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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “ReQU”

Estimation of Non-Crossing Quantile Regression Process with Deep ReQU Neural Networksstat.ML

Deep neural networks enforce non-crossing quantile regression curves.

problem Estimating quantile regression curves without crossing.

method Penalized deep ReQU neural networks with a non-crossing penalty.

result Established non-asymptotic risk and error bounds for the estimated QRP.

quantile regression deep learning non-crossing rectifier quadratic unit neural networks

2022-07-21abs ↗pdf ↗

Sampling Complexity of Deep Approximation Spacescs.LG

New study shows exponential sample growth for ReQU neural networks.

problem Computing neural network approximations from samples is challenging.

method Information-based complexity tools.

result Functions can be approximated by ReQU neural networks at arbitrary rates but require exponentially growing samples.

neural networks approximation sample complexity ReLU ReQU

2023-12-20abs ↗pdf ↗

Semi-Supervised Deep Sobolev Regression: Estimation and Variable Selection by ReQU Neural Networkstat.ML

SDORE uses neural networks to estimate regression functions and their gradients, even with limited labeled data.

problem Nonparametric estimation of regression functions and their gradients.

method Semi-supervised deep ReQU neural networks with gradient norm regularization.

result Achieves minimax optimal convergence rates in

L^{2}

-norm and plug-in gradient estimator convergence.

Semi-supervised learning Deep ReQU neural networks Gradient estimation Nonparametric regression Minimax optimality

2024-01-09abs ↗pdf ↗

Boundary-Adapted PINNs for Elliptic Dirichlet Problems:

H^2(Ω)

A Priori Error Bounds with Application to Mean Escape Time Computationmath.NA

New PINNs method improves accuracy in computing Mean Escape Time from bounded domains.

problem Computing Mean Escape Time from bounded domains with high accuracy.

method Boundary-adapted Physics-Informed Neural Networks (PINNs) with exact Dirichlet boundary enforcement.

result Derivation of

H^2(Ω)

a priori error bounds for PINNs with normalized distance approximations.

PINNs Mean Escape Time Dirichlet BVPs Distance Approximation H2 error bounds

2026-07-21abs ↗pdf ↗

Regularity of Solutions to Beckmann's Parametric Optimal Transportmath.AP

Develops regularity theory for Beckmann's optimal transport problem.

problem Minimizing total squared flux in continuous transport from source to target.

method Unconstrained Lagrangian formulation, variational first order optimality conditions, Schauder estimates.

result Exact Hölder regularity of potential, flux, and flow generating on bounded, regular domains.

optimal transport Beckmann's problem regularity theory Hölder continuity Schauder estimates

2026-03-20abs ↗pdf ↗

A Quantitative Approximation Framework for Flow Distillation in Diffusion Modelsstat.ML

Develops a framework for distilling flow models from few steps.

problem Improving few-step sampling in diffusion models for better performance.

method Local approximation errors and dynamical amplification controlled through analytical tractability.

result Deep residual compositions efficiently approximate long-horizon transport with controlled global error.

diffusion models flow distillation stability amplification score approximation time-integrated Jacobian

2026-06-02abs ↗pdf ↗