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.

169,291 papers · 148 categories

Trend · papers per month

162325487649 · Jun 202019922001200920182026
48 results for 1-Lipschitz functions

In this paper, we study the Lévy-Milman concentration phenomenon of 1-Lipschitz maps into infinite dimensional metric spaces. Our main theorem asserts that the concentration to an infinite dimensional p\ell^p-ball with the q\ell^q-distance function for 1p<q+1\leq p<q\leq +\infty is equivalent to the concentration to the…

2008-08-24abs ↗pdf ↗

The paper studies concentration of measure on manifolds with boundary, focusing on 11-Lipschitz functions.

problem Concentration of measure phenomena of non-negative 11-Lipschitz functions on manifolds with Dirichlet boundary condition.
method Examined relation between boundary concentration phenomena and large spectral gap phenomena of Dirichlet eigenvalues of Laplacian. Introduced new invariant called the observable inscribed radius.
result Formulated comparison theorems for the observable inscribed radius under lower Ricci curvature and mean curvature bounds for the boundary.

New findings show depth separations for natural radial functions are not possible.

problem Depth separations for natural radial functions in neural networks.
method Study of O(1)\mathcal{O}(1)-Lipschitz radial functions with depth 2 networks.
result Approximating O(1)\mathcal{O}(1)-Lipschitz radial functions with depth 2, size poly(d) networks for every constant ε.

This paper examines weight initialization for 1-Lipschitz networks to improve robustness against adversarial attacks.

problem Improving the robustness of deep neural networks against adversarial attacks.
method Examined weight parametrization of AOL and SLL networks, calculated weight variance bounds, and demonstrated weight decay.
result Weight initialization causes deep 1-Lipschitz networks to decay to zero, and weight variance does not affect output variance distribution.

Orthogonium offers unified, efficient layers for robust deep learning.

problem Fragmented and computationally demanding implementations of orthogonal and 1-Lipschitz layers.
method Unified, efficient PyTorch library providing orthogonal and 1-Lipschitz layers.
result Reduced overhead and standardized tools for robust experimentation.

1-Lipschitz networks are as accurate as classical networks and offer robustness.

problem Misconceptions about 1-Lipschitz neural networks and their properties.
method Analysis of 1-Lipschitz neural networks' accuracy, robustness, and generalization.
result 1-Lipschitz neural networks are as accurate as classical networks and can fit arbitrarily difficult boundaries.

New neural network design resists small \ell_\infty-norm adversarial perturbations.

problem Vulnerability of neural networks to small \ell_\infty-norm adversarial perturbations.
method Designing \ell_\infty-dist neurons and constructing \ell_{\infty}-dist nets, proving their 1-Lipschitz property and expressive power.
result Certified robustness of \ell_{\infty}-dist nets with state-of-the-art performance on various datasets.

1-Lipschitz neural networks produce clearer, more focused Saliency Maps for explainable AI.

problem Noisy and limited Saliency Maps from traditional neural networks.
method Dual loss of optimal transport problem for 1-Lipschitz neural networks.
result Saliency Maps from 1-Lipschitz networks are highly concentrated and less noisy, aligning with human explanations.

The paper studies optimal transport for vector measures and confirms a conjecture about their conditional measures.

problem Optimal transport of vector measures and conditional measures.
method Developed a theory of optimal transport for vector measures and used it to answer a conjecture.
result The conditional measures of vector measures have total mass zero under certain conditions.

Maps persistence diagrams into Hilbert and Euclidean spaces with explicit distortions.

problem Embedding persistence diagrams into Euclidean spaces for statistical analysis.
method Explicit geometric maps with distortion functions.
result Controlled geometric information loss through explicit distortion functions.

Optimizes optimal transport distances using low-dimensional embeddings.

problem High computational cost of optimal transport distances in high dimensions.
method Approximate OT distances using 1-Lipschitz maps in a lower-dimensional space.
result Efficiently approximates optimal transport distances with lower computational cost.

The Nash-Kuiper Theorem states that the collection of C1C^1-isometric embeddings from a Riemannian manifold MnM^n into EN\mathbb{E}^N is C0C^0-dense within the collection of all smooth 1-Lipschitz embeddings provided that n<Nn < N. This result is now known to be a consequence of Gromov's more general hh-principle. Ther…

2015-07-31abs ↗pdf ↗

Lipschitz maps on metric surfaces are rigid if they preserve area.

problem Understanding the rigidity of Lipschitz maps on metric surfaces.
method Established a coarea inequality for continuous Sobolev functions on metric surfaces.
result Proved that 1-Lipschitz maps from a closed metric surface to a closed Riemannian surface preserving area are isometries.

Maps between certain Lipschitz manifolds are isometries if they preserve volume.

problem Volume preservation and isometry conditions for Lipschitz manifolds.
method Volume-preserving 1-Lipschitz maps from integral currents onto infinitesimally Euclidean Lipschitz manifolds.
result Volume-preserving maps are isometries under given conditions.

Defines and analyzes pseudo-metrics on Teichmüller space of semi-translation surfaces.

problem Defining and analyzing metrics on Teichmüller space of semi-translation surfaces.
method Defines and analyzes pseudo-metrics LFL_F, KFK_F, LFaL_F^a, KFaK_F^a on Teichmüller space of semi-translation surfaces.
result Proves completeness of pseudo-metrics LFL_F and KFK_F.

JacNet learns Jacobians to enforce structure on derivatives for invertibility and Lipschitz functions.

problem Enforcing structure on derivatives of neural network mappings.
method Proposes using a neural network to directly learn the Jacobian of the input-output function, allowing control over derivative structure.
result Demonstrates learning invertible approximations to simple and 1-Lipschitz functions.

New neural network architecture preserves gradient norms to approximate Lipschitz functions.

problem Training neural networks with strict Lipschitz constraints to ensure robustness and generalization.
method Identified gradient norm preservation as a necessary property, combined with norm-constrained weight matrices and GroupSort activation function.
result Norm-constrained GroupSort architectures can approximate Lipschitz functions and achieve tighter Wasserstein distance estimates.

Proves rigidity for maps between manifolds using degree theory and current developments.

problem Lipschitz-volume rigidity for maps between metric manifolds and Riemannian manifolds.
method Degree theory and recent developments of Lipschitz-volume rigidity for integral currents.
result Proves a Lipschitz-volume rigidity result for 1-Lipschitz maps.

We show that for a metric space with an even number of points there is a 1-Lipschitz map to a tree-like space with the same matching number. This result gives the first basic version of an unoriented Kantorovich duality. The study of the duality gives a version of global calibrations for 1-chains with coefficients in $…

2014-09-30abs ↗pdf ↗

Deep neural networks can approximate complex functions through repeated compositions of a fixed-size ReLU network.

problem Understanding the expressive power of deep neural networks through function compositions.
method Demonstrated the surprising expressive power of repeated compositions of a single fixed-size ReLU network.
result Repeated compositions of a single fixed-size ReLU network can approximate 1-Lipschitz continuous functions on [0,1]d[0,1]^d with an error O(r1/d)\mathcal{O}(r^{-1/d}).

We prove a Lipschitz-Volume rigidity theorem in Alexandrov geometry, that is, if a 1-Lipschitz map f ⁣:X=⨿XYf\colon X=\amalg X_\ell\to Y between Alexandrov spaces preserves volume, then it is a path isometry and an isometry when restricted to the interior of XX. We furthermore characterize the metric structure on YY with re…

2011-10-25abs ↗pdf ↗

This thesis uses Kantorovich-Rubinstein distance for classifying points based on their measures.

problem Classifying points based on their measures in a metric space.
method Using Kantorovich-Rubinstein distance as a metric in the space of measures to capture geometry and topology.
result A large Kantorovich-Rubinstein distance indicates the existence of a 1-Lipschitz classifier that well classifies the points.

Framework for designing nonlinearities in neural networks with slope constraints.

problem Designing nonlinearities with specific properties for signal processing.
method Variational framework with regularization for slope constraints and optimization of adaptive splines.
result Adaptive nonuniform linear splines achieve global optimum in constrained optimization.

LOT improves adversarial robustness by training 1-Lipschitz convolution layers.

problem Improving adversarial robustness of deep neural networks.
method LOT: Layer-wise Orthogonal Training for 1-Lipschitz convolution layers.
result LOT significantly enhances certified robustness of Lipschitz-bounded models.

This paper generalizes the cut locus concept for almost distance functions.

problem Generalizing the cut locus concept for almost distance functions.
method Introducing 1-Lipschitz functions called almost distance functions and studying their singular loci.
result Obtained a structure theorem for the singular locus of an almost distance function on a 2D Finsler manifold.

Proves depth 2 neural networks can't approximate certain functions as well as depth 3 networks.

problem Approximating functions with depth 2 networks in high dimensions.
method Lower bound proof using worst-to-average-case random self-reducibility.
result Proves depth 2 networks can't approximate certain functions as well as depth 3 networks, resolving an open problem.

Optimal transport theory characterizes convex order between probability measures.

problem Characterizing convex order between probability measures using optimal transport.
method Quantitative bounds on optimal transport, infimum of functionals over 1-Lipschitz functions.
result Two measures are in convex order if and only if a specific cost functional inequality holds.

Study extends biholomorphisms between convex domains in complex space without boundary constraints.

problem Extending biholomorphisms between convex domains without boundary regularity.
method Combining coarse geometry techniques with dynamical properties of maps in Gromov hyperbolic spaces.
result Proves extensions for biholomorphisms and quasi-isometries between convex domains.

New framework enhances neural network robustness against adversarial attacks.

problem Vulnerability of deep neural networks to small perturbations.
method Integrates Lipschitz constraint using optimal transport and hinge regularization.
result Proposes a new loss function that certifies adversarial robustness.

The degree condition affects the rigidity of maps between manifolds.

problem Investigating the degree condition for scalar curvature rigidity.
method Analyzing maps between Riemannian manifolds with scalar curvature constraints.
result The degree condition is necessary for scalar curvature rigidity but not for Ricci curvature rigidity.

This work analyzes how deep neural networks' expressiveness increases with depth and width.

problem Understanding the expressiveness of deep neural networks (DNNs) based on their Lipschitz constants.
method Leveraging random matrix theory, the study characterizes the expressiveness of DNNs by their Lipschitz constant, showing exponential and polynomial increases with depth and width, respectively.
result The expressiveness of DNNs increases exponentially with depth and polynomially with width, consistent with function approximation benefits.

Two-layer neural networks need more neurons to be robust.

problem Understanding the robustness of two-layer neural networks and the role of overparametrization.
method Investigation of the tradeoffs between network size and robustness, using Lipschitz constant as a measure.
result A conjecture that robustness requires overparametrization, with precise bounds for different cases.

Quadratic memory is essential for optimal convex optimization queries.

problem Optimal query complexity for convex optimization and feasibility problems.
method Lower bounds on query complexity for convex optimization and feasibility problems.
result Center-of-mass algorithms are Pareto-optimal for both convex optimization and feasibility problems.

Paper addresses ERM in LDP, reducing sample complexity for smooth and convex losses.

problem Achieving error α in ERM with non-interactive LDP, especially for high-dimensional data.
method Developed algorithms using Bernstein polynomial and polynomial approximation techniques.
result For smooth and convex losses, sample complexity is linear in dimensionality.

Unified plug-in approach for estimating symmetric properties of distributions efficiently.

problem Estimating symmetric properties of distributions with high accuracy and efficiency.
method Profile-maximum-likelihood (PML) based estimator.
result Achieves theoretical limit for universal symmetric property estimation.