Research
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.

169,341 papers · 148 categories

Trend · papers per month

237475712949 · Jun 202019922001200920182026
48 results for network essence

New invariants measure how far spanning surfaces are from being compressible.

problem Understanding how essential spanning surfaces are in 3-manifolds.
method Introducing algebraic and geometric essence invariants, proving plumbing respects algebraic essence, and extending results to arbitrary 3-manifolds.
result Plumbing respects the algebraic essence of spanning surfaces, extending Ozawa's theorem.

Investigates latent variable models for useful generative concept representations.

problem Creating latent representations that support various concepts and attributes.
method Latent variable modeling, including latent variable models, latent representations, and latent spaces.
result Hierarchical latent representations and latent space vectors and geometry are effective for generative concept representations.

Identifies influential neurons in deep networks for better explanations.

problem Explaining complex behaviors of deep neural networks.
method Identifies neurons with high influence using an influence measure and provides interpretations.
result Identifies influential concepts that generalize across instances and isolates individual features used by the network.

Variational Laplace improves Bayesian neural network performance without sampling.

problem Improving Bayesian neural network performance and calibration.
method Develops a new variational Laplace method for BNNs, exploiting curvature of likelihood.
result Variational Laplace outperforms standard VI methods in test performance and calibration.

Paper introduces a new edge exchangeable block model for complex networks.

problem Limitations of the stochastic block model in analyzing complex networks.
method Develops a Bayesian nonparametric edge exchangeable block model.
result The new model outperforms state-of-the-art SBMs for link prediction.

mGRN improves multivariate time series prediction by managing marginal and joint memories.

problem Extracting dependencies in multivariate sequential data with strong serial and cross-sectional dependencies.
method Developed a novel recurrent network architecture, Memory-Gated Recurrent Networks (mGRN), with gates for marginal and joint memories.
result mGRN consistently outperforms state-of-the-art architectures on various public datasets.

Generative Adversarial Forests improve GAN performance through better conditioning.

problem Improving the stability and performance of Generative Adversarial Networks (GANs).
method Embedding decision forest capabilities into GAN discriminators.
result Significant performance improvements on the Oxford Flowers and Aligned Celebrity Faces datasets.

This work analyzes industrial IoT data for security using machine learning.

problem Security vulnerabilities in industrial IoT networks.
method Transformed industrial network data into time series and analyzed with three algorithms.
result Matrix Profiles outperform other methods with minimal parameterization.

WaveFit uses fixed-point iteration to create high-quality neural vocoders.

problem Creating high-quality neural vocoders with fast inference.
method Integrates GANs' adversarial training into a DDPM-like iterative framework based on fixed-point iteration.
result WaveFit synthesizes speech with naturalness comparable to human speech, and is significantly faster than existing methods.

This paper provides mathematical foundations for regression methods used in forward initial margin approximation.

problem Developing robust methods for approximating forward initial margin.
method Introduces mathematical rigor to show that regression methods are variations of approximating the conditional expectation function.
result Each regression method is a numerical estimation of the conditional expectation with a different functional form.

Proposes a new confidence criterion for deep neural networks to predict failures.

problem Predicting failures in deep neural networks.
method Introduces True Class Probability (TCP) as a new confidence criterion and proposes a learning scheme to estimate it.
result The proposed approach consistently outperforms existing methods in failure prediction.

CGRL improves graph neural networks' OOD generalization by blocking spurious correlations.

problem Graph Neural Networks struggle with out-of-distribution data due to learning spurious correlations.
method Formulates a causal graph, uses backdoor adjustment, and introduces a loss replacement strategy.
result Significantly improves OOD generalization of GNNs, stabilizing mutual information learning.

Globalization is one of the central concepts of our age. The common perception of the process is that, due to declining communication and transport costs, distance becomes less and less important. However, the distance coefficient in the gravity model of trade, which grows in time, indicates that the role of distance i…

2014-09-21abs ↗pdf ↗

This study uses complex networks to analyze influential spreaders and their effects on different market sectors.

problem Existing methods failed to distinguish between positive and negative influences of market sectors.
method LIEST (Local Influential Effects for Specific Target) method using complex network analysis.
result LIEST effectively distinguishes positive and negative influences of market sectors during different periods.

STanHop predicts multivariate time series with memory-enhanced capabilities.

problem Predicting multivariate time series with memory-enhanced capabilities.
method Sparse Tandem Hopfield Network (STanHop) with two external memory modules.
result STanHop outperforms dense Hopfield models in memory retrieval error.

New method calibrates confidence of neural networks for better out-of-distribution detection.

problem Detecting samples from in-distribution vs. out-of-distribution in machine learning.
method Jointly trains classification and generative neural networks with additional terms to improve confidence calibration.
result Significantly improved detection performance on various image datasets.

NetSMF efficiently embeds large networks by sparse matrix factorization.

problem Learning latent representations for large-scale networks efficiently.
method NetSMF leverages spectral sparsification to efficiently sparsify and factorize a dense matrix.
result NetSMF achieves high efficiency and effectiveness on large-scale networks.

A new framework decouples SSL tasks into VDA and VLC, revealing VDA's importance.

problem Designing effective self-supervised learning tasks without manual annotation.
method Borrowing a multi-view perspective, the paper decouples popular pretext tasks into VDA and VLC, focusing on VDA's role in feature learning.
result VDA tasks dominate SSL performance, and integrating predictions from augmented views improves overall performance.

Few-shot unsupervised image-to-image translation model learns from a few examples.

problem Current unsupervised image-to-image translation methods require many images at training time.
method Coupling adversarial training with a novel network design for few-shot learning.
result Model achieves effective few-shot image-to-image translation.

We provide yet another proof of the existence of calibrated forecasters; it has two merits. First, it is valid for an arbitrary finite number of outcomes. Second, it is short and simple and it follows from a direct application of Blackwell's approachability theorem to carefully chosen vector-valued payoff function and …

2009-12-18abs ↗pdf ↗

Estimates and compares the capabilities of neural network architectures.

problem Developing quantitative methods to estimate and compare neural network architectures.
method Defining capacity as the logarithm of the number of functions an architecture can compute, and proving a cubic polynomial formula for layered architectures.
result The capacity of a neural network is given by a cubic polynomial in the layer sizes, with bottlenecks affecting the capacity.

The main goal of the paper is to solve some problems about shadow for the sphere generalized on the case of the ellipsoid. Here, the essence of the problem is to find the the minimal number of non-overlapping balls with centers on the sphere which are not holding the center of the sphere and such that every line passin…

2015-10-07abs ↗pdf ↗

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.

ECC compresses DNNs for energy-constrained devices like UAVs and smartphones.

problem Energy-constrained deep neural networks in vision applications.
method ECC uses a bilinear regression model to estimate DNN energy consumption and optimizes compression to meet energy constraints.
result ECC achieves higher accuracy under the same or lower energy budget compared to state-of-the-art techniques.