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.

168,695 papers · 148 categories

Trend · papers per month

122243365486 · May 202619922001200920172026
48 results for across field

Paper proposes a method to compare vector fields across surfaces, useful for analyzing brain folding patterns.

problem Comparing vector fields across surfaces of different geometries is challenging.
method The paper introduces a framework to transport vector fields onto a common space using differential geometry.
result The proposed framework enables the computation of statistics on vector fields, demonstrating its effectiveness in analyzing brain folding patterns.

The study examines dataset usage patterns in machine learning research.

problem Lack of attention to dataset dynamics in machine learning research.
method Analysis of dataset usage patterns across machine learning subcommunities and time periods (2015-2020).
result Increasing concentration on fewer and fewer datasets, significant adoption from other tasks, and concentration across the field on datasets introduced by elite institutions.

NN-Turb generates turbulent velocity statistics using neural networks.

problem Creating a 1D field with turbulent velocity statistics.
method Fully-convolutional neural network (NN-Turb) to generate the field.
result NN-Turb generates a 1D field that satisfies Kolmogorov's 2/3 and 4/5 laws, exhibiting intermittency.

We consider branes NN in a Schwarzschild-AdS(n+2)\text{AdS}_{(n+2)} bulk, where the stress energy tensor is dominated by the energy density of a scalar fields map $\f:N\ra \mc S$ with potential VV, where $\mc S$ is a semi-Riemannian moduli space. By transforming the field equation appropriately, we get an equivalent field …

2004-09-13abs ↗pdf ↗

Estimates binary labels from dependent data using Markov Random Fields.

problem Statistical estimation from dependent data across spatial, temporal, and social domains.
method Modeling dependencies as Markov Random Fields and providing efficient estimation algorithms.
result Statistically efficient estimation rates for Ising models from a single sample.

G-FuNK learns solutions for nonlinear PDEs on multiple domains and parameters.

problem Predicting time-dependent dynamics of complex systems governed by nonlinear PDEs with varying parameters and domains.
method Graph Fourier Neural Kernels combining domain-adapted and transferable components for non-diffusive and diffusive terms.
result G-FuNK achieves low relative errors on unseen domains and fiber fields, significantly accelerating predictions.

TSCI improves causal inference in dynamical systems using vector fields.

problem Challenges in causal discovery with time series data in dynamical systems.
method TSCI method using vector fields to check for synchronization between learned dynamics.
result TSCI outperforms traditional methods like CCM and its generalizations.

GEM learns a manifold for cross-modal data, capturing structure without modality dependence.

problem Modality-specific neural models limit flexibility and custom architecture.
method Casts learning as manifold inference, enforcing coverage, linearity, and isometry.
result GEM learns latent structure across image, shape, audio, and cross-modal domains.

DRFormer uses dynamic tokenization and multi-scale transformer to forecast long time series.

problem Forecasting long-term time series data across diverse scales.
method Dynamic tokenizer, multi-scale transformer, dynamic sparse learning, rotary position encoding.
result DRFormer outperforms existing methods in forecasting accuracy.

Paper identifies a shared toolkit of strategies for risk management across fields.

problem Uncertainty and risk management in various fields.
method Systematic identification and categorization of 110 strategies.
result RDOT: Risk-reducing Design and Operations Toolkit provides versatile responses to uncertainty.

Study on black hole interiors with matter fields, showing oscillation condition impacts blow-up.

problem Examining Strong Cosmic Censorship in the presence of matter fields.
method Einstein equations coupled with charged/massive scalar fields, spherically symmetric data, relaxation rate analysis.
result Oscillation condition on event horizon determines whether matter fields blow up or not.

Field theory explains optimal scaling in ResNets for signal propagation.

problem Understanding optimal scaling parameter for ResNet performance.
method Finite-size field theory for ResNets to study signal propagation and scaling.
result Analytical expressions for optimal scaling parameter, independent of other hyperparameters.

Transformers approximate mean-field dynamics of indistinguishable particles.

problem Approximating the dynamics of indistinguishable particles in complex systems.
method Using transformers to model the mean-field dynamics of interacting particle systems.
result Theoretical bounds on the distance between true and transformer-obtained mean-field dynamics.

Residual networks with depthwise hyperparameter scaling transfer optimal hyperparameters across width and depth.

problem The challenge of hyperparameter tuning in deep learning, especially for large models.
method Combining μμP parameterization with residual networks having a residual branch scale of 1/extdepth1/\sqrt{ ext{depth}}.
result Optimal hyperparameters transfer across width and depth in residual networks trained with this parameterization.

Optimizes intervention design for causal discovery using integer programming.

problem Identifying causal structures from observational data due to confounding variables.
method Uses integer programming to design minimal intervention sets for causal structure identifiability.
result Provides exact and modular solutions adaptable to various experimental settings and constraints.

New method estimates and samples high-dimensional probability distributions avoiding optimization and approximation curse.

problem Estimating high-dimensional probability distributions from data samples.
method Hierarchic probability flow from coarse to fine scales, defined by conditional probabilities across scales.
result Sampling hierarchic models avoids critical slowing down at phase transitions and generates turbulence and dark matter images.

Develops scalable model for learning velocity fields in complex traffic scenarios.

problem Learning heterogeneous and dynamic velocity fields in complex traffic scenarios.
method Nonparametric Bayesian modeling with hierarchical Dirichlet process and infinite hidden Markov model, Gaussian process prior, and scalable approximate inference.
result Demonstrates effective scalability and applicability to real-world traffic data.

The paper studies how neural networks evolve representations, finding a unique fixed point for nonlinear activations.

problem Understanding how neural networks transform input data across layers.
method Theoretical framework for the evolution of the kernel sequence, using mean-field regime and Hermite polynomials.
result For nonlinear activations, the kernel sequence converges globally to a unique fixed point.

This paper designs sensor arrays for estimating unsteady flows efficiently.

problem Estimating high-dimensional unsteady flow fields with limited sensor placement.
method Combines data-driven modeling, Kalman Filter design, and sparsification for sensor selection.
result Proposed sensor arrays are highly effective for flow-field estimation across various conditions.

Brain decoding is a data analysis paradigm for neuroimaging experiments that is based on predicting the stimulus presented to the subject from the concurrent brain activity. In order to make inference at the group level, a straightforward but sometimes unsuccessful approach is to train a classifier on the trials of a g…

2014-04-16abs ↗pdf ↗

Linear regression is an important tool across many fields that work with sensitive human-sourced data. Significant prior work has focused on producing differentially private point estimates, which provide a privacy guarantee to individuals while still allowing modelers to draw insights from data by estimating regressio…

2019-10-29abs ↗pdf ↗

Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form. Therefore, multiple approaches have emerged to construct vectorial representations of structured data, from kernel and distance approaches to recurrent, recursive, and convolutional neural networks. Re…

2019-05-15abs ↗pdf ↗

In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time. We show that we are able to perform exact and efficient inference on a densely connected spatio-temporal graph by capitalizing on recent advances on deep Gaussian Conditional …

2018-07-03abs ↗pdf ↗

Proposes a topological framework to study modular invariants and related concepts.

problem Exploring modular invariants and related concepts in topological quantum field theory.
method Topological paradigm in alterfold topological quantum field theory.
result Establishes a novel integral identity for modular invariance across multiple Morita contexts.

Develops a dynamic mean field theory for reinforcement learning.

problem Finite state and action Bayesian reinforcement learning in large state spaces.
method Analogies with statistical physics, interpreting probabilities as couplings and values as spins, solving mean field equations.
result State-action values are statistically independent in the asymptotic state space limit, with exact or approximate equations for computation.

The cohomology theory for financial market can allow us to deform Kolmogorov space of time series data over time period with the explicit definition of eight market states in grand unified theory. The anti-de Sitter space induced from a coupling behavior field among traders in case of a financial market crash acts like…

2016-06-09abs ↗pdf ↗