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.

168,695 papers · 148 categories

Trend · papers per month

275481108 · Jun 202019922001200920172026
48 results for Lipschitz norm

Training neural networks under a strict Lipschitz constraint is useful for provable adversarial robustness, generalization bounds, interpretable gradients, and Wasserstein distance estimation. By the composition property of Lipschitz functions, it suffices to ensure that each individual affine transformation or nonline…

2018-11-13abs ↗pdf ↗

The paper proves inequalities linking geometric norms and Thurston norms in hyperbolic 3-manifolds.

problem Inequalities linking geometric norms and Thurston norms in hyperbolic 3-manifolds.
method Analyzes geometric L2L^2-norms, Thurston norms, and Lipschitz maps to prove inequalities.
result Proves an inequality between geometric L2L^2-norm and Thurston norm, qualitatively sharp.

New method for efficient proximal mapping of 1-path-norm in shallow networks.

problem Efficiently handling the 1-path-norm of shallow neural networks.
method Closed-form proximal operator for efficient computation and upper bound on Lipschitz constant.
result Proximal mapping allows robust training against adversarial perturbations.

We model how Lipschitz continuity changes during neural network training.

problem Understanding how Lipschitz continuity evolves during training.
method We use a system of stochastic differential equations to capture the dynamics of Lipschitz continuity under SGD.
result We identify three factors driving the evolution of Lipschitz continuity: gradient flow projection, gradient noise, and Hessian projection.

New method for differentially private optimization with general Lipschitz conditions.

problem Differentially private optimization under general Lipschitz conditions.
method Generalized Lipschitz condition for per-sample gradients, tuning clip norm based on minimum per-sample Lipschitz constant.
result Efficacy of the recommended clip norm tuning method verified on 8 datasets.

The paper examines convergence of distances in Lipschitz structures on manifolds.

problem Convergence of distances in Lipschitz vector fields and norms on manifolds.
method Analysis of convergence of distances associated to converging structures of Lipschitz vector fields and norms.
result Under mild controllability assumption, distances converge locally uniformly to the limit Carnot-Carathéodory distance.

CNN layers with large norms are still robust to adversarial attacks.

problem Understanding the relationship between layer norms and adversarial robustness in CNNs.
method Theoretical analysis of 1\ell_1 and \ell_\infty norms, norm decay method, adversarial training frameworks.
result Adversarially robust CNNs can have comparable or larger layer norms than non-adversarially robust ones.

Generative adversarial networks (GANs) are one of the most popular approaches when it comes to training generative models, among which variants of Wasserstein GANs are considered superior to the standard GAN formulation in terms of learning stability and sample quality. However, Wasserstein GANs require the critic to b…

2019-07-12abs ↗pdf ↗

We study the asymmetry of the Lipschitz metric d on Outer space. We introduce an (asymmetric) Finsler norm that induces d. There is an Out(F_n)-invariant potential Ψon Outer space such that when the Lipschitz norm is corrected by the derivative of Ψ, the resulting norm is quasisymmetric. As an application, we give new …

2009-10-28abs ↗pdf ↗

RVFL networks can efficiently approximate Lipschitz functions in L∞ norm.

problem Efficiently approximating Lipschitz continuous functions in L∞ norm.
method Random Vector Functional Link (RVFL) network with ReLU activation functions, proving approximation in L∞ norm.
result An RVFL with ReLU activation functions can approximate Lipschitz continuous functions in L∞ norm.

We show that the log-likelihood of several probabilistic graphical models is Lipschitz continuous with respect to the lp-norm of the parameters. We discuss several implications of Lipschitz parametrization. We present an upper bound of the Kullback-Leibler divergence that allows understanding methods that penalize the …

2012-02-14abs ↗pdf ↗

We investigate the effect of explicitly enforcing the Lipschitz continuity of neural networks with respect to their inputs. To this end, we provide a simple technique for computing an upper bound to the Lipschitz constant---for multiple pp-norms---of a feed forward neural network composed of commonly used layer types.…

2018-04-12abs ↗pdf ↗

Revisits shallow neural networks using Lipschitz norms and measures.

problem Existence and compactness of minimizers in neural network formulations.
method Mean field parametrization, signed measures, duality pairings, Kantorovich-Rubinstein norms.
result Compactness results and uniform large data limits for empirical risk minimization.

Proves continuum limits of Lipschitz learning using Γ-convergence.

problem Semi-supervised learning with graph-based methods and continuum limits of pp-Laplacian learning.
method Proves continuum limits of Lipschitz learning using Γ-convergence.
result Proves ΓΓ-convergence in the LL^\infty-topology to the supremum norm of the gradient.

The paper examines partial regularity of Lipschitz solutions to minimal surface system.

problem Understanding the regularity of solutions to the minimal surface system.
method Investigation of stationary, integral weak, and viscosity solutions; interior gradient estimate using maximum principle.
result Partial regularity results for Lipschitz solutions, including interior gradient estimate.

New bounds for neural networks ensure robustness and accuracy.

problem Ensuring robustness of neural networks by computing Lipschitz constants.
method Analyzed and proposed new bounds for l1l^1 and ll^\infty norms, using explicit and implicit methods for convnets.
result One of the new bounds is optimal and more accurate than existing ones.

We present a lower bound for a fragmentation norm and construct a bi-Lipschitz embedding I ⁣:RnHam(M)I\colon \mathbb{R}^n\to\mathrm{Ham}(M) with respect to the fragmentation norm on the group Ham(M)\mathrm{Ham}(M) of Hamiltonian diffeomorphisms of a symplectic manifold (M,ω)(M,ω). As an application, we provide an answer to Brandenbursk…

2019-01-07abs ↗pdf ↗

PSiLON Net uses L1L_1 weight normalization and 1-path-norm regularization for efficient learning and sparsity.

problem Efficient learning and sparsity in neural networks with limited data.
method PSiLON Net employs L1L_1 weight normalization and 1-path-norm regularization to simplify the 1-path-norm and achieve efficient learning and near-sparse parameters.
result PSiLON Net achieves reliable optimization and strong performance in the small data regime.

We consider the mean curvature flow of entire Lagrangian graphs with Lipschitz continuous initial data. Assuming only a certain bound on the Lipschitz norm of an initial entire Lagrangian graph in R2n\R^{2n}, we show that the parabolic equation \eqref{PMA} for the Lagrangian potential has a longtime solution which is sm…

2009-02-19abs ↗pdf ↗

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.

The paper explores how close two Lipschitz functions can be without their difference exceeding a certain bound.

problem Understanding the closeness of two Lipschitz functions and their difference.
method Investigates the relationship between two Lip(γ)(\gamma) functions being close throughout a subset of their domain and the bound on the difference's Lipschitz norm.
result The Lipschitz norm of the difference between two functions is bounded by a small value when the distance to a subset is small.

The mean curvature flow is the gradient flow of volume functionals on the space of submanifolds. We prove a fundamental regularity result of the mean curvature flow in this paper: a Lipschitz submanifold with small local Lipschitz norm becomes smooth instantly along the mean curvature flow. This generalizes the regular…

2002-09-14abs ↗pdf ↗

The purpose of the paper is to characterize the dimension of sublinear Higson corona νL(X)ν_L(X) of XX in terms of Lipschitz extensions of functions: Theorem: Suppose (X,d)(X,d) is a proper metric space. The dimension of the sublinear Higson corona νL(X)ν_L(X) of XX is the smallest integer m0m\ge 0 with the following property…

2006-08-28abs ↗pdf ↗

The paper shows how Hamiltonian diffeomorphisms and homeomorphisms can be broken down into smaller, manageable pieces.

problem Fragmenting Hamiltonian diffeomorphisms and homeomorphisms on surfaces.
method Develops a C0C^0-fragmentation property for Hamiltonian diffeomorphisms and homeomorphisms on surfaces, proving it with a Lipschitz estimate.
result Hamiltonian diffeomorphisms and homeomorphisms can be decomposed into smaller, compactly supported pieces with a Lipschitz estimate on the C0C^0-norm.

New approach to certifiably robust neural networks using Boolean function perspective.

problem Lack of principled understanding and certified robustness for \ell_\infty perturbations.
method New perspective on Boolean functions, deriving impossibility results, and developing a unified Lipschitz network.
result Unified Lipschitz network that bypasses expressive power limitations and achieves better certified robustness.

Let AA be an expanding d×dd\times d matrix with integer entries and DZd{\mathcal D}\subset {\mathbb Z}^d be a finite digit set. Then the pair (A,D)(A, {\mathcal D}) defines a unique integral self-affine set K=A1(K+D)K=A^{-1}(K+{\mathcal D}). In this paper, by replacing the Euclidean norm with a pseudo-norm ww in terms of AA, we…

2017-04-24abs ↗pdf ↗

We show the existence of a global unique and analytic solution for the mean curvature flow, the surface diffusion flow and the Willmore flow of entire graphs for Lipschitz initial data with small Lipschitz norm. We also show the existence of a global unique and analytic solution to the Ricci-DeTurck flow on euclidean s…

2009-02-09abs ↗pdf ↗

Characterizes isometries between non-reversible Finsler manifolds.

problem Understanding isometries in non-reversible Finsler manifolds.
method Generalization of Myers-Nakai Theorem for Riemannian manifolds, modification of function spaces to accommodate asymmetric structure.
result Functional characterization of isometries between non-reversible Finsler manifolds.

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.

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.

Efficient local Lipschitz bounds improve neural network robustness.

problem Certifying robustness of neural networks is challenging and often leads to over-regularization.
method Proposes an efficient trainable local Lipschitz upper bound by considering activation functions and weight matrices.
result Consistently outperforms state-of-the-art methods in clean and certified accuracy on various datasets.