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.

168,657 papers · 148 categories

Trend · papers per month

121242363484 · Jun 202019922001200920172026
48 results for smooth approximation

Smooth activations enable optimal error rates in neural networks for Sobolev function classes.

problem Achieving optimal approximation and estimation error rates for neural networks in Sobolev function classes.
method Study of neural networks with smooth activations, proving optimal rates via approximation and statistical properties.
result Constant-depth networks with smooth activations achieve optimal rates of approximation and estimation, demonstrating smoothness adaptivity.

Deep ReLU networks can approximate and learn smooth functions efficiently.

problem Efficiently approximating and learning smooth functions using deep ReLU neural networks.
method Extending recent results to anisotropic and mixed smooth function classes, establishing approximation rates.
result Deep ReLU networks achieve minimax optimal rates up to logarithmic factors for various smooth function classes.

Smooth approximation of integral cycles mod 2 in Riemannian manifolds.

problem Approximating mod 2 integral cycles by smooth submanifolds.
method Approximation of mod 2 integral cycles by smooth submanifolds with controlled singularities.
result Every mod 2 integral cycle can be approximated by a smooth submanifold with a controlled singular set.

Deep neural networks with piecewise-polynomial activations can approximate smooth functions and their derivatives.

problem Approximating smooth functions and their derivatives with neural networks.
method Derives the depth, width, and sparsity required for approximation in Hölder norms.
result Deep neural networks with bounded weights can approximate Hölder smooth functions and their derivatives.

We study local and global approximations of smooth nets of curvature lines and smooth conjugate nets by respective discrete nets (circular nets and planar quadrilateral nets) with infinitesimal quads. It is shown that choosing the points of discrete nets on the smooth surface one can obtain second-order approximation g…

2007-06-21abs ↗pdf ↗

Transformers struggle to approximate smooth functions, relying on piecewise constant approximations.

problem Understanding the expressivity of Transformers for function approximation.
method Theoretical analysis and experimental validation of Transformer's ability to approximate smooth functions.
result Transformers cannot reliably approximate smooth functions, relying on piecewise constant approximations.

Deep, wide ConvResNets can approximate functions and their smoothness.

problem Function approximation and smoothness in deep networks.
method Analyzing ConvResNets, proving their ability to approximate functions and their smoothness.
result Large ConvResNets can approximate functions and exhibit sufficient first-order smoothness.

Smoothing splines provide a powerful and flexible means for nonparametric estimation and inference. With a cubic time complexity, fitting smoothing spline models to large data is computationally prohibitive. In this paper, we use the theoretical optimal eigenspace to derive a low rank approximation of the smoothing spl…

2019-11-23abs ↗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.

Smoothed SGD improves quantile estimation without crossing curves.

problem Estimating quantiles without crossing estimated curves.
method Smoothed SGD algorithm with Bahadur representation and Gaussian approximation.
result Smoothed SGD provides non-asymptotic tail probability bounds and a Gaussian approximation for quantile estimates.

Stochastic approximation proves asymptotic normality for non-smooth problems.

problem Solving non-smooth stochastic approximation problems.
method Stochastic approximation algorithms for solving smooth equations, extended to non-smooth problems.
result Asymptotic normality and optimality in non-smooth stochastic approximation is proven.

Develops wavelet-based neural network approximation theory.

problem Analyzing neural network approximation capabilities over various activation functions.
method Wavelet frame theory on spaces of homogeneous type, sufficient conditions for approximation, error estimates.
result Derives sufficient conditions for neural networks to approximate any functions in a given space, including non-smooth activations.

This work improves polynomial approximations for functions with asymmetric behavior.

problem Efficiently approximating functions with asymmetric behavior, especially those growing unbounded on one side.
method Introduces weighted deep polynomial approximants that combine learnable deep polynomials with one-sided weights.
result Weighted deep polynomial approximants outperform existing methods in approximating functions with asymmetric behavior.

Quasispheres can be approximated by smooth spheres.

problem Characterizing quasispheres using geometric conditions.
method Proving every quasisphere is a limit of smooth spheres and providing necessary and sufficient conditions for uniform quasispheres.
result Every quasisphere can be approximated by uniform quasispheres that satisfy specific geometric conditions.

In this paper we aim for a generalisation of the Steenrod Approximation Theorem from, concerning a smoothing procedure for sections in smooth locally trivial bundles. The generalisation is that we consider locally trivial smooth bundles with a possibly infinite-dimensional typical fibre. The main result states that a c…

2006-10-07abs ↗pdf ↗

We show a Whitney Approximation Theorem for a continuous map from a manifold to a smooth CW complex. This enables us to show that a topological CW complex is homotopy equivalent to a smooth CW complex in a category of topological spaces. It is also shown that, for any open covering of a smooth CW complex, there exists …

2020-01-09abs ↗pdf ↗

Smooth flows with surgery approximate weak mean curvature flows with spherical and neck-pinch singularities.

problem Approximating weak mean curvature flows with singularities using smooth flows.
method Combining Choi-Haslhofer-Hershkovits and Choi-Haslhofer-Hershkovits-White work on canonical neighbourhoods and barriers to flows with surgery.
result Smooth flows with surgery can approximate weak mean curvature flows with spherical and neck-pinch singularities.

We use geometric measure theory to introduce the notion of asymptotic cones associated with a singular subspace of a Riemannian manifold. This extends the classical notion of asymptotic directions usually defined on smooth submanifolds. We get a simple expression of these cones for polyhedra in E^3, as well as converge…

2015-01-12abs ↗pdf ↗

Quantifies polynomial approximation rates for smooth functions under various distributions.

problem Approximating smooth functions with polynomials under different distributional constraints.
method Develops a quantitative analogue of Carleman's theorem using complex analysis.
result Establishes superexponential rates of approximation for certain function classes over general distributions.

Smooths metrics with nonnegative scalar curvature near singular sets.

problem Approximating metrics with nonnegative scalar curvature near singularities.
method Ricci-DeTurck flow to approximate metrics.
result Approximated metrics converge to the original metric in CC^\infty away from the singular set.

New RBF networks can approximate any continuous function.

problem Approximating any continuous function on a compact subset.
method Replacing smoothing factors with shifts in RBF networks and proving approximation under certain conditions.
result RBF networks can approximate any continuous function on any compact subset.

We consider the smoothing probabilities of hidden Markov model (HMM). We show that under fairly general conditions for HMM, the exponential forgetting still holds, and the smoothing probabilities can be well approximated with the ones of double sided HMM. This makes it possible to use ergodic theorems. As an applicatio…

2009-10-24abs ↗pdf ↗

If f is a smooth function on a Hodge manifold, we construct a canonical sequence of real algebraic functions that converge to f in the smooth topology. The definition of of the approximants is inspired by Berezin-Toeplitz quantization. The proof follows quickly from known results of Fine, Liu and Ma.

2010-10-17abs ↗pdf ↗

Smooth approximations near singularities of constant mean curvature surfaces are found.

problem Finding smooth approximations for constant mean curvature surfaces near singular points.
method Proving the existence of sequences of smooth CMC hypersurfaces converging to a given one in a ball centered at the singularity.
result Smooth approximations exist in a ball centered at the singularity of a CMC hypersurface.

A new federated learning algorithm improves on existing methods by exploiting data smoothness.

problem Federated learning optimization with smooth loss functions.
method Federated Low Rank Gradient Descent (FedLRGD) algorithm.
result FedLRGD outperforms Federated Averaging (FedAve) in federated oracle complexity under certain conditions.

Deep neural networks with specific parameter sets can approximate smooth functions efficiently.

problem Approximating smooth functions with deep neural networks.
method Deep neural networks with ReLU activation and specific parameter sets {0,±12,±1,2}\{0,\pm \frac{1}{2}, \pm 1, 2\} are used to approximate CβC_β-smooth functions.
result The constructed networks can approximate CβC_β-smooth functions with parameters {0,±12,±1,2}\{0,\pm \frac{1}{2}, \pm 1, 2\} efficiently, achieving the same convergence rate as sparse networks with parameters in [1,1][-1,1].