The hierarchical representations at the layered network naturally correspond to the structural phase transitions along the information curve. We believe that this new insight can lead to new optimality bounds and deep learning algorithms.read more
Citations
More filters
Posted Content
Multi-Layered Gradient Boosting Decision Trees
Ji Feng,Yang Yu,Zhi-Hua Zhou +2 more
TL;DR: This work proposes the multi-layered GBDT forest, with an explicit emphasis on exploring the ability to learn hierarchical representations by stacking several layers of regression GBDTs as its building block, and confirms the effectiveness of the model in terms of performance and representation learning ability.
Journal ArticleDOI
Information-Optimum LDPC Decoders Based on the Information Bottleneck Method
Jan Lewandowsky,Gerhard Bauch +1 more
TL;DR: This paper explains in detail, how the Information Bottleneck method can be applied to construct discrete message passing decoders for regular low-density parity-check codes using only unsigned integers and using only simple lookup tables as node operations.
Posted Content
Meta-Learning without Memorization
TL;DR: This paper designs a meta-regularization objective using information theory that places precedence on data-driven adaptation and demonstrates its applicability to both contextual and gradient-based meta-learning algorithms, and applies it in practical settings where applying standard meta- learning has been difficult.
Posted Content
An information-theoretic analysis of deep latent-variable models
TL;DR: An information-theoretic framework for understanding trade-offs in unsupervised learning of deep latent-variables models using variational inference and how this framework sheds light on many recent proposed extensions to the variational autoencoder family is presented.
Journal Article
FMix: Enhancing Mixed Sample Data Augmentation
Ethan Harris,Antonia Marcu,Matthew Painter,Mahesan Niranjan,Adam Prügel-Bennett,Jonathon S. Hare +5 more
TL;DR: FMix is proposed, an MSDA that uses binary masks obtained by applying a threshold to low frequency images sampled from Fourier space that improves performance over MixUp and CutMix for a number of models across a range of data sets and problem settings.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Book
Elements of information theory
Thomas M. Cover,Joy A. Thomas +1 more
TL;DR: The author examines the role of entropy, inequality, and randomness in the design of codes and the construction of codes in the rapidly changing environment.
Journal ArticleDOI
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Journal ArticleDOI
Representation Learning: A Review and New Perspectives
TL;DR: Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks.
Book
Learning Deep Architectures for AI
TL;DR: The motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer modelssuch as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks are discussed.