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

91182273364 · Jun 202019922001200920172026
48 results for singular dimension descent

Extends positive mass theorem to arbitrary dimensions using a new inductive scheme.

problem Overcoming singularities in the Schoen-Yau proof for arbitrary dimensions.
method Inductive scheme combining shielding principle, conformal blow-up, and Cheeger-Naber bound.
result Proof of positive mass theorem in arbitrary dimensions.

Prove Riemannian positive mass theorem for asymptotically flat metrics with low-codimension singularities.

problem Prove Riemannian positive mass theorem for asymptotically flat metrics with low-codimension singularities.
method Prove Riemannian positive mass theorem for asymptotically flat metrics with low-codimension singularities.
result Prove Riemannian positive mass theorem for asymptotically flat metrics with low-codimension singularities.

Stochastic gradient descent regularizes least squares problems by smoothing large singular values.

problem Regularization of least squares problems using stochastic gradient descent.
method Analysis of stochastic gradient descent applied to least squares problems, showing a regularization effect.
result Stochastic gradient descent leads to a quick regularization effect, smoothing large singular values.

Gradient descent recovers principal components of overparametrized asymmetric matrices without explicit regularization.

problem Asymmetric matrix factorization under overparametrization with minimal rank assumptions.
method Vanilla gradient descent with small random initialization and proper early stopping.
result Gradient descent produces the best low-rank approximation without explicit regularization.

In this paper we will discuss how one may be able to use mean curvature flow to tackle some of the central problems in topology in 4-dimensions. We will be concerned with smooth closed 4-manifolds that can be smoothly embedded as a hypersurface in R^5. We begin with explaining why all closed smooth homotopy spheres can…

2012-08-29abs ↗pdf ↗

New method for analyzing learning dynamics in singular models.

problem Challenges in analyzing learning of singular models with no one-to-one parameter space.
method Relative reparameterization technique to extract regular sub-models.
result Demonstrated differences in convergence behavior due to algorithmic and intrinsic aspects.

Perimeter minimizers in curved spaces have a singular set no more than 5 dimensions.

problem Understanding the structure of minimizers in spaces with bounded Ricci curvature.
method Analysis of non-collapsed Ricci limit spaces with two-sided curvature bounds.
result The Hausdorff dimension of the singular set is at most \(N-5\).

PrecGD restores linear convergence in over-parameterized nonconvex matrix factorization.

problem Slow convergence of local search algorithms in over-parameterized nonconvex matrix factorization.
method Preconditioned Gradient Descent (PrecGD) with an inexpensive 2\ell_2 regularization.
result PrecGD restores linear convergence rate even in the over-parameterized case.

Regression models can interpolate noisy data and still perform well, contrary to the bias-variance tradeoff.

problem Understanding why overparametrized models can generalize well despite the bias-variance tradeoff.
method Analysis of minimum norm solutions and ridge regression, focusing on the smallest singular value of the regression matrix.
result Testing error exhibits double descent behavior as model order increases, contrary to the classical bias-variance tradeoff.

This paper explains double descent in linear neural networks, identifying new factors.

problem Understanding double descent in linear neural networks.
method Gradient flow derivation and necessary conditions for double descent.
result Singular values of input-output covariance matrix are important for double descent in two-layer models.

Sharp bound on singular set dimension for specific geometric problems.

problem Hausdorff dimension of singular set in free boundary problems.
method Analysis of noncollapsed limits of manifolds with Ricci curvature bounds.
result Dimension bound of singular set is n5n-5.

Constructs Kahler-Einstein metrics near isolated log canonical singularities.

problem Constructing metrics near singularities in complex geometry.
method Constructs Kahler-Einstein metrics with negative scalar curvature near isolated log canonical singularities.
result Metrics are complete near the singularity if the underlying space has complex dimension 2 or if the singularity is smoothable.

Riemannian gradient descent escapes some spurious critical points on low-rank matrix manifold.

problem Spurious critical points on the boundary of low-rank matrix manifold.
method Riemannian gradient descent with dynamical low-rank approximation and rescaled gradient flow.
result Riemannian gradient descent escapes some spurious critical points on the boundary of the manifold.

Extends results on smoothability of singular Fano and Calabi-Yau varieties.

problem Smoothability of singular Fano and Calabi-Yau varieties under terminal singularities.
method Generalizes deformation theory results for Calabi-Yau and Fano threefolds to higher dimensions, using higher Du Bois and rational singularities.
result Identifies a class of singularities for which smoothing results hold, including generalized Fano and Calabi-Yau varieties.

New black hole solutions with positive and negative masses in 4 and 5 dimensions.

problem Constructing static vacuum black hole solutions with signed masses.
method Axisymmetric and bi-axisymmetric solutions in 4 and 5 dimensions, using Weyl-Papapetrou coordinates.
result Signed mass black holes can be superposed, with specific topologies in 5 dimensions.

Proves boundedness of log Fano cone singularities with bounded local volumes.

problem Understanding the boundedness of log Fano cone singularities.
method Analyzes K-semistable log Fano cone singularities with bounded volumes.
result The set of local volumes of klt singularities has zero as the only accumulation point.

A new method for Bayesian inference in high dimensions using projected Stein variational gradient descent.

problem Bayesian inference challenges in high-dimensional data.
method Adapting Stein variational gradient descent to exploit intrinsic low dimensionality of data.
result pSVGD is more accurate and efficient than SVGD, especially in high-dimensional settings.

The paper derives estimates for linear potentials and applies them to improve Hausdorff dimensions of singular sets in conformal geometry.

problem Estimating linear potentials and understanding their impact on singular sets in conformal geometry.
method Derives estimates for linear potentials and applies them to improve Hausdorff dimensions of singular sets.
result Improves the Hausdorff dimensions of singular sets in conformal geometry, achieving stronger results in dimension 4.

Detects singularities in complex data to improve machine learning models.

problem Real-world data often contains non-manifold structures (singularities) that can mislead machine learning models.
method Develops a topological framework to quantify local intrinsic dimension and Euclidicity score for multiple scales.
result Identifies singularities and captures local geometric complexity in image data.

Study maximizes eigenvalues in dimensions 3 and above.

problem Maximizing the k-th eigenvalue functional over measures on Riemannian manifolds.
method Generalizes previous work on first eigenvalue to higher dimensions, proving optimal bounds on singular set dimensions.
result Optimal upper bound for Hausdorff dimension of singular set is m-7.

Rigidity theorem for scalar curvature on odd-dimensional singular manifolds.

problem Understanding scalar curvature on manifolds with cone-like singularities.
method Analysis of abstract cone operators, spectral flow argument, and twisted Dirac operators.
result Lipschitz rigidity for scalar curvature on Riemannian spin manifolds with cone-like singularities in odd dimensions.

Smooth minimizing hypersurfaces in 11D are generic, with singularities in higher dimensions.

problem Finding smooth minimizing hypersurfaces in high dimensions.
method Analyzing the Plateau problem and area minimization in integral homology.
result Smooth minimizing hypersurfaces are generic in 11D, with singularities in higher dimensions.

Proves Penrose inequality in all dimensions for specific manifolds.

problem Proving Penrose inequality in arbitrary dimensions for certain manifolds.
method Extends Bray's conformal-flow method to higher dimensions, dealing with singular outer-minimizing enclosures.
result Proves the Riemannian Penrose inequality in arbitrary dimensions.

Improved computational complexity in statistical models using second-order information.

problem Polynomial convergence of gradient descent in singular statistical models.
method Normalized Gradient Descent (NormGD) algorithm with second-order information.
result NormGD reaches final statistical radius in logarithmic iterations of nn.

Gradient descent in deep networks tends to find flat minima, which are nearly balanced.

problem Understanding the effect of gradient descent on the structure of minima in deep neural networks.
method Characterized flat minima in linear neural networks trained with a quadratic loss.
result Flat minima correspond to nearly balanced networks where the gain from input to intermediate representations is nearly constant.

We study singularity structure of Yang-Mills flow in dimensions n4n \geq 4. First we obtain a description of the singular set in terms of concentration for a localized entropy quantity, which leads to an estimate of its Hausdorff dimension. We develop a theory of tangent measures for the flow, which leads to a stratifi…

2016-02-09abs ↗pdf ↗

Compact RCD spaces derived from singular Kahler metrics on 3D projective varieties.

problem Understanding geometric structures of singular Kahler spaces.
method Proving RCD spaces homeomorphic to 3D projective varieties with bounded Nash entropy and Ricci curvature.
result Compact RCD spaces are equivalent to underlying projective varieties.

Study on singularities in Lagrangian mean curvature flow with special Lagrangian cones.

problem Understanding singularities in Lagrangian mean curvature flow.
method Analysis of tangent flows and blowup limits of special Lagrangian cones.
result Uniqueness of tangent flows in dimension two and any dimension when the link is connected.