Results 31 to 40 of about 90,344 (240)
Embo: a Python package for empirical data analysis using the Information Bottleneck
Journal of Open Research Software, 2021 We present 'embo', a Python package to analyze empirical data using the Information Bottleneck (IB) method and its variants, such as the Deterministic Information Bottleneck (DIB).
Eugenio Piasini +3 more
doaj +1 more source
Collaborative Information Bottleneck [PDF]
IEEE Transactions on Information Theory, 2019 Submitted to IEEE Transactions on Information Theory (revised, 29, 7 figures)
Matías Vera +2 more
openaire +3 more sources
Information Bottleneck Analysis by a Conditional Mutual Information Bound
Entropy, 2021 Task-nuisance decomposition describes why the information bottleneck loss I(z;x)−βI(z;y) is a suitable objective for supervised learning. The true category y is predicted for input x using latent variables z.
Taro Tezuka, Shizuma Namekawa
doaj +1 more source
CoRR, 2020 Representation learning of graph-structured data is challenging because both graph structure and node features carry important information. Graph Neural Networks (GNNs) provide an expressive way to fuse information from network structure and node features. However, GNNs are prone to adversarial attacks.
Tailin Wu +3 more
openaire +3 more sources
Learning and generalization with the information bottleneck [PDF]
Theoretical Computer Science, 2008 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Ohad Shamir +2 more
openaire +1 more source
The Information Bottleneck and Geometric Clustering [PDF]
Neural Computation, 2019 The information bottleneck (IB) approach to clustering takes a joint distribution [Formula: see text] and maps the data [Formula: see text] to cluster labels [Formula: see text], which retain maximal information about [Formula: see text] (Tishby, Pereira, & Bialek, 1999 ).
DJ Strouse, David J. Schwab
openaire +4 more sources
Variational Information Bottleneck for Semi-Supervised Classification
Entropy, 2020 In this paper, we consider an information bottleneck (IB) framework for semi-supervised classification with several families of priors on latent space representation. We apply a variational decomposition of mutual information terms of IB.
Slava Voloshynovskiy +4 more
doaj +1 more source
The Dual Information Bottleneck
CoRR, 2020 The Information Bottleneck (IB) framework is a general characterization of optimal representations obtained using a principled approach for balancing accuracy and complexity. Here we present a new framework, the Dual Information Bottleneck (dualIB), which resolves some of the known drawbacks of the IB.
Zoe Piran +2 more
openaire +2 more sources
On Information Bottleneck for Gaussian Processes
2022 IEEE Information Theory Workshop (ITW), 2022 2022 IEEE Information Theory Workshop (ITW)
Michael Dikshtein +2 more
openaire +3 more sources
Multivariate Information Bottleneck
CoRR, 2013 Appears in Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence (UAI2001)
Nir Friedman +3 more
openaire +3 more sources