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.

169,051 papers · 148 categories

Trend · papers per month

61122183244 · Jun 202019922001200920182026
48 results for Non-Local Partial Convolutions

This paper improves image super-resolution by integrating cross-scale non-local attention.

problem Improving image super-resolution by leveraging long-range and cross-scale feature correlations.
method Proposes a Cross-Scale Non-Local (CS-NL) attention module integrated into a recurrent neural network.
result Significantly improved performance on SISR benchmarks.

Study of Dirac equation with non-local nonlinearity on spheres.

problem Conformally invariant Dirac equation with non-local nonlinearity.
method Investigation of compactness, bubbling, and energy quantization of energy functional; characterization of ground state solutions; proof of Aubin-type inequality and Brezis-Nirenberg type result.
result Existence of solutions to the conformal Einstein-Dirac problem in dimension 4.

Deep learning model predicts traffic flows across entire network for multiple steps ahead.

problem Accurately forecasting future traffic flows across all network links.
method Spatial-Temporal Sequence to Sequence (STSeq2Seq) model combining seq2seq and graph convolution.
result STSeq2Seq achieves state-of-the-art performance in traffic forecasting.

We introduce a notion of non-local almost minimal boundaries similar to that introduced by Almgren in geometric measure theory. Extending methods developed recently for non-local minimal surfaces we prove that flat non-local almost minimal boundaries are smooth. This can be viewed as a non-local version of the Almgren-…

2010-03-12abs ↗pdf ↗

Two local learning rules are investigated to avoid weight transport in neural networks.

problem Local learning rules that avoid weight transport are unstable and require tuning.
method Investigated two non-local learning rules and a more robust local rule.
result Non-local learning rules match state-of-the-art performance and operate effectively in noisy updates.

The paper explains implicit regularization in hierarchical tensor factorization and deep CNNs.

problem Understanding implicit regularization in complex neural network architectures.
method Theoretical analysis using dynamical systems to overcome challenges in hierarchy.
result Established implicit regularization towards low hierarchical tensor rank, equivalent to locality in CNNs.

Paper proposes an active learning method for surgical workflow recognition using long-range temporal dependency.

problem Challenges in automatic surgical workflow recognition due to lack of large-scale labelled datasets.
method NL-RCNet with non-local block for capturing long-range temporal dependency and intra-clip dependency score for selection.
result Our approach outperforms state-of-the-art methods by selecting only 50% of samples for training.

Study the boundary operator property on simplicial complexes, proving essential properties for Hodge theory.

problem Characterize the boundary operator property =0\partial\partial = 0 on simplicial complexes.
method Characterization in 2\ell^2 terms of recurrence of links, defining relative cohomology, and proving harmonic eigenforms.
result Essential properties for Hodge theory, including weak decomposition and existence of harmonic eigenforms.

New kernels capture both local and non-local interactions efficiently.

problem Designing kernels that capture both local and non-local interactions while remaining computationally tractable.
method Spectral truncation kernels based on CC^*-algebra.
result Spectral truncation kernels induce interactions across the data function domain and reduce computational cost.

It is argued that the enlargement of the gauge group found in non-commutative gauge theory is more fundamentally thought of as a consequence of the non-locality of the construction and that it was already encountered in an earlier discussion of a non-local gauge theory.

2009-02-24abs ↗pdf ↗

Deep learning systems have become ubiquitous in many aspects of our lives. Unfortunately, it has been shown that such systems are vulnerable to adversarial attacks, making them prone to potential unlawful uses. Designing deep neural networks that are robust to adversarial attacks is a fundamental step in making such sy…

2018-05-31abs ↗pdf ↗

Study shows that dimension of Dolbeault harmonic forms is not always equal to B- on certain 4-manifolds.

problem Determining the dimension of Dolbeault harmonic (1,1)-forms on almost Hermitian 4-manifolds.
method Provided examples and proved non-equality of h1,1h^{1,1}_{\overline\partial} and bb^- for certain structures.
result Dimension of Dolbeault harmonic (1,1)-forms is not always equal to B- on almost Hermitian 4-manifolds.

A new GCN variant tackles large eigengaps in dense graphs and hypergraphs.

problem Large eigengaps in dense graphs and hypergraphs hinder popular GCN architectures.
method Uses pseudoinverse of the Laplacian and low-rank approximation for efficient computation.
result Improves runtime and accuracy in various experiments with real-world datasets.

Fractional porous media equations yield q-Gaussian solutions for stock price returns.

problem Modeling stock price returns using fractional porous media equations.
method Analyzed three types of fractional extensions of the porous media equation.
result Local and non-local fractional extensions fit S&P 500 data better than classical models.

We study the space of generalized translation invariant valuations on a finite-dimensional vector space and construct a partial convolution which extends the convolution of smooth translation invariant valuations. Our main theorem is that McMullen's polytope algebra is a subalgebra of the (partial) convolution algebra …

2014-06-17abs ↗pdf ↗

We give necessary conditions for certain real analytic tube generic submanifolds in C^n to be locally algebraizable. As an application, we exhibit families of real analytic non locally algebraizable tube generic submanifolds in C^n. During the proof, we show that the local CR automorphism group of a minimal, finitely n…

2004-04-13abs ↗pdf ↗

The ability to witness non-local correlations lies at the core of foundational aspects of quantum mechanics and its application in the processing of information. Commonly, this is achieved via the violation of Bell inequalities. Unfortunately, however, their systematic derivation quickly becomes unfeasible as the scena…

2018-08-21abs ↗pdf ↗

In this paper, we study global existence and blow up properties to LpL^p norm preserving non-local heat flows. We first study two kinds of LpL^p norm preserving non-local flows and prove that these flows have the global solutions. Finally, we give a example to show that one kind of this heat flow may blow up in $L^{\in…

2009-10-26abs ↗pdf ↗

NESTA accelerates neural networks by compressing Hamming weights.

problem Efficiently computing convolution layers in deep neural networks.
method NESTA reformats convolutions into 3imes33 imes 3 batches and uses Hamming Weight Compressors to process each batch, approximating partial sums and adding residuals.
result Significantly speeds up convolution computations with reduced energy consumption.

NL-LinkNet improves road extraction from satellite images with fewer parameters and faster training.

problem Efficiently extracting roads from high-resolution satellite images.
method Integrates non-local blocks into LinkNet for better feature context.
result NL-LinkNet outperformed state-of-the-art models in the DeepGlobe Challenge.

MFNs parameterize non-local interactions through matrix equivariant functions, improving graph neural network performance.

problem Challenges in modeling non-local interactions in graphs, such as oversmoothing and oversquashing.
method Matrix Function Neural Networks (MFNs) using resolvent expansions for non-local interactions.
result Achieves state-of-the-art performance in graph benchmarks and captures intricate non-local interactions.

Low-rank signal modeling has been widely leveraged to capture non-local correlation in image processing applications. We propose a new method that employs low-rank tensor factor analysis for tensors generated by grouped image patches. The low-rank tensors are fed into the alternative direction multiplier method (ADMM) …

2018-03-19abs ↗pdf ↗

Weather2vec learns representations to adjust for non-local confounding in air pollution studies.

problem Non-local confounding in evaluating environmental policies and climate events on health outcomes.
method weather2vec framework using balancing scores to learn representations of non-local information.
result The framework effectively adjusts for confounding in air pollution studies.

Study non-local isoperimetric energies on spheres using a Riemannian autocorrelation function.

problem Analyse non-local isoperimetric energies on spheres.
method Introduce Riemannian autocorrelation function and use it to reformulate and compute the energies.
result Show that the non-local isoperimetric energies can be reformulated and computed using the Riemannian autocorrelation function.

Scientific discovery is limited by hypothesis redundancy, and hybrid methods can exploit non-local exploration.

problem Limitation of scientific discovery due to hypothesis redundancy.
method Hybrid discovery systems combining structured local search with LLM-generated non-local proposals.
result Hybrid methods can exploit non-local exploration when three geometric conditions co-occur.

In this paper, we consider a kind of area preserving non-local flow for convex curves in the plane. We show that the flow exists globally, the length of evolving curve is non-increasing, and the curve converges to a circle in C^{\infty} sense as time goes into infinity.

2009-07-09abs ↗pdf ↗

FBSJNN solves PIDEs and FBSDEJs with deep learning, offering theoretical and numerical efficiency.

problem Solving Partial Integro-Differential Equations and Forward-Backward Stochastic Differential Equations with Jumps.
method FBSJNN framework using a single neural network for both solution approximation and non-local integral.
result FBSJNN achieves numerical solutions with a relative error of 10310^{-3}, demonstrating efficiency.

Recently, it was demonstrated in [CS2012,CS2013] that the robustness of the classical Non-Local Means (NLM) algorithm [BCM2005] can be improved by incorporating p(0<p2)\ell^p (0 < p \leq 2) regression into the NLM framework. This general optimization framework, called Non-Local Patch Regression (NLPR), contains NLM as a spe…

2013-03-02abs ↗pdf ↗

New boundary conditions solve Cauchy problem for Dirac operators on spacetimes.

problem Understanding non-local boundary conditions for Dirac operators on spacetimes.
method Define and analyze a class of Lorentzian boundary conditions that are local in time and non-local in spatial directions.
result Well-posed Cauchy problem for the Dirac operator is established under these conditions.

Study finds non-uniqueness in sphere metrics with constant fractional curvature.

problem Non-uniqueness of metrics with constant positive fractional curvature on spheres.
method Bifurcation techniques applied to non-local equations with critical non-linearity.
result Non-uniqueness results for complete metrics on SnSkS^n \setminus S^k.

We study conformal metrics on R3R^3, i.e., metrics of the form gu=e2udx2g_u=e^{2u}|dx|^2, which have constant QQ-curvature and finite volume. This is equivalent to studying the non-local equation (Δ)32u=2e3u (-Δ)^\frac32 u = 2 e^{3u} in R3R^3 V:=R3e3udx<,V:=\int_{\mathbb{R}^3}e^{3u}dx<\infty, where VV is the volume of gug_u. Adapting a te…

2013-09-17abs ↗pdf ↗