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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “Bridge-connections”

RES-SE-NET: Boosting Performance of Resnets by Enhancing Bridge-connectionscs.LG

Res-SE-Net boosts Resnet performance by enhancing bridge-connections.

problem Reduced accuracy in Resnet due to lack of feature map contribution from bridge-connections.

method Proposed Res-SE-Net architecture with Squeeze-and-Excitation (SE) block to quantify and weight feature map importance.

result Res-SE-Net generalizes better than Resnet and SE-Resnet on CIFAR-10 and CIFAR-100 datasets.

ResNet Bridge-connections Squeeze-and-Excitation Feature importance Deep learning

2019-02-16abs ↗pdf ↗

An invariant for colored bonded knotsmath.GT

An invariant for knots with colored bonds respects HOMFLYPT relation.

problem Modeling and distinguishing knots with colored bonds.

method Introducing a HOMFLYPT skein module for colored bonded knots.

result The non-rigid version of the module provides information about knottedness of bonds.

knot theory colored bonds HOMFLYPT skein module protein modeling knot invariants

2019-10-10abs ↗pdf ↗

Self-shrinkers with any number of ends in

\mathbb{R}^{3}

by stacking

\mathbb{R}^{2}

math.DG

New self-shrinkers with multiple ends constructed by stacking planes.

problem Constructing self-shrinkers with any number of ends in 3D space.

method PDE gluing methods and Linearised Doubling methodology.

result Construction of self-shrinkers with

2J+1

ends and genus

2J(m-1)

self-shrinkers 3D space PDE gluing genus catenoidal bridges

2025-07-24abs ↗pdf ↗

Crossing Stocks and the Positive Grassmannian I: The Geometry behind Stock Marketq-fin.ST

It seems to be very unlikely that all relevant information in the stock market could be fully encoded in a geometrical shape. Still,the present paper will reveal the geometry behind the stock market transactions. The prices of market index (DJIA) stock components are arranged in ascending order from the smallest one in…

2014-02-06abs ↗pdf ↗

Cheeger bounds on spin-two fieldshep-th

Compact gravity models yield tiny spin-two field masses.

problem Understanding the mass of spin-two fields in compactified gravity models.

method Relies on Bakry-Émery geometry, Cheeger constant, and synthetic Ricci lower bounds.

result Proves the existence of a spin-two field with very small mass under general assumptions.

spin-two fields gravity compactifications Cheeger constant synthetic Ricci bounds CFT dualities

2021-09-23abs ↗pdf ↗

Model Bridging: Connection between Simulation Model and Neural Networkstat.ML

A new framework connects machine learning models with simulation models efficiently.

problem Interpreting complex machine learning models for real-world applications.

method Model-bridging framework using kernel mean embeddings.

result Simulations and machine learning models can be used together without high computational costs.

model bridging machine learning simulation models kernel mean embedding interpretability

2019-06-22abs ↗pdf ↗

Tensor networks for unsupervised machine learningcond-mat.stat-mech

Tensor networks improve unsupervised learning performance.

problem Improving unsupervised machine learning models.

method Autoregressive Matrix Product States (AMPS) combining quantum and machine learning.

result AMPS significantly outperforms existing tensor network models and neural networks.

Tensor networks unsupervised learning autoregressive modeling matrix product states reinforcement learning

2021-06-24abs ↗pdf ↗