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.

169,291 papers · 148 categories

Trend · papers per month

84169253337 · Jun 202019922001200920182026
48 results for bridge design

Study uses machine learning to predict optimal bridge types based on NBI data.

problem Improving bridge design selection through machine learning.
method Supervised learning on modified NBI dataset, feature selection, cross-validation, state-specific models.
result Supervised learning models predict optimal bridge types with high accuracy.

The paper bridges spectral and spatial graph convolutions, improving model capacity and transferability.

problem Improving graph neural networks by bridging spectral and spatial design.
method Theoretical demonstration and general framework for spectral analysis, new spectral convolutions, and depthwise separable convolutions.
result General framework allows spectral analysis of ConvGNNs, showing their performance and limits, and proposing new spectral convolutions.

Neural approach enhances AI trustworthiness, generalization, and robustness.

problem Challenges in explaining, generalizing, and adapting AI models to uncertain environments.
method Customized trustworthy networks, flexible learning regularizers, open-world recognition losses.
result Significant performance improvements across various open-world multimedia recognition scenarios.

Unified framework for robust, stable, and efficient density ratio estimation.

problem Density-chasm and support-chasm problems in density ratio estimation.
method Dequantified diffusion-Schrödinger bridge (D3RE) framework with DDBI and DSBI.
result Offers uniform approximation and bounded time scores in theory and empirical performance.

New algorithm solves Schrödinger bridge problem with mismatched channels.

problem Solving Schrödinger bridge problem with input and noise channel mismatch.
method Design of a Sinkhorn recursion with memory for nonlinear PDEs.
result Demonstrates solving control-affine Schrödinger bridge problem.

Extends diffusion-based Schrödinger bridge models to handle time-dependent potentials.

problem Approximating optimal transport dynamics between two boundary distributions with a twisted Brownian motion reference.
method Introduces Twisted Schrödinger Bridge Matching (TSBM) using the Iterative Markovian Fitting (IMF) paradigm, incorporating a gradient-dependent bridge-matching loss.
result Improves trajectory inference across high-dimensional settings, including crowd navigation and single-cell data.

Model trains passing events on a bridge using multilevel Gaussian process.

problem Represent aggregate train-passing events from a bridge monitoring system.
method Formulate a combined model with low-rank approximation hierarchical Gaussian process, incorporating domain expertise as constraints.
result Allow for simulation of previously unobserved train types.

BRIDGE improves decentralized learning resilience against Byzantine failures.

problem Decentralized learning in distributed systems is vulnerable to Byzantine failures.
method Introduces BRIDGE, a scalable Byzantine-resilient decentralized gradient descent algorithm.
result Proves algorithmic and statistical convergence guarantees for BRIDGE.

New framework bridges climate science and ML for easier climate model emulation.

problem High computational costs and mistrust of ML methods in climate models.
method Integrating climate science and machine learning perspectives to design easy-to-adopt emulators.
result Demonstrated reliability of emulators designed to address specific tasks.

We propose the Bayesian bridge estimator for regularized regression and classification. Two key mixture representations for the Bayesian bridge model are developed: (1) a scale mixture of normals with respect to an alpha-stable random variable; and (2) a mixture of Bartlett--Fejer kernels (or triangle densities) with r…

2011-09-11abs ↗pdf ↗

Differentiable optimization bridges arbitrary metrics to tree metrics.

problem Designing algorithms to convert arbitrary metrics to tree metrics with guarantees.
method DeltaZero framework, leveraging differentiable Gromov hyperbolicity.
result DeltaZero consistently achieves state-of-the-art distortion on synthetic and real-world datasets.

Paper bridges theory and algorithm for domain adaptation.

problem Domain adaptation from theory to algorithm gap.
method Extended domain adaptation theories, introduced Margin Disparity Discrepancy, and transformed into adversarial learning algorithm.
result Empirical studies show state-of-the-art accuracies on domain adaptation tasks.

We bridge statistical and worst-case approaches to experimental design for linear regression.

problem Designing efficient experiments for linear regression models with arbitrary responses.
method Propose a new experimental design framework for arbitrary response distributions, combining statistical and worst-case approaches.
result Develop efficient randomized design procedures achieving strong variance bounds for unbiased estimators using few responses.

Paper bridges ResNet and Feynman path integral for mathematical understanding.

problem Gradient vanishing issue in ResNet.
method Proves equivalence between ResNet and Feynman path integral, using partial differential equations.
result ResNet's advantage in gradient vanishing issue is mathematically explained.

Smooth Contextual Bandits bridge two previously studied extremes of non-differentiable and parametric-response bandits.

problem Nonparametric contextual bandits with Hölder smoothness.
method Developed a novel algorithm that optimally balances between non-differentiable and parametric-response bandits.
result Proved the algorithm achieves rate-optimal regret for all smoothness settings.

BOED improves SBI by optimizing experimental designs and inference functions.

problem Efficiently use experimental resources for better inference on complex models.
method Link mutual information bounds between SBI and BOED, optimizing both design and inference.
result BOED improves inference in real-world simulators in epidemiology and biology.

Study on knot diagrams showing bridge number can differ from crossing number.

problem Incompatibility between crossing number and bridge number for knot diagrams.
method Defined and compared various bridge number computations for knot diagrams, studied minimizing diagrams, and constructed families of minimal crossing diagrams.
result Found examples where bridge number differs from crossing number, and demonstrated this difference can grow infinitely.

A new approach to PCGML uses discriminative models to improve design control.

problem Fundamental tension between detailed training examples and return on investment.
method Discriminative models trained on positive and negative examples.
result Demonstrates new mode of control for learning-based generators.

The paper provides examples of keen weakly reducible bridge spheres for links in b-bridge position.

problem Characterizing and finding examples of keen weakly reducible bridge spheres.
method Analyzing bridge spheres and their properties in terms of compressing disks and width complex.
result Infinitely many examples of keen weakly reducible bridge spheres for links in b-bridge position.

Novel algorithms for entropic optimal transport from an optimisation perspective.

problem Solving the entropic-regularised optimal transport problem.
method Developed novel methods inspired by mirror descent, solving semi-dual problems or non-convex constrained problems over joint distributions.
result Non-asymptotic rates of convergence for the proposed methods under minimal assumptions.

Framework enhances AI explainability by aligning with human cognitive models.

problem Lack of explainability in AI models hinders trust and accountability.
method Integrates explainability techniques with Malle's five category model of behavior explanation.
result Demonstrates practical relevance in credit risk assessment and regulatory analysis.

Equivariant trisections for group actions on 4-manifolds are introduced and studied.

problem Understanding the equivariant topology of GG-manifolds and their quotients.
method Introducing GG-equivariant trisections and bridge trisections, and establishing their existence for GG-manifolds.
result Any GG-manifold XX admits a GG-equivariant trisection such that a GG-invariant surface S\mathcal{S} is in equivariant bridge trisection position.

Suppose a knot in a 33-manifold is in nn-bridge position. We consider a reduction of the knot along a bridge disk DD and show that the result is an (n1)(n-1)-bridge position if and only if there is a bridge disk EE such that (D,E)(D, E) is a cancelling pair. We apply this to an unknot KK, in nn-bridge position with re…

2016-06-23abs ↗pdf ↗

Adversarial training improves gradient interpretability, reducing misinterpretations.

problem Improving gradient interpretability in adversarially trained deep networks.
method Identified and demonstrated that adversarial training restricts gradients closer to the image manifold, making them more interpretable.
result Adversarial training leads to more meaningful loss gradients, aligning better with human perception.