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

4589134178 · Jun 202019922001200920182026
48 results for non-smooth potentials

Extends diffuse interface methods to graphs and hypergraphs with non-smooth potentials.

problem Semi-supervised learning on graphs and hypergraphs.
method Generalizes diffuse interface methods using non-smooth potential functions and hypergraph Laplacians.
result The diffuse interface method can be applied to both graph and hypergraph data.

This work defines mean curvature in non-smooth spaces and proves sharp inequalities.

problem Defining and proving geometric inequalities in non-smooth metric spaces.
method Introducing mean curvature for level sets in non-smooth spaces and proving sharp inequalities.
result Mean curvature vectors in non-smooth spaces satisfy sharp Willmore inequalities.

Expanding FCCO to non-smooth weakly-convex problems, improving deep learning performance.

problem Addressing the limitations of current FCCO methods by tackling non-smooth weakly-convex problems.
method Developed a single-loop algorithm for non-smooth weakly-convex FCCO and extended it to tri-level problems.
result Established the complexity for finding ε-stationary points in the Moreau envelop of the objective function.

This work improves SGMs' convergence guarantees for semiconvex distributions with discontinuous gradients.

problem Establishing convergence guarantees for SGMs under weak regularity conditions.
method Developed non-asymptotic Wasserstein-2 convergence analysis for SGMs targeting semiconvex distributions with discontinuous gradients.
result Achieved optimal dependence of O(d)O(\sqrt{d}) on data dimension dd and convergence rate of order one.

Investigates training challenges for morphological neural networks.

problem Training morphological neural networks with gradient descent is difficult.
method Examines differentiation and backpropagation for morphological networks, using Bouligand derivative.
result Provides theoretical insights and guidelines for initialization and learning rates.

A new optimization method, BPM, converges linearly in non-convex, non-smooth problems.

problem Non-smooth and non-convex optimization challenges.
method Ball-Proximal Point Method (BPM), inspired by Proximal Point Method (PPM).
result BPM converges linearly and in a finite number of steps in non-convex, non-smooth problems.

MARINA-P improves non-smooth federated optimization with adaptive stepsizes.

problem Non-smooth federated optimization in machine learning applications.
method Extends EF21-P and MARINA-P to non-smooth convex setting, proving optimal convergence rate and communication complexity bounds.
result MARINA-P achieves O(1/T)O(1/\sqrt{T}) convergence rate and communication complexity matching classical subgradient methods.

We introduce non-smooth symplectic forms on manifolds and describe corresponding Poisson structures on the algebra of Colombeau generalized functions. This is achieved by establishing an extension of the classical map of smooth functions to Hamiltonian vector fields to the setting of non-smooth geometry. For mildly sin…

2014-03-02abs ↗pdf ↗

New bounds explain deterministic non-smooth deep nets without large Lipschitz constants.

problem Challenges in explaining generalization of deterministic non-smooth deep nets.
method De-randomized PAC-Bayes margin bounds for deterministic non-convex and non-smooth predictors.
result New bounds avoid large Lipschitz constants, providing generalization guarantees.

The paper explores various stationarity concepts in non-smooth optimization.

problem Understanding stationarity in non-smooth optimization problems.
method Introduction and discussion of different stationarity concepts for non-convex non-smooth functions.
result Clarification of the relationship among different stationarity concepts and their relevance in iterative methods.

Smoothness analysis of adversarial training reveals LL_\infty constraints cause more non-smoothness.

problem Non-smoothness of adversarial training loss function.
method Analyzed the smoothness of adversarial training loss function using optimal attacks for model parameters.
result The LL_\infty constraint causes more non-smoothness than L2L_2 constraint.

In the framework of Lorentzian warped products, we study the Friedmann-Robertson-Walker cosmological model to investigate non-smooth curvatures associated with multiple discontinuities involved in the evolution of the universe. In particular we analyze non-smooth features of the spatially flat Friedmann-Robertson-Walke…

2003-08-16abs ↗pdf ↗

Improved non-smooth optimization methods achieve faster convergence rates.

problem Non-smooth optimization problems, especially in \ell_\infty and 1\ell_1-SVM.
method Higher-order accelerated methods, leveraging recent advances in smooth convex optimization.
result Achieved O(ε4/5)O(ε^{-4/5}) iteration complexity for \ell_\infty regression, breaking previous barriers.

This work speeds up hyperparameter selection for non-smooth convex models using implicit differentiation.

problem Optimizing hyperparameters of non-smooth convex models.
method Implicit differentiation of proximal gradient and coordinate descent methods.
result Implicit differentiation can speed up hyperparameter optimization, especially for non-smooth problems.

Synthetic framework for null hypersurfaces in non-smooth spacetimes.

problem Analyzing null hypersurfaces in non-smooth spacetimes.
method Develops synthetic null hypersurfaces using optimal transport and Lorentzian geometry.
result Synthetic null energy condition stabilizes under convergence and applies to low-regularity spacetimes.

Deep neural networks excel at learning non-smooth functions.

problem Understanding why deep neural networks perform better for non-smooth functions.
method Theoretical analysis of statistical properties of deep neural networks for non-smooth functions.
result Deep neural networks achieve almost optimal generalization error for non-smooth functions.

Positive mass theorem for non-smooth metrics on flat manifolds with corners.

problem Proving a positive mass theorem for non-smooth metrics on asymptotically flat manifolds with non-compact boundary.
method Proves a positive mass theorem for metrics that are only continuous across a compact hypersurface.
result Obtains a positive mass theorem on manifolds with non-compact corners.

Advances smooth over-parameterization for solving non-smooth optimization problems.

problem Non-smooth optimization with structural constraints in imaging and machine learning.
method Smooth over-parameterization of non-smooth problems, using gradient descent and mirror descent.
result Gradient descent on the reformulated smooth problem converges efficiently without parameter tuning.

The study analyzes methods for solving non-convex, non-smooth optimization problems.

problem Finding critical points of non-convex and non-smooth functions.
method Gradient descent, proximal update, Frank-Wolfe update methods for general and continuous sub-analytic functions.
result Established rates of convergence and faster rates for specific function classes.

New methods improve convergence in non-convex non-smooth learning problems.

problem Sparse learning from high-dimensional data with non-convex, non-smooth regularizers.
method Stochastic proximal gradient methods with arbitrary sampling.
result Independent sampling improves performance over uniform sampling.

Proposes a differentiable LSE-ICNN for modeling multi-well potentials.

problem Modeling multi-well potentials in various scientific domains.
method Log-sum-exponential (LSE) mixture of input convex neural network (ICNN) modes.
result Smooth surrogate that retains convexity within basins and allows gradient-based learning.

The study analyzes convergence rates for sparse pivotal estimators in high-dimensional regression.

problem Sparse pivotal estimation in high-dimensional regression problems.
method Theoretical analysis and comparison of non-smooth + non-smooth optimization problems, including smoothing techniques.
result Minimax sup-norm convergence rates for square-root Lasso-type estimators are derived.

New SPS variant improves non-smooth optimization without small gradients.

problem Improving non-smooth optimization without small gradients.
method Safeguarded Stochastic Polyak Step Size (SPSsafe_{safe}) for non-smooth optimization.
result Rigorous convergence guarantees for non-smooth convex optimization without strong assumptions.

Optimizes deep learning pipelines with novel algorithms for smooth and non-smooth functions.

problem Optimizing deep learning pipelines for smooth and non-smooth functions.
method Provided matching lower and upper bounds for smooth convex and non-convex functions, and developed PPRS for non-smooth convex functions.
result PPRS achieves near-linear speed-up and convergence time for non-smooth non-convex problems.

Stochastic approximation proves asymptotic normality for non-smooth problems.

problem Solving non-smooth stochastic approximation problems.
method Stochastic approximation algorithms for solving smooth equations, extended to non-smooth problems.
result Asymptotic normality and optimality in non-smooth stochastic approximation is proven.

Study of spectral gaps in non-smooth spaces with bounded Ricci curvature.

problem Analyzing spectral gaps in non-smooth metric measure spaces.
method Establishing a Polya-Szego type inequality and applying it to show spectral gaps for the p-Laplace operator.
result Sharp spectral gap results for the p-Laplace operator on various non-smooth spaces.

Study weak Frenet frame for non-smooth curves with finite curvature and torsion.

problem Defining weak binormal and normal for non-smooth curves with finite total curvature and torsion.
method Piecewise linear methods and density argument applied to polygonal curves.
result Weak binormal and normal are rectifiable curves agreeing with total absolute torsion and vector product of tangent indicatrix and weak binormal.

We consider first order gradient methods for effectively optimizing a composite objective in the form of a sum of smooth and, potentially, non-smooth functions. We present accelerated and adaptive gradient methods, called FLAG and FLARE, which can offer the best of both worlds. They can achieve the optimal convergence …

2016-05-26abs ↗pdf ↗

Safe-EF improves federated learning for non-smooth, constrained optimization.

problem Federated learning's communication bottlenecks with high-dimensional model updates.
method Error feedback (EF) for non-smooth convex optimization with safety constraints.
result Safe-EF matches lower complexity bounds and ensures safety constraints.