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

20395978 · Jun 202019922001200920172026
48 results for Non-Euclidean Norms

New method turns optimization algorithms into uniformly stable learning algorithms for non-Euclidean norms.

problem Non-Euclidean norms in binary classification problems.
method Black-box reduction method using uniformly convex regularizers.
result Achieves optimal statistical risk bounds on excess risk for non-Euclidean norms.

Gradient descent near stability threshold shows sharpness oscillations.

problem Understanding sharpness and stability in non-Euclidean norms during gradient descent.
method Interpreted EoS through Directional Smoothness, defined generalized sharpness for arbitrary norms.
result Non-Euclidean GD exhibits sharpness oscillations around the stability threshold.

Gradient descent near stability threshold exhibits sharpness oscillations.

problem Understanding sharpness behavior near stability threshold in non-Euclidean norms.
method Interpreted EoS through Directional Smoothness and generalized sharpness under arbitrary norms.
result Non-Euclidean GD with generalized sharpness shows sharpness oscillations near 2/η2/η.

New algorithms optimize convex functions with high-order derivatives.

problem Optimizing convex functions with high-order derivatives under various norms.
method Developed a non-Euclidean inexact accelerated proximal point method using an inexact uniformly convex regularizer.
result Showed nearly optimal algorithms for high dimensions in the black-box oracle model for p\ell_p-settings and all q1q \geq 1.

New optimization method combines gradient clipping and non-Euclidean smoothness.

problem Improving optimization in non-Euclidean spaces for machine learning.
method Hybrid of steepest descent and conditional gradient, incorporating weight decay.
result Achieves optimal convergence rate and demonstrates effectiveness in deep learning.

EF21-Muon optimizes deep learning with error feedback, improving efficiency and accuracy.

problem Lack of principled distributed frameworks for non-Euclidean LMO-based optimizers.
method Introduces EF21-Muon, a communication-efficient, non-Euclidean LMO-based optimizer with convergence guarantees.
result First efficient distributed implementation of non-Euclidean LMO-based optimizers, achieving up to 7x communication savings.

The paper analyzes and improves a deep learning optimization technique using matrix gradient orthogonality.

problem Improving deep learning training through more effective optimization methods.
method Develops a stochastic non-Euclidean trust-region gradient method for deep learning optimization.
result Proves state-of-the-art convergence results for the proposed algorithm in various scenarios.

The paper explores centroids and static equilibrium points in non-Euclidean geometries.

problem Investigating centroids and static equilibrium points in spherical, hyperbolic, and normed spaces.
method Extending Gal'perin's work, the paper examines convex bodies in these spaces and analyzes the minimum number of equilibrium points.
result Every plane convex body in any of these spaces has at least four equilibrium points, and there are mono-monostatic convex bodies in 3D spherical, hyperbolic, and certain normed spaces.

The paper extends manifold learning to arbitrary norms, improving molecular motion mapping.

problem Improving manifold learning for non-Euclidean norms.
method Determines the limiting differential operator for graph Laplacians using any norm.
result A modified Laplacian eigenmaps algorithm using Earthmover's distance outperforms Euclidean methods in molecular motion mapping.

New method accelerates steepest descent for convex optimization.

problem Achieving acceleration for general p\ell_p smooth functions.
method Primal-dual iterate sequences with differing norms, implicitly determined interpolation parameter.
result Improves iteration complexity to O(d12p)O(d^{1-\frac{2}{p}}) for p\ell_p norm smooth problems.

New framework improves robustness of implicit neural networks.

problem Ill-posedness and convergence instability in implicit neural networks.
method NEMON framework based on contraction theory for \ell_{\infty} norm, including well-posedness condition, average iteration, and input-output Lipschitz constant regularization.
result Improved accuracy and robustness of implicit models with smaller input-output Lipschitz bounds.

We prove a relation between the scaling hβh^β of the elastic energies of shrinking non-Euclidean bodies ShS_h of thickness h0h\to 0, and the curvature along their mid-surface SS. This extends and generalizes similar results for plates [BLS16, LRR] to any dimension and co-dimension. In particular, it proves that the na…

2018-01-07abs ↗pdf ↗

Develops a new asymptotic efficiency theory for non-Euclidean parameter spaces.

problem Lack of a unified efficiency theory for non-Euclidean parameter spaces.
method Introduces a new theory for Riemannian manifolds with regularity conditions.
result Establishes efficiency bounds for non-Euclidean parameter spaces.

We investigate isometric immersions of disks with constant negative curvature into R3\mathbb{R}^3, and the minimizers for the bending energy, i.e. the L2L^2 norm of the principal curvatures over the class of W2,2W^{2,2} isometric immersions. We show the existence of smooth immersions of arbitrarily large geodesic balls i…

2010-05-24abs ↗pdf ↗

New algorithm achieves optimal privacy and efficiency in non-Euclidean convex optimization.

problem Optimizing convex functions while maintaining privacy in non-Euclidean settings.
method Developed a linear-time algorithm for p\ell_p-setups, leveraging geometric properties.
result Optimal excess risk achieved in linear time for 1<p21 < p \leq 2.

Muon optimizes Transformer training with heavy-tailed data, achieving optimal sample complexity.

problem Theoretical understanding of non-Euclidean optimisation methods for heavy-tailed data in training Transformers.
method Addressing the gap in theoretical understanding, we show Muon achieves optimal sample complexity under heavy-tailed noise.
result Muon finds an ε-stationary point in nuclear norm with optimal sample complexity, absorbing heavy-tailed noise without dimension dependence.

Muons and random optimizers perform similarly, challenging geometric optimization theory.

problem Empirical success of Muon optimizer challenges geometric optimization theory.
method Introducing Freon and Kaon optimizers, demonstrating performance without precise geometric structure.
result Performance of optimizers is controlled by alignment and descent potential, not geometric structure.

We take a Hamiltonian-based perspective to generalize Nesterov's accelerated gradient descent and Polyak's heavy ball method to a broad class of momentum methods in the setting of (possibly) constrained minimization in Euclidean and non-Euclidean normed vector spaces. Our perspective leads to a generic and unifying non…

2019-06-02abs ↗pdf ↗

The goal of this paper is to introduce and study analogues of the Euclidean Funk and Hilbert metrics on open convex subsets ΩΩ of hyperbolic or spherical spaces. At least at a formal level, there are striking similarities among the three cases: Euclidean, spherical and hyperbolic. We start by defining non-Euclidean an…

2012-09-19abs ↗pdf ↗

Unified framework for non-Euclidean CPD under scalable stochastic mirror descent.

problem Handling non-Euclidean losses in tensor decomposition.
method Tensor fiber sampling strategy-based stochastic mirror descent.
result Global convergence to a stationary point under reasonable conditions.

This foreword discusses the contributions of Bolyai, Gauss, and Lobachevsky to non-Euclidean geometry.

problem The development of non-Euclidean geometries by Bolyai, Gauss, and Lobachevsky.
method Historical review of the contributions of these mathematicians.
result The foundational work on non-Euclidean geometries by Bolyai, Gauss, and Lobachevsky.

This paper deals with various topics in analysis on hyperbolic spaces. It surveys some recent progress in non-Euclidean Fourier Analysis and proves some new results for the geodesic Radon transform on hyperbolic spaces.

2004-11-18abs ↗pdf ↗

Piecewise flat approximations for curvature in Euclidean and non-Euclidean spaces.

problem Approximating local extrinsic curvature on discrete manifolds.
method Constructing discrete curvature forms on piecewise flat manifolds, using weighted sums of hinge angles.
result Converges to smooth curvature values as mesh refinement occurs, favorably comparing with other discrete approaches.

This paper tightens the generalization error bound for graph embedding in non-Euclidean spaces.

problem High generalization error in non-Euclidean graph embedding, preventing practical applications.
method Novel upper bound of graph embedding's generalization error using local Rademacher complexity.
result The new bound is tighter and faster, allowing better performance in non-Euclidean spaces.

Study on bending energy of surfaces with curvature concentration, deriving new lower bounds.

problem Analyzing the Willmore energy of surfaces with curvature concentration.
method Using isoperimetric inequalities and framed loops, derive new lower bounds for the bending energy.
result Optimal blowup rates of the Willmore energy when curvature is concentrated.

Study classifies graphs in Euclidean and non-Euclidean spaces with specific curvature conditions.

problem Classifying graphs with prescribed curvature in various spaces.
method Proves rigidity and classification results for graphs in Riemannian manifolds, focusing on R2\mathbb{R}^2 and R3\mathbb{R}^3.
result Provides general splitting theorems for graphs in these settings.

In this paper we demonstrate how the geometrically motivated algorithm to determine whether a two generator real Mobius group acting on the Poincare plane is or is not discrete can be interpreted as a non-Euclidean Euclidean algorithm. That is, the algorithm can be viewed as an application of the Euclidean division alg…

2012-07-04abs ↗pdf ↗

Extends illumination bodies to non-Euclidean spaces and proves their volume derivative defines surface area.

problem Defining surface area in non-Euclidean geometries.
method Generalizes illumination bodies to Riemannian spaces of constant curvature and projective Finsler geometries, proving their volume derivative defines surface area.
result Derivative of volume of illumination bodies defines surface area in non-Euclidean geometries.