There has recently been much work on the "wide limit" of neural networks, where Bayesian neural networks (BNNs) are shown to converge to a Gaussian process (GP) as all hidden layers are sent to infinite width. However, these results do not apply to architectures that require one or more of the hidden layers to remain n…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “network bottlenecks”
Wide neural networks become linear, but adding bottlenecks makes them bilinear or multilinear.
problem Understanding the transition of neural networks from linearity to higher-order functions.
method Analyzing the behavior of randomly initialized wide neural networks with and without bottleneck layers.
result Bottleneck layers transform the network's function from linear to bilinear or multilinear.
The paper identifies network bottlenecks using minimax paths in stochastic networks.
problem Identifying bottlenecks in networks with stochastic weights.
method Modeling as combinatorial semi-bandit problem, applying combinatorial Thompson Sampling, and approximating the original objective due to computational intractability.
result Established an upper bound on Bayesian regret and evaluated Thompson Sampling performance on real-world networks.
Graph neural networks struggle to propagate long-range information, causing over-squashing.
problem Graph neural networks struggle to propagate long-range information.
method Identified over-squashing as the bottleneck in GNNs, demonstrated on various models.
result Breaking the bottleneck improves GNNs' performance on long-range problems.
Deep ResNets favor low bottleneck rank with proper hyperparameters.
problem Understanding the inductive bias of deep neural networks.
method Computed minimum-norm weights of a deep linear ResNet.
result Deep nonlinear ResNets have an inductive bias towards minimizing bottleneck rank.
Softmax is an output activation function for modeling categorical probability distributions in many applications of deep learning. However, a recent study revealed that softmax can be a bottleneck of representational capacity of neural networks in language modeling (the softmax bottleneck). In this paper, we propose an…
Unified information-theoretic objectives for training deep neural networks.
problem Difficulty in computing information-theoretic quantities for large deep neural networks.
method Review and unify competing objectives, develop surrogate objectives.
result Surrogate objectives allow applying information bottleneck to modern neural network architectures.
New research shows non-bottlenecked autoencoders can outperform bottlenecked ones for anomaly detection.
problem The necessity of a bottleneck in autoencoders for anomaly detection.
method Investigated two ways to remove bottlenecks: overparameterising the latent layer and introducing skip connections. Carried out extensive experiments on various AE types and datasets.
result Non-bottlenecked autoencoders can outperform bottlenecked ones, improving anomaly detection performance.
PCBMs turn any neural network into interpretable models without dense annotations.
problem Restrictive nature of CBMs and lack of dense concept annotations in training data.
method Introduce PCBMs that can turn any neural network into interpretable models without dense annotations.
result PCBMs can turn any neural network into interpretable models without dense annotations, improving interpretability and performance.
We introduce the HSIC (Hilbert-Schmidt independence criterion) bottleneck for training deep neural networks. The HSIC bottleneck is an alternative to the conventional cross-entropy loss and backpropagation that has a number of distinct advantages. It mitigates exploding and vanishing gradients, resulting in the ability…
This paper analyzes the training dynamics of binary neural networks using information bottleneck.
problem Training binary neural networks is challenging due to discontinuity in activation functions.
method The approach uses the Information Bottleneck principle to analyze BNN training dynamics.
result Training dynamics of BNNs are different from DNNs, with both phases occurring simultaneously.
Proposes Decodable Information Bottleneck for optimal representation learning.
problem Finding optimal representations for supervised learning.
method Integrates information retention and compression with the desired predictive family.
result Optimal representations lead to better expected test performance and can be estimated with guarantees.
CNNs use a bottleneck structure to focus on a few frequencies, affecting function representation.
problem Understanding how CNNs focus on specific frequencies in their feature learning.
method Defined Convolution Bottleneck (CBN) structure, measured CBN rank, and analyzed parameter norms.
result Parameter norm scales with depth and CBN rank, and networks with optimal parameters exhibit this structure.
GIB improves neural network generalization by dynamically selecting task-relevant features across different sequential environments.
problem Poor generalization of deep neural networks to unseen environments.
method Proposes a gated information bottleneck (GIB) approach that dynamically drops spurious correlations and selects task-relevant features.
result GIB outperforms other IB approaches in adversarial robustness and OOD detection.
MPNNs struggle with class-bottlenecks and heterophily, leading to performance limitations.
problem Performance limitations of MPNNs under heterophily and structural bottlenecks.
method A statistical framework decomposing model performance into SNR components and proving bounds on sensitivity.
result Optimal graph structures for maximizing higher-order homophily are disjoint unions of single-class and two-class-bipartite clusters.
In this draft, which reports on work in progress, we 1) adapt the information bottleneck functional by replacing the compression term by class-conditional compression, 2) relax this functional using a variational bound related to class-conditional disentanglement, 3) consider this functional as a training objective for…
Graph Information Bottleneck (GIB) optimizes graph representations for robustness against adversarial attacks.
problem Challenges in learning graph representations due to structure and feature information.
method GIB is an information-theoretic principle that balances expressiveness and robustness by maximizing mutual information between representation and target, while constraining mutual information with input data.
result GIB-based models are more robust to adversarial attacks, achieving up to 31% improvement.
The Information bottleneck method is an unsupervised non-parametric data organization technique. Given a joint distribution P(A,B), this method constructs a new variable T that extracts partitions, or clusters, over the values of A that are informative about B. The information bottleneck has already been applied to doc…
We present a simple case study, demonstrating that Variational Information Bottleneck (VIB) can improve a network's classification calibration as well as its ability to detect out-of-distribution data. Without explicitly being designed to do so, VIB gives two natural metrics for handling and quantifying uncertainty.
Graph rewiring method alleviates over-squashing in GNNs.
problem Over-squashing and bottlenecks in graph neural networks.
method Curvature-based graph rewiring method.
result Negatively curved edges cause over-squashing in GNNs.
DAB enriches deep networks with uncertainty estimates using a codebook of training inputs.
problem Lack of uncertainty estimation in deep neural networks.
method Distance Aware Bottleneck (DAB) method that learns a codebook of training inputs.
result DAB achieves better OOD detection and misclassification prediction than prior methods.
DS-Sync improves distributed DNN training efficiency by 94% with minimal accuracy loss.
problem Network bottlenecks in distributed DNN training.
method Divide workers into non-overlapping groups for independent synchronization, then shuffle workers among groups iteratively.
result DS-Sync achieves up to 94% improvement in training time with minimal accuracy loss.
New Variational InfoMax objective improves neural network performance.
problem Optimizing neural networks using Bayesian Inference and Information Bottleneck.
method Derive Variational InfoMax (VIM) objective that maximizes InfoMax directly.
result VIM improves model performance in accuracy, robustness, and representation quality.
This work analyzes how bottleneck layers and skip connections affect linear denoising autoencoders' generalization.
problem Understanding the generalization of linear denoising autoencoders in overparameterized regimes.
method Analyzes two-layer linear denoising autoencoders with a bottleneck layer and skip connection, deriving test risk formulas.
result Bottleneck layers introduce an additional complexity measure, while skip connections can mitigate variance.
FrostNet improves INT8 quantization efficiency in mobile networks.
problem The importance of network architecture for optimal INT8 quantization.
method Quantization-aware training (QAT) with StatAssist and GradBoost, hardware-aware NAS.
result FrostNets achieve higher recognition accuracy with comparable latency when quantized.
An accurate and fast estimation of the available bandwidth in a network with varying cross-traffic is a challenging task. The accepted probing tools, based on the fluid-flow model of a bottleneck link with first-in, first-out multiplexing, estimate the available bandwidth by measuring packet dispersions. The estimation…
Deep learning networks have shown state-of-the-art performance in many image reconstruction problems. However, it is not well understood what properties of representation and learning may improve the generalization ability of the network. In this paper, we propose that the generalization ability of an encoder-decoder n…
Tutorial on information bottleneck problems with connections to coding and learning.
problem Information bottleneck problems and their connections to coding and learning.
method Information theoretic perspective, practical methods, connections to various problems.
result Optimal trade-offs between relevance and complexity in discrete and vector Gaussian frameworks.
Proposes a robust VIB approach using soft labels and mutual info estimation.
problem Improving robustness of VIB to adversarial perturbations.
method Refines categorical class information with soft labels from a reference network, relaxes Gaussian posterior assumption.
result Significantly outperforms benchmarked models on MNIST and CIFAR-10.
Combining the Information Bottleneck model with deep learning by replacing mutual information terms with deep neural nets has proved successful in areas ranging from generative modelling to interpreting deep neural networks. In this paper, we revisit the Deep Variational Information Bottleneck and the assumptions neede…
Large neural networks learn low-dimensional representations that balance complexity and regularity.
problem Understanding the tradeoff between low-dimensional representations and complexity in deep neural networks.
method Computed finite depth corrections to reveal a measure of regularity that bounds the pseudo-determinant of the Jacobian.
result Proved the conjectured bottleneck structure in learned features as network depth increases, showing almost all hidden representations are approximately low-dimensional and weight matrices have singular values close to 1.
PCBM improves neural network generalization by partially observing concepts.
problem Decreased generalization performance due to observing all concepts in CBM.
method Developed a theoretical analysis of PCBM's Bayesian generalization error.
result PCBM's generalization error is lower than CBM's due to partial concept observation.
New learning rules from information bottleneck improve deep learning without precise labels.
problem Training deep neural networks with backpropagation is biologically implausible.
method Kernelized information bottleneck principle with 3-factor Hebbian structure.
result The new learning rules perform nearly as well as backpropagation on image classification tasks.
LogDet estimator improves entropy estimation in neural networks.
problem Inconsistent observations and diversified interpretation in neural networks.
method Proposes LogDet estimator for reliable entropy approximation.
result LogDet estimator overcomes distributional diversity issues.
Variational Information Bottleneck for Unsupervised Clustering: Deep Gaussian Mixture Embeddingcs.LG
In this paper, we develop an unsupervised generative clustering framework that combines the Variational Information Bottleneck and the Gaussian Mixture Model. Specifically, in our approach, we use the Variational Information Bottleneck method and model the latent space as a mixture of Gaussians. We derive a bound on th…
New method improves deep neural network performance in regression tasks.
problem Improving generalization, robustness, and explainability of deep neural networks in regression.
method Developed a new Information Bottleneck approach using Cauchy-Schwarz divergence.
result Demonstrated superior performance on six real-world regression tasks.
Study clarifies Bayesian generalization error in CBM for 3-layered linear neural networks.
problem Understanding the generalization error in concept bottleneck models.
method Mathematical analysis of Bayesian generalization error and free energy in CBM for 3-layered linear neural networks.
result CBM significantly alters the parameter region and Bayesian generalization error compared to standard models.
Information bottleneck (IB) is a technique for extracting information in one random variable that is relevant for predicting another random variable . IB works by encoding in a compressed "bottleneck" random variable from which can be accurately decoded. However, finding the optimal bottleneck variab…
Deep neural networks (DNNs) are incredibly brittle due to adversarial examples. To robustify DNNs, adversarial training was proposed, which requires large-scale but well-labeled data. However, it is quite expensive to annotate large-scale data well. To compensate for this shortage, several seminal works are utilizing l…
Estimates latent dimensionality for prediction tasks using mutual information.
problem Estimating the latent dimensionality needed for accurate prediction.
method Formulates the problem as an Information Bottleneck question and uses neural mutual information estimators with a hybrid critic to preserve latent geometry.
result The hybrid critic method provides a more accurate estimation of task-relevant dimensionality.
This paper focuses on the problem of query by example spoken term detection (QbE-STD) in zero-resource scenario. State-of-the-art approaches primarily rely on dynamic time warping (DTW) based template matching techniques using phone posterior or bottleneck features extracted from a deep neural network (DNN). We use bot…
We find the maximum mutual information for neural networks and its key determinants.
problem Understanding the maximum mutual information in neural architectures.
method Derived closed-form expression for maximum mutual information across neural network families.
result Maximum mutual information stems from a generalized formula and is influenced by network width and statistical invariances.
We propose a novel strategy for extracting features in supervised learning that can be used to construct a classifier which is more robust to small perturbations in the input space. Our method builds upon the idea of the information bottleneck by introducing an additional penalty term that encourages the Fisher informa…
Finet uses FBN for efficient, lightweight neural networks.
problem Building efficient neural networks with limited computational resources.
method Introduces Fine-grained Batch Normalization (FBN) and a novel light-weight network (Finet) that combines FBN with standard convolution.
result Finet achieves state-of-the-art performance on ImageNet classification with reduced computational complexity.
Recent years, many researches attempt to open the black box of deep neural networks and propose a various of theories to understand it. Among them, Information Bottleneck (IB) theory claims that there are two distinct phases consisting of fitting phase and compression phase in the course of training. This statement att…
SCBMs model causal effects using low-dimensional bottlenecks.
problem Causal effect estimation in high-dimensional systems.
method Structural causal models with low-dimensional summary statistics.
result SCBMs provide a flexible framework for task-specific dimension reduction.
Sparse neural networks visualize paired transcriptomic and electrophysiological data.
problem Efficiently analyzing and visualizing paired multivariate neuroscientific data.
method Sparse deep neural networks with a two-dimensional bottleneck and group lasso penalty.
result Biologically interpretable two-dimensional visualizations of paired data.
Proposes GIB for recognizing informative subgraphs in graphs.
problem Recognizing a subgraph that is maximally informative yet compressive.
method Graph Information Bottleneck (GIB) framework, mutual information estimator, bi-level optimization, connectivity loss.
result IB-subgraph improves graph classification, interpretation, and denoising.