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.

168,738 papers · 148 categories

Trend · papers per month

25497498 · May 202619922001200920172026
48 results for Hessian concentration

Constructs flows on manifolds with small curvature, proving Euclidean topology.

problem Geometric structure of manifolds with unbounded curvature.
method Distance like functions with integral hessian bound, Ricci flows.
result Manifolds with Ricci lower bound, non-negative scalar curvature, bounded entropy, Ahlfors nn-regular and small curvature concentration are topologically Euclidean.

Our work connects parameter magnitudes and Hessian eigenspaces in deep neural nets.

problem Understanding the relationship between parameter magnitudes and Hessian curvature in deep learning models.
method Developed a matrix-free algorithm based on sketched SVDs to measure similarity between parameter masks and Hessian eigenspaces.
result Top Hessian eigenvectors tend to be concentrated around larger parameters, indicating a connection between parameter magnitudes and loss curvature.

Proves smooth solutions for generalised Monge-Ampère equations on projective manifolds.

problem Existence of smooth solutions for generalised Monge-Ampère equations on projective manifolds.
method Intersection numbers and degenerate concentration of mass result.
result Proves existence of smooth solutions for generalised Monge-Ampère equations on projective manifolds.

SGD noise helps select flat minima by concentrating in sharp directions and being proportional to loss value.

problem Understanding the implicit regularization of SGD and selecting flat minima in over-parameterized models.
method Relating SGD's linear stability to the Frobenius norm of the Hessian and analyzing the alignment property of SGD noise.
result Flat minima are linearly stable for SGD, and their sharpness is bounded independently of model size and sample size.

Large scale optimization problems are ubiquitous in machine learning and data analysis and there is a plethora of algorithms for solving such problems. Many of these algorithms employ sub-sampling, as a way to either speed up the computations and/or to implicitly implement a form of statistical regularization. In this …

2016-01-18abs ↗pdf ↗

The asymptotic concentration of the Fr{é}chet mean of IID random variables on a Rieman-nian manifold was established with a central limit theorem by Bhattacharya \& Patrangenaru (BP-CLT) [6]. This asymptotic result shows that the Fr{é}chet mean behaves almost as the usual Euclidean case for sufficiently concentrated di…

2019-06-18abs ↗pdf ↗

A new dimension reduction method based on Gaussian finite mixtures is proposed as an extension to sliced inverse regression (SIR). The model-based SIR (MSIR) approach allows the main limitation of SIR to be overcome, i.e., failure in the presence of regression symmetric relationships, without the need to impose further…

2015-08-10abs ↗pdf ↗

The study proves that certain noncompact Hessian manifolds are diffeomorphic to R^n.

problem Characterizing complete noncompact Hessian manifolds with nonnegative Hessian sectional curvature.
method Using a geometric flow on noncompact affine Riemannian manifolds, constructing Hessian metrics, and proving diffeomorphism.
result Complete noncompact Hessian manifolds with nonnegative Hessian sectional curvature are diffeomorphic to R^n if their tangent bundle has maximal volume growth.

Many data-fitting applications require the solution of an optimization problem involving a sum of large number of functions of high dimensional parameter. Here, we consider the problem of minimizing a sum of nn functions over a convex constraint set XRp\mathcal{X} \subseteq \mathbb{R}^{p} where both nn and pp are lar…

2016-01-18abs ↗pdf ↗

New Hessian estimates for heat equations on manifolds.

problem Estimating Hessian matrices for heat-type equations on Riemannian manifolds.
method Using Bismut-Stroock Hessian formula, with explicit coefficients and delay/growth rate functions.
result Novel backward weak Harnack inequality and precise pointwise Hessian estimates for eigenfunctions.

We prove that, in dimensions greater than 2, the generic metric is not a Hessian metric and find a curvature condition on Hessian metrics in dimensions greater than 3. In particular we prove that the forms used to define the Pontryagin classes in terms of the curvature vanish on a Hessian manifold. By contrast all anal…

2013-12-04abs ↗pdf ↗

Curved Frobenius manifolds link to Hessian metrics in geometry.

problem Understanding curved Frobenius manifolds and their relation to Hessian metrics.
method Analyzing the relationship between curved Frobenius structures and Hessian metrics on spaces with non-vanishing curvature.
result Consistent curved Frobenius structures on constant curvature spaces are linked to Hessian metrics.

Criterion for solvability of complex 2-Hessian equation on compact Kähler manifolds.

problem Solvability of complex 2-Hessian equation on compact Kähler manifolds.
method Nakai--Moishezon-type criterion associated with the complex 2-Hessian equation.
result Criterion equivalent to existence of a smooth 2-admissible representative in complex dimension three.

Constructs homogeneous Kähler structures on tangent bundles of Hessian manifolds.

problem Creating Kähler structures on tangent bundles of Hessian manifolds.
method Endowing Hessian manifolds with Kähler structures using group actions and homothetic vector fields.
result Homogeneous conformally Kähler structures on tangent bundles of selfsimilar Hessian manifolds.

Paper proves inequalities on Hermitian manifolds with applications to bounded solutions.

problem Establishing mixed Hessian inequalities on Hermitian manifolds.
method Weak convergence theorem of complex Hessian operators and general mixed Hessian inequality.
result Existence of bounded solutions of complex Hessian equations.

A selfsimiar manifold is a Riemannian manifold (M,g)\left(M,g\right) endowed with a homothetic vector field ξξ. We characterize global selfsimilar manifolds and describe the structure of local selfsimilar manifolds. We prove that any selfsimilar manifold with a potential homothetic vector field is a conical Riemannian ma…

2019-08-05abs ↗pdf ↗

Study of contravariant pseudo-Hessian manifolds and their Poisson structures.

problem Understanding properties of contravariant pseudo-Hessian manifolds.
method Investigation of flat connections and symmetric bivector fields satisfying a contravariant Codazzi equation.
result Association of a Poisson tensor to contravariant pseudo-Hessian manifolds.

This paper uncovers the low-rank structure of neural network Hessians.

problem Understanding the structure of Hessians in neural networks.
method Proposes a decoupling conjecture to decompose layer-wise Hessians into Kronecker products of smaller matrices.
result Proves the structure of top eigenspaces in 2-layer networks and shows high overlap in top eigenvectors across different models.

Study confirms Chern's conjecture on compact Hessian manifolds and classifies their topologies.

problem Global topological constraints and structural properties of compact Hessian manifolds.
method Novel fibration and splitting theorems, Chern's conjecture, Hitchin systems, Cheng-Yau solution.
result Topological classification of complete Hessian surfaces and closed orientable Hessian 3-manifolds.

Paper discusses solving generalized Hessian inequalities with various operators.

problem Finding global solutions to generalized Hessian inequalities.
method Analyzes various Hessian operators and provides conditions for global solvability.
result Provides necessary and sufficient conditions for global solvability of generalized Hessian inequalities.

Hessian alignment improves OOD generalization in deep learning.

problem Improving deep learning models' ability to generalize to out-of-distribution data.
method Analyzed Hessian and gradient alignment for domain generalization using recent OOD theory.
result Hessian alignment methods achieve promising performance on various OOD benchmarks.

New perspective on CNNs using Hessian maps reveals their structure.

problem Understanding the nature of Convolutional Neural Networks (CNNs).
method Developed a framework using Toeplitz representation of CNNs to reveal Hessian structure and prove rank bounds.
result Proved that the Hessian rank of CNNs grows as the square root of the number of parameters.