We define the intrinsic scale at which a network begins to reveal its identity as the scale at which subgraphs in the network (created by a random walk) are distinguishable from similar sized subgraphs in a perturbed copy of the network. We conduct an extensive study of intrinsic scale for several networks, ranging fro…
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 “intrinsic networks”
New method quantifies intrinsic causal contributions in neural networks.
problem Measuring the causal influence of input features in deep neural networks.
method Proposes an identifiable generative post-hoc framework to quantify intrinsic causal contributions (ICC) as structural causal models.
result ICC generates more intuitive and reliable explanations compared to existing global explanation techniques.
Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionalitystat.ML
Bayesian neural networks achieve optimal posterior contraction rates in Besov spaces with intrinsic dimensionality.
problem High-dimensional structured estimation problems with unknown smoothness levels.
method Sparse Bayesian neural networks with either sparse or continuous shrinkage priors.
result Optimal posterior contraction rates are achieved, adapting to the unknown smoothness level of the true function.
Proposes eDNNs and iDNNs for deep learning on manifolds.
problem Deep learning on manifolds with geometric preservation and intrinsic geometry incorporation.
method Intrinsic and extrinsic deep neural networks (iDNNs and eDNNs) with geometric embeddings and maps.
result Empirical risk minimizers of eDNNs and iDNNs converge optimally.
Geometry-aware similarity metrics for neural representations on Riemannian and statistical manifoldscs.LG
MSA compares neural representations' intrinsic geometry for better understanding.
problem Existing similarity measures fail to capture subtle distinctions between neural network solutions.
method Metric similarity analysis (MSA) using Riemannian geometry.
result MSA can disentangle features of neural computations and compare nonlinear dynamics.
This paper addresses the following questions pertaining to the intrinsic dimensionality of any given image representation: (i) estimate its intrinsic dimensionality, (ii) develop a deep neural network based non-linear mapping, dubbed DeepMDS, that transforms the ambient representation to the minimal intrinsic space, an…
Estimates intrinsic dimension of data for GANs.
problem Estimating intrinsic dimension of high-dimensional data.
method Uses Wasserstein distances for estimation.
result Provides sample complexity bounds for GANs.
New risk measures for financial networks avoid external capital, reducing systemic risk.
problem Systemic risk in financial networks is underestimated by traditional methods.
method Developed set-valued, intrinsic risk measures for financial networks.
result Systemic intrinsic risk measures are more stable and avoid reliance on external capital.
New method estimates deep neural network's intrinsic dimension for better generalization.
problem Estimating intrinsic dimension of deep neural networks for generalization.
method Topological data analysis (TDA) and persistent homology (PHD).
result Efficient algorithm to estimate PHD in deep neural networks.
Shallow nonlinear networks can separate classes linearly with polynomially scaling width.
problem Understanding the linear separability of deep networks' features.
method Modeling inputs as a union of low-dimensional subspaces and using random weights and quadratic activations.
result Shallow nonlinear networks can achieve linear separation with polynomially scaling width.
The paper explores how neural networks generalize differently from natural and medical images.
problem Discrepancies in generalization error between natural and medical images.
method Established and empirically validated a generalization scaling law with respect to intrinsic dataset properties.
result Higher intrinsic 'label sharpness' of medical images leads to higher adversarial vulnerability.
The focus of this paper is on intrinsic methods to detect overfitting. By intrinsic methods, we mean methods that rely only on the model and the training data, as opposed to traditional methods (we call them extrinsic methods) that rely on performance on a test set or on bounds from model complexity. We propose a famil…
CNNs trained by gradient descent can learn intrinsic image rank robustly to background noises.
problem Understanding the intrinsic dimension of data in over-parameterized CNNs.
method Theoretical analysis and experiments on synthetic and real datasets.
result CNNs trained by gradient descent can learn the intrinsic dimension of clean images robustly to background noises.
Data living on manifolds commonly appear in many applications. Often this results from an inherently latent low-dimensional system being observed through higher dimensional measurements. We show that under certain conditions, it is possible to construct an intrinsic and isometric data representation, which respects an …
Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionalitystat.ML
In this study, we prove that an intrinsic low dimensionality of covariates is the main factor that determines the performance of deep neural networks (DNNs). DNNs generally provide outstanding empirical performance. Hence, numerous studies have actively investigated the theoretical properties of DNNs to understand thei…
We propose networked exponential families to jointly leverage the information in the topology as well as the attributes (features) of networked data points. Networked exponential families are a flexible probabilistic model for heterogeneous datasets with intrinsic network structure. These models can be learnt efficient…
Three training regimes found for scale-invariant neural networks on the sphere.
problem Training scale-invariant neural networks on the sphere with varying effective learning rate.
method Investigated three regimes of training: convergence, chaotic equilibrium, and divergence.
result Discovered three distinct training regimes with unique characteristics.
Deep networks can adapt to intrinsic dimensionality beyond domain constraints.
problem Approximating functions on low-dimensional manifolds with high-dimensional data.
method Two-layer compositions with ReLU activation, using dimensionality reducing feature maps.
result Near optimal approximation rates depend on the complexity of the dimensionality reducing map, not the ambient dimension.
Capsule Networks improve autonomous navigation in sparse environments.
problem Challenges in reinforcement learning for sparse reward environments.
method Caps-EM pairs CapsNets with Advantage Actor Critic, using fewer parameters.
result Caps-EM achieves significant time improvements and fewer parameters compared to competing methods.
We introduce an event based framework of directional changes and overshoots to map continuous financial data into the so-called Intrinsic Network - a state based discretisation of intrinsically dissected time series. Defining a method for state contraction of Intrinsic Network, we show that it has a consistent hierarch…
From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learningcs.LG
Deep multi-task learning benefits from low intrinsic dimensionality, leading to better generalization.
problem Improving generalization in deep multi-task learning with high-dimensional models.
method Parametrizing multi-task networks in a low-dimensional space using random expansions and weight compression.
result First non-vacuous generalization bounds for deep multi-task networks are derived.
Deep networks can approximate high-dimensional distributions from low-dimensional ones.
problem Approximating high-dimensional distributions from low-dimensional ones.
method Proved neural networks can transform low-dimensional distributions to high-dimensional ones with arbitrary closeness measured by Wasserstein distances and maximum mean discrepancy.
result Upper bounds of the approximation error are obtained in terms of the width and depth of neural network.
Neural networks' performance scales with data size, explained by data manifold dimensionality.
problem Understanding the scaling of neural network performance with the number of parameters.
method Explained by the intrinsic dimension of the data manifold, confirmed through teacher/student framework and various datasets.
result The scaling exponent α is approximately 4 divided by the intrinsic dimension d of the data manifold.
Study reveals differences in medical image models' hidden representation refinement.
problem Understanding how intrinsic dimensionality changes in neural network hidden representations across different domains.
method Analysis of 11 natural and medical image datasets using 6 network architectures.
result Medical image models refine hidden representations earlier, suggesting differences in feature abstraction.
At an early age, human infants are able to learn and build a model of the world very quickly by constantly observing and interacting with objects around them. One of the most fundamental intuitions human infants acquire is intuitive physics. Human infants learn and develop these models, which later serve as prior knowl…
Low-dimensional structure in images helps deep learning models generalize better.
problem Understanding the intrinsic dimensionality of images for better model performance.
method Applied dimension estimation tools to popular image datasets and used GANs to manipulate intrinsic dimensionality.
result Natural image datasets have very low intrinsic dimensionality, which aids neural networks in learning and generalizing.
New algorithm estimates intrinsic dimension of discrete datasets.
problem Inaccuracies in using continuous methods for discrete datasets.
method Introduced an algorithm to infer intrinsic dimension of discrete spaces.
result Demonstrated accuracy on benchmark datasets and found a small intrinsic dimension in a metagenomic dataset.
New research shows that the dimension gap between intrinsic and ambient dimensions affects adversarial vulnerability of machine learning models.
problem The mystery of adversarial attacks on machine learning models.
method Introducing two types of adversarial attacks and proving their relationship to the dimension gap.
result The dimension gap between intrinsic and ambient dimensions makes clean-trained models more vulnerable to off-manifold adversarial perturbations.
Adaptive framework for learning latent space dimensions in GANs.
problem Inadequate latent space dimensions lead to poor generative models for complex data.
method Proposes a novel framework (LWGAN) that adaptively learns latent dimensions of data manifolds.
result Proves that the estimated intrinsic dimension is a consistent estimate of the true data manifold dimension.
Many recently trained neural networks employ large numbers of parameters to achieve good performance. One may intuitively use the number of parameters required as a rough gauge of the difficulty of a problem. But how accurate are such notions? How many parameters are really needed? In this paper we attempt to answer th…
The paper proposes a least squares method for binary compressive sampling with low intrinsic dimension signals.
problem Recovering signals from binary measurements with noise and sign flips.
method Least squares decoder for signals with low generative intrinsic dimension.
result The least squares decoder achieves a sharp estimation error of under certain conditions.
New metric explains neural network performance, simplifying generalization error calculation.
problem Precise characterization of neural network generalization error.
method Introducing Representation Gap, linking to intrinsic dimension and equivariant diffusion models.
result Asymptotic equivalent of Representation Gap is governed by intrinsic dimension, easy to estimate.
LIDL estimates local intrinsic dimension in high dimensions.
problem Estimating local intrinsic dimension in high-dimensional data.
method Approximate likelihood using parametric neural density estimation.
result LIDL scales to thousands of dimensions and yields competitive results.
Conformal Autoencoders infer intrinsic dimensionality and impose invariance.
problem Detecting intrinsic dimensionality and imposing invariance in nonlinear manifold data.
method Imposing orthogonality conditions on latent variables to infer intrinsic dimensionality and build coordinate invariance.
result The method can infer intrinsic dimensionality and build coordinate invariance on submanifolds.
In a complex system, the interactions between individual agents often lead to emergent collective behavior like spontaneous synchronization, swarming, and pattern formation. The topology of the network of interactions can have a dramatic influence over those dynamics. In many studies, researchers start with a specific …
Deep neural networks progressively transform their inputs across multiple processing layers. What are the geometrical properties of the representations learned by these networks? Here we study the intrinsic dimensionality (ID) of data-representations, i.e. the minimal number of parameters needed to describe a represent…
One popular hypothesis of neural network generalization is that the flat local minima of loss surface in parameter space leads to good generalization. However, we demonstrate that loss surface in parameter space has no obvious relationship with generalization, especially under adversarial settings. Through visualizing …
Neural networks provide a rich class of high-dimensional, non-convex optimization problems. Despite their non-convexity, gradient-descent methods often successfully optimize these models. This has motivated a recent spur in research attempting to characterize properties of their loss surface that may explain such succe…
Wasserstein Autoencoders improve model efficiency and interpretability for low-dimensional data.
problem Limited statistical guarantees for WAEs in low-dimensional data.
method Proper network architecture selection and analysis of expected excess risk convergence rates.
result WAEs can learn data distributions efficiently when intrinsic dimension is considered.
Introduces intrinsic Hopf-Lax semigroup linking to intrinsic slope.
problem Understanding intrinsic Hopf-Lax semigroup and its relation to intrinsic slope.
method Introduces and proves the link between intrinsic Hopf-Lax semigroup and intrinsic slope.
result Intrinsic Hopf-Lax semigroup is a subsolution of Hamilton-Jacobi type equality.
Deep networks can approximate functions with fewer learnable parameters than previously thought.
problem High computational costs due to large number of parameters in deep neural networks.
method Theoretical design of ReLU networks with a few intrinsic parameters and numerical experiments.
result ReLU networks with a small number of intrinsic parameters can achieve good approximations of functions.
This paper improves spectral embedding for multipartite networks, revealing latent subspaces and providing consistent node representations.
problem Improving spectral embedding for multipartite networks to better represent node types.
method Developed a follow-on step to spectral embedding that recovers node representations in their intrinsic rather than ambient dimension, proving consistency under a specific model.
result Node representations in multipartite networks lie near type-specific subspaces, and the proposed method recovers these representations consistently.
New research shows common ID estimators in neural representations are inaccurate.
problem Inaccurate estimation of intrinsic dimensions in neural representations.
method Theoretical and empirical investigation of ID estimators in neural representations.
result Common ID estimators do not accurately reflect the true underlying ID of neural representations.
Study shows dataset properties impact adversarial machine learning robustness.
problem Vulnerability of DNNs to adversarial attacks.
method Examined five datasets, analyzed input size and contrast effects.
result Input size and contrast significantly influence adversarial success.
On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimensionstat.ML
The paper improves GANs' theoretical guarantees for low-dimensional data.
problem Theoretical guarantees for GANs' statistical accuracy remain pessimistic.
method Analytical derivation of statistical guarantees on estimated densities.
result Theoretical rates of convergence for GANs and BiGANs are derived.
The paper examines Wiener process for LID estimation methods.
problem Estimating local intrinsic dimension in high-dimensional datasets.
method Investigates recent LID estimation methods from a Wiener process perspective.
result Explains how methods behave under non-ideal conditions.
Efficient exploration remains a challenging problem in reinforcement learning, especially for those tasks where rewards from environments are sparse. A commonly used approach for exploring such environments is to introduce some "intrinsic" reward. In this work, we focus on model uncertainty estimation as an intrinsic r…
Recently, adversarial deception becomes one of the most considerable threats to deep neural networks. However, compared to extensive research in new designs of various adversarial attacks and defenses, the neural networks' intrinsic robustness property is still lack of thorough investigation. This work aims to qualitat…