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.

168,742 papers · 148 categories

Trend · papers per month

74148221295 · Jun 202019922001200920172026
48 results for Sobolev loss

Sobolev training helps neural nets fit function values and derivatives.

problem Training neural nets to match function values and derivatives accurately.
method Using Sobolev loss with gradient flow for overparameterized networks.
result Gradient flow from random initialization can fit any function and its derivatives.

This paper compares deeper and wider neural networks for optimal generalization error in Sobolev losses.

problem The dilemma of choosing between deeper or wider neural networks for optimal generalization error.
method Analytical investigations into the influence of sample points, parameters, and loss function regularity on neural network architecture.
result A higher number of parameters favors wider neural networks, while more sample points and greater loss function regularity favor deeper neural networks.

Proposes a new generalization bound for Bayesian deep nets without strict assumptions.

problem Lack of generalization bounds for Bayesian deep nets without strict assumptions.
method Exploits contractivity of Log-Sobolev inequalities to add a loss-gradient norm term to the generalization bound.
result Introduces a new generalization bound for Bayesian deep nets that avoids strict assumptions.

Optimal multiscale learning of linear operators

problem Statistical and computational limits of learning bounded linear operators between Sobolev spaces
method Reformulate as an infinite-dimensional matrix regression problem with heterogeneous multiscale structure
result Establish minimax rates and construct a finite-resolution blockwise least-squares estimator attaining these rates

The study proves conditions for nontrivial solutions on Riemannian manifolds.

problem Conditions for nontrivial solutions to the Dirac equation on Riemannian manifolds.
method Proves a necessary criterion using the Yamabe invariant and Sobolev constant.
result Sharp conditions on the sphere for nontrivial solutions.

Neural networks solve variational inequalities for optimal stopping problems.

problem Solving variational inequalities for optimal stopping problems in finance.
method Proposed neural network approach using loss functions directly incorporating variational inequality on whole domain.
result Existence and convergence of neural networks whose losses converge to zero.

We study some basic analytic questions related to differential operators on Lie manifolds, which are manifolds whose large scale geometry can be described by a a Lie algebra of vector fields on a compactification. We extend to Lie manifolds several classical results on Sobolev spaces, elliptic regularity, and mapping p…

2004-02-19abs ↗pdf ↗

The paper provides approximation guarantees for neural networks trained with gradient flow.

problem Approximating neural networks trained with gradient flow in continuous L2(Sd1)L_2(\mathbb{S}^{d-1})-norm.
method NTK argument for non-convex second but last layer, under-parametrized regime.
result Gradient flow convergence guarantees for neural networks under Sobolev smoothness assumptions.

Develop a comprehensive theory for regularized M-estimation in reproducing kernel Hilbert spaces.

problem Regularized M-estimation in reproducing kernel Hilbert spaces
method Existence and measurability of the estimator, sharp rates of convergence
result New rates for tensor product Sobolev spaces

Develops PAC-Bayesian framework for physics-informed machine learning.

problem Lack of statistical generalisation understanding for PIML models.
method PAC-Bayesian framework with multi-task perspective, incorporating physical structure.
result High-probability generalisation guarantees with unbounded losses.

Novel algorithm speeds up computation of Sobolev IPM for graph-based probability measures.

problem Efficient computation of Sobolev IPM for graph-based probability measures.
method Established relation between Sobolev norm and weighted LpL^p-norm, proposed novel regularization, leveraged graph structure.
result Proposed regularized Sobolev IPM provides closed-form expression for fast computation.

We propose a new Integral Probability Metric (IPM) between distributions: the Sobolev IPM. The Sobolev IPM compares the mean discrepancy of two distributions for functions (critic) restricted to a Sobolev ball defined with respect to a dominant measure μμ. We show that the Sobolev IPM compares two distributions in hig…

2017-11-14abs ↗pdf ↗

Explains optimal functional inequalities, focusing on Sobolev and fractional Sobolev.

problem Optimal functional inequalities and their stability.
method Compactness theorems, characterization of optimizers, and quantitative stability analysis.
result Characterization and stability of optimizers for Sobolev inequalities and their fractional generalizations.

Log Sobolev and Michael Simon inequalities for tensor fields on curved manifolds.

problem Establishing inequalities for tensor fields on curved manifolds.
method Applying the ABP method to symmetric tensor fields on manifolds with nonnegative sectional curvature.
result Log Sobolev and Michael Simon inequalities for tensor fields.

New PAC-Bayes bounds for unbounded losses using Cramér-Chernoff techniques.

problem Developing bounds for unbounded losses in PAC-Bayesian settings.
method Introducing a new PAC-Bayes oracle bound using Cramér-Chernoff bounds and controlling random variable tails.
result Our bounds generalize and improve upon previous results, providing more informative and potentially tighter bounds.

Two-sample tests using MMD control type I error and achieve optimal power.

problem Developing reliable nonparametric two-sample tests for small sample sizes.
method Maximum Mean Discrepancy (MMD) for constructing novel nonparametric tests, proving non-asymptotic error control and optimality.
result MMDAgg test controls type I error and achieves minimax rate over Sobolev balls, outperforming other tests.

In this paper we study the problem of deriving further Sobolev inequalities from a given Sobolev inequality. We use several different methods, including Bessel potentials and Riesz transforms. We apply the results to the Ricci flow to extend the author's results on the W1,2W^{1,2} Sobolev inequality along the Ricci flow …

2007-09-04abs ↗pdf ↗

Proves Sobolev inequality on manifolds with specific curvature properties.

problem Proving Sobolev inequality on manifolds with asymptotically nonnegative Bakry-Émery Ricci curvature.
method Density and Bakry-Émery Ricci curvature.
result Proves Sobolev inequality on manifolds with asymptotically nonnegative Bakry-Émery Ricci curvature.

Paper connects Fenchel-Willmore and Sobolev inequalities for submanifolds in curved spaces.

problem Developing inequalities for submanifolds in curved spaces.
method Connecting Fenchel-Willmore and logarithmic Sobolev inequalities for mean-convex submanifolds.
result Established extensions of Fenchel-Willmore inequality and derived new Sobolev-type inequalities.

New bounds close the score matching gap for diffusion models.

problem The difference between sample quality and score matching loss in diffusion models.
method Theoretical analysis of score matching gap, developing tighter bounds for KL divergence, reverse KL divergence, and Wasserstein distance.
result The quality of score approximation impacts closing the score matching gap for low noise scales.

Study shows how close functions are to optimal in Riemannian manifolds.

problem Understanding how close functions are to optimal in Riemannian manifolds.
method Analyzes quantitative stability of Sobolev inequalities on compact Riemannian manifolds.
result Functions that nearly saturate a critical Sobolev inequality are quantitatively close to extremal functions.

The paper examines stability of Sobolev inequalities on manifolds with Ricci curvature bounds.

problem Stability of Sobolev inequalities on Riemannian manifolds with Ricci curvature lower bounds.
method Generalized Lions' concentration compactness and rigidity results of Sobolev inequalities on singular spaces.
result Almost extremal functions are close to extremal functions on the round sphere and Euclidean Sobolev inequality.

Generalizes Sobolev IPM for graph-based measures using Orlicz geometric structure.

problem Limitation of Le et al. (2025) framework to LpL^p geometry.
method Generalizes Sobolev IPM through Orlicz geometric structure, employing convex functions to capture nuanced geometric relationships.
result GSI-M reduces to a simple univariate optimization problem, achieving remarkable computational efficiency.

Paper uses ABP method to prove logarithmic Sobolev inequalities on curved spaces.

problem Proving logarithmic Sobolev inequalities on manifolds with nonnegative curvature.
method Employing the ABP method developed by Brendle.
result Sharp L2L^2 and LpL^p logarithmic Sobolev inequalities established.

The paper proves inequalities on Finsler manifolds under Ricci curvature bounds.

problem Proving (p,q)(p, q)-Sobolev and Nash inequalities on Finsler metric measure manifolds.
method Global pp-Poincaré inequality, (p,q)(p, q)-Sobolev inequality, Nash inequality derivation.
result Established global optimal (p,q)(p, q)-Sobolev inequality with a sharp constant.

Completeness of surface metrics established for Sobolev spaces.

problem Ensuring completeness of reparametrization-invariant Sobolev metrics on surface spaces.
method Recasting completeness criteria for infinite-dimensional Riemannian manifolds and applying geometric estimates based on the Michael--Simon--Sobolev inequality.
result Established metric and geodesic completeness for specific Sobolev metrics on immersed surfaces, validating Mumford's conjecture.

In this article, we prove a Sobolev-like inequality for the Dirac operator on closed compact Riemannian spin manifolds with a nearly optimal Sobolev constant. As an application, we give a criterion for the existence of solutions to a nonlinear equation with critical Sobolev exponent involving the Dirac operator. We fin…

2008-04-07abs ↗pdf ↗

Study on completeness of Sobolev metrics on manifold-valued curves.

problem Completeness of Sobolev metrics on spaces of manifold-valued curves.
method Analysis of reparametrization invariant Sobolev metrics of order n2n\ge 2.
result Sobolev immersions are metrically and geodesically complete for several important cases of metrics.

Sharp Sobolev inequalities proved on manifolds with non-negative Ricci curvature.

problem Proving sharp Sobolev inequalities on noncompact Riemannian manifolds with non-negative Ricci curvature.
method Using Optimal Mass Transportation with quadratic distance cost.
result Sharp LpL^p-Sobolev and LpL^p-logarithmic Sobolev inequalities established for p>1p>1 and p=1p=1.

Ancient Ricci flows with bounded Nash entropy have uniform Sobolev inequalities.

problem Bounding Nash entropy in ancient Ricci flows.
method Uniformly bounded Nash entropy implies uniform bounds on the ν-functional, leading to uniform logarithmic and Sobolev inequalities.
result Uniform logarithmic and Sobolev inequalities on ancient Ricci flows with bounded Nash entropy.

Proves new Sobolev inequalities for submanifolds in manifolds with nonnegative intermediate Ricci curvature.

problem Proving Sobolev inequalities for submanifolds in manifolds with nonnegative intermediate Ricci curvature.
method Using the Alexandrov-Bakelman-Pucci method to prove Michael-Simon type inequalities.
result Extends existing inequalities to the kk-Ricci curvature setting and provides isoperimetric inequalities.

Frank and Lieb gave a new, rearrangement-free, proof of the sharp Hardy-Littlewood-Sobolev inequalities by exploiting their conformal covariance. Using this they gave new proofs of sharp Sobolev inequalities for the embeddings Wk,2(Rn)L2nn2k(Rn)W^{k,2}(\mathbb{R}^n)\hookrightarrow L^{\frac{2n}{n-2k}}(\mathbb{R}^n). We show that their …

2019-10-31abs ↗pdf ↗

New Sobolev inequality found for mean convex spacelike submanifolds in Minkowski space.

problem Finding a Sobolev inequality for mean convex spacelike submanifolds in Minkowski space.
method Applying the ABP estimate method to spacelike submanifolds in Rn,1\mathbb R^{n,1}.
result Obtained a Sobolev inequality without a mean curvature term for mean convex hypersurfaces.