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.

169,181 papers · 148 categories

Trend · papers per month

94189283377 · Jun 202019922001200920182026
48 results for scale invariant

Scale-invariant algorithms for unconstrained online learning.

problem Designing online algorithms invariant to arbitrary linear transformations of input vectors.
method Exploiting scale invariance symmetry, developing algorithms for coordinate-wise and general invariance.
result Achieved optimal regret bound for coordinate-wise invariance, and almost achieved it for general invariance with logarithmic overhead.

We study scale invariant but not necessarily conformal invariant deformations of non-relativistic conformal field theories from the dual gravity viewpoint. We present the corresponding metric that solves the Einstein equation coupled with a massive vector field. We find that, within the class of metric we study, when w…

2009-06-23abs ↗pdf ↗

Paper derives a fast learning rate for deep neural networks without scale invariant activation functions.

problem Analyzing the impact of non-scale invariant activation functions on deep learning performance.
method Using Suzuki (2018) framework, derived a tight generalization error bound for deep neural networks with non-scale invariant activations.
result Without scale invariance of activation functions, deep learning can still achieve a fast learning rate.

New learning dynamics achieve fast convergence in games without needing to know utility scales.

problem Fast convergence guarantees in learning games require prior knowledge of utility scales.
method Developed scale-free and scale-invariant learning dynamics using optimistic follow-the-regularized-leader with adaptive learning rates and clipping techniques.
result Achieved fast convergence rates to Nash and correlated equilibria without prior utility scale knowledge.

New algorithm optimizes ReLU networks by transforming to a scale-invariant space.

problem Optimization issues in ReLU networks due to mismatch between optimization space and network's scale-invariance.
method Developed G\mathcal{G}-SGD algorithm operating in a new G\mathcal{G}-space, invariant under positive scaling.
result Significant improvement in optimizing ReLU networks compared to conventional SGD.

Three training regimes found for scale-invariant neural networks on the sphere.

problem Training scale-invariant neural networks on the sphere with varying effective learning rate.
method Investigated three regimes of training: convergence, chaotic equilibrium, and divergence.
result Discovered three distinct training regimes with unique characteristics.

DeepHoyer introduces differentiable, scale-invariant sparsity measures for neural networks.

problem Efficiently sparsifying neural networks with scale-invariant sparsity measures.
method Developed DeepHoyer, a set of differentiable, scale-invariant sparsity-inducing regularizers based on the Hoyer measure.
result DeepHoyer produces sparser neural networks than previous methods, maintaining similar accuracy.

We introduce a new weight-decay scaling rule to maintain sublayer gains across different widths in modern scale-invariant architectures.

problem In modern scale-invariant architectures, training quickly enters a steady state where normalization layers create backward scale sensitivity, degrading learning-rate transfer.
method We introduce a weight-decay scaling rule for AdamW that preserves sublayer gain across widths by equalizing the effective learning rate.
result Our empirical weight-decay scaling rule λ2dλ_2\propto \sqrt{d} approximately keeps sublayer gains width invariant, enabling zero-shot transfer of learning rate and weight decay.

Proves uniqueness of Ricci flow with scaling invariant estimates.

problem Proving uniqueness of Ricci flow with scaling invariant curvature bound.
method Solving Ricci-harmonic map heat flow in unbounded curvature background.
result Complete Ricci flow starting from uniformly non-collapsed, non-negatively curved manifold is unique in dimension three.

Critical points of scale-invariant curvature energies in 4D are analytic.

problem Analyzing critical points of curvature energies in 4D manifolds.
method Applying Noether's theorem to identify conservation laws and lower order elliptic system of PDEs, then using integrability by compensation and interpolation theory.
result Critical points of scale-invariant curvature energies in 4D are analytic.

New bounds on self-normalized martingales improve online linear regression performance.

problem Improving regret bounds in online linear regression.
method Characterizing scale-invariant bounds on self-normalized martingales.
result For d=1d=1, O(logT)O(\log T) doubly-uniform regret is possible; for d>1d>1, sublinear doubly-uniform regret is impossible.

Adam performs better with equal momentum parameters, revealing a gradient scale invariance principle.

problem Why Adam performs better with β1=β2β_1 = β_2.
method Formalized gradient scale invariance and proved it for Adam with equal β1β_1 and β2β_2.
result Adam becomes gradient scale invariant of first order if and only if β1=β2β_1 = β_2.

We develop a scale-invariant truncated Lévy (STL) process to describe physical systems characterized by correlated stochastic variables. The STL process exhibits Lévy stability for the probability density, and hence shows scaling properties (as observed in empirical data); it has the advantage that all moments are fini…

1999-06-25abs ↗pdf ↗

AdamP optimizes momentum-based optimizers for scale-invariant weights, improving model performance.

problem Premature decay of effective step sizes in momentum-based optimizers for scale-invariant weights.
method Proposes SGDP and AdamP to eliminate the radial component at each optimizer step, preserving convergence properties.
result Uniform gains across multiple benchmarks, improving model performance.

The paper classifies left-invariant pseudo-Riemannian metrics on specific Lie groups.

problem Classifying left-invariant pseudo-Riemannian metrics on Lie groups.
method Analyzing left-invariant metrics on specific Lie groups with n4n \geq 4.
result A complete classification of left-invariant pseudo-Riemannian metrics for Lie groups of dimension n4n \geq 4.

Wavelet scattering spectra model non-Gaussian time-series, proving scale invariance for self-similar processes.

problem Modeling non-Gaussian time-series with stationary increments.
method Complex wavelet transform for scale variations, joint correlation matrix for scale dependencies, second wavelet transform for diagonalization, maximum entropy models conditioned by scattering spectra coefficients.
result Scattering spectra of self-similar processes are scale invariant, allowing statistical testing and generation of new time-series.

ASAM improves deep neural network generalization by adapting sharpness to scale.

problem Fixed-radius sharpness measure is sensitive to parameter scaling, weakening its connection to generalization.
method Introduces adaptive sharpness, a scale-invariant measure, and proposes ASAM for deep learning.
result ASAM significantly improves model generalization performance across various datasets.

Investigates energy minimizers and critical points of scale-invariant tangent-point energies for knots.

problem Finding and characterizing minimizers and critical points of scale-invariant tangent-point energies for closed curves.
method Develops convergence and regularity theories based on fractional Sobolev spaces and new energy functionals.
result Minimizing sequences converge to locally critical embeddings in all but finitely many points, and locally critical embeddings are regular.

The paper develops a regularity theory for O'hara knot energies, focusing on Möbius energy.

problem Developing a regularity theory for extremal knots of scale invariant knot energies defined by J. O'hara.
method Reinterpreting O'hara knot energies as a nonlinear, nonlocal LpL^p-energy acting on the unit tangent of the knot parametrization, drawing a connection to the theory of (fractional) harmonic maps into spheres.
result Proves regularity for minimizers and critical knots of the scale-invariant O'hara knot energies.

Study shows how near crushing singularities, Kasner-like regions can exist.

problem Understanding spatial volume densities near crushing singularities.
method Relates existence of Kasner-like regions to asymptotics of spatial volume densities under scale-invariant curvature bounds.
result Kasner-like regions can exist near crushing singularities under certain curvature conditions.

Transforms improve CNNs' invariance to image transformations.

problem Current CNN models lack robustness to spatial transformations.
method Randomly transform feature maps during training to learn invariant representations.
result Significant improvements on benchmark tasks, including image recognition and retrieval.

Unified framework for scale-invariant representation learning using MAPCA.

problem Learning invariant representations in data.
method Metric-Aware Principal Component Analysis (MAPCA) based on generalized eigenproblem.
result MAPCA provides a unified geometric language for various self-supervised learning objectives.

Paper introduces normalized flat minima to address scale dependence in neural network optimization.

problem Scale dependence in existing flat minima definitions affects generalization studies.
method PAC-Bayesian analysis to introduce normalized flat minima, free from scale dependence.
result Normalized flat minima provides better hierarchy in hypothesis class and improved generalization.

SAM improves deep learning tasks by promoting balancedness, reducing outlier impact.

problem Improving generalization in deep learning tasks, especially with scale-invariant problems.
method Introduces balancedness as a new concept to depict global behaviors of SAM, focusing on the difference between squared norms of two variables.
result SAM promotes balancedness and is data-responsive, outperforming SGD in outlier scenarios.

SAM improves generalization in overparameterized models, but its behavior in tensorized models is less understood.

problem Understanding the implicit regularization of SAM in tensorized models.
method Scale-invariance analysis and gradient flow analysis to derive Norm Deviation as a measure of core norm imbalance, and propose Deviation-Aware Scaling (DAS).
result DAS achieves competitive or improved performance over SAM, while offering reduced computational overhead.

New methods improve adversarial attacks' transferability to other models.

problem Vulnerability of deep learning models to adversarial examples.
method Nesterov Iterative Fast Gradient Sign Method (NI-FGSM) and Scale-Invariant attack Method (SIM).
result NI-FGSM and SIM generate more transferable adversarial examples.

A new geometric method approximates slow invariant manifolds without explicit time-scale separation.

problem Approximating slow invariant manifolds in systems with multiple time-scales.
method Geodesic Stretching and Flow Curvature methods translated into tensorial constructions of Riemannian geometry.
result The method approximates normally attracting invariant manifolds without requiring explicit time-scale separation.

Generalized algorithm for translation and scale-invariant prediction.

problem Sequential prediction with expert advice, focusing on translation and scale invariance.
method Designing a generalized online algorithm using the universal prediction perspective to compete against a generic class of expert selection strategies.
result No preliminary knowledge of loss sequences is required; performance bounds are stable under arbitrary scalings and translations.

We introduce multiscale invariant dictionaries to estimate quantum chemical energies of organic molecules, from training databases. Molecular energies are invariant to isometric atomic displacements, and are Lipschitz continuous to molecular deformations. Similarly to density functional theory (DFT), the molecule is re…

2016-05-16abs ↗pdf ↗

We study the concept of coarse disjointness and large scale nn-to-11 functions. As a byproduct, we obtain an Ostrand-type characterization of asymptotic dimension for coarse structures. It is shown that properties like finite asymptotic dimension, coarse finitism, large scale weak paracompactness, ect. are all invari…

2015-08-12abs ↗pdf ↗

The results of R^2 dynamical random surface model (2-dimensional quantum gravity with a R2R^2 term) are applied to explain the personal income distribution. A scale invariance exists if there is not the R2R^2 term in the action. The R^2 term provides a typical scale and breaks the scale invariance explicitly in the low…

2002-03-20abs ↗pdf ↗

Trading invariance hypothesis is revised with high correlation to trading costs.

problem Revisiting trading invariance hypothesis in metaorders.
method Empirical analysis of a large dataset of metaorders, investigating the quantity II and its correlation with trading costs.
result Trading invariance hypothesis is revised; II is not invariant but highly correlated with trading costs.

The paper studies minimal resistance dynamics in radial fields, finding unique solutions for incompressible flows.

problem Nonlinear dynamics of minimal resistance in radial fields.
method Analysis of two non-equilibrium scenarios: scale-invariant free expansion and incompressible source flow.
result Incompressible flow acts as a structural regularizer, admitting unique, smooth, and strictly concave solutions.

Study reveals a universal formula for knotting in random equilateral polygons.

problem Probability of knotting in equilateral random polygons.
method Extensive Monte Carlo simulations with improved algorithms and knot invariants.
result A universal scaling formula for knotting probability with number of edges, involving exponential and power law factors.