arXiv math/06015302006-01-22math.OC

Clarke subgradients of stratifiable functions

J. Bolte, A. Daniilidis, A. S. Lewis, M. Shiota

英文摘要：

We establish the following result: if the graph of a (nonsmooth) real-extended-valued function $f:\mathbb{R}^{n}\to \mathbb{R}\cup\{+\infty\}$ is closed and admits a Whitney stratification, then the norm of the gradient of $f$ at $x\in{dom}f$ relative to the stratum containing $x$ bounds from below all norms of Clarke subgradients of $f$ at $x$. As a consequence, we obtain some Morse-Sard type theorems as well as a nonsmooth Kurdyka-Łojasiewicz inequality for functions definable in an arbitrary o-minimal structure.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Clarke subgradients for directionally Lipschitzian stratifiable functions

Using a geometric argument, we show that under a reasonable continuity condition, the Clarke subdifferential of a semi-algebraic (or more generally stratifiable) directionally Lipschitzian function admits a simple form: the normal cone to the domain and limits of gradients generate the entire Clarke subdifferential. The characterization formula we obtain unifies various apparently disparate results that have appeared in the literature. Our techniques also yield a simplified proof that closed semialgebraic functions on $\R^n$ have a limiting subdifferential graph of uniform local dimension $n$.

2012-11-15math.OC

Clarke切锥、次梯度、最优性条件以及无穷远处的Lipschitz性

Clarke's tangent cones, subgradients, optimality conditions and the Lipschitzness at infinity

该研究针对$\n\mathbb{R}^n$中的无约束优化相关问题，分析了无穷远处Clarke切锥的性质，推导了无穷远次梯度的计算规则与优化的必要最优性条件，还刻画了下半连续函数的无穷远Lipschitz连续性。

2024-05-16math.CAmath.OC

Stochastic subgradient method converges on tame functions

Cornell University（康奈尔大学）；University of Washington（华盛顿大学）；University of Southern California（南加利福尼亚大学）

This work considers the question: what convergence guarantees does the stochastic subgradient method have in the absence of smoothness and convexity? We prove that the stochastic subgradient method, on any semialgebraic locally Lipschitz function, produces limit points that are all first-order stationary. More generally, our result applies to any function with a Whitney stratifiable graph. In particular, this work endows the stochastic subgradient method, and its proximal extension, with rigorous convergence guarantees for a wide class of problems arising in data science---including all popula…

2018-05-26cs.LGmath.OC

基于高斯平滑的零阶非光滑非凸优化

Zeroth-Order Non-smooth Non-convex Optimization via Gaussian Smoothing

Indian Institute of Science（印度科学学院）

针对仅含噪声函数值的Lipschitz连续非光滑非凸优化问题，提出一种双时间尺度零阶投影随机次梯度方法，利用高斯平滑逼近Clarke次微分，并证明迭代几乎必然收敛到Clarke驻点邻域。

2026-06-01math.OC

半代数函数上随机次梯度方法的非极小吸引子

Nonminimizing Attractors of Stochastic Subgradient Methods on Semialgebraic Functions

该研究否定了Davis等人2026年的猜想，构造了二维半代数函数，证明随机次梯度方法可收敛到非极小Clarke临界点，为相关算法收敛性分析提供了反例。

2026-10-09math.OC

关于在半代数函数上子梯度下降法收敛速率的分析

On convergence rates of subgradient descent on semialgebraic functions

本文研究了子梯度方法在非光滑非凸函数上的收敛速率，通过几何条件证明了在特定分层结构下，子梯度方法能局部逼近黎曼梯度下降，从而测量站性，并推导出基于分层结构的收敛速率。

2026-04-18math.OC

更多相关论文收起更多论文

Examples of pathological dynamics of the subgradient method for Lipschitz path-differentiable functions

We show that the vanishing stepsize subgradient method -- widely adopted for machine learning applications -- can display rather messy behavior even in the presence of favorable assumptions. We establish that convergence of bounded subgradient sequences may fail even with a Whitney stratifiable objective function satisfying the Kurdyka-Lojasiewicz inequality. Moreover, when the objective function is path-differentiable we show that various properties all may fail to occur: criticality of the limit points, convergence of the sequence, convergence in values, codimension one of the accumulation s…

2020-07-22cs.NAmath.DSmath.NA

A Unified Approach to Convex and Convexified Generalized Differentiation of Nonsmooth Functions and Set-Valued Mappings

In the early 1960's, Moreau and Rockafellar introduced a concept of called \emph{subgradient} for convex functions, initiating the developments of theoretical and applied convex analysis. The needs of going beyond convexity motivated the pioneer works by Clarke considering generalized differentiation theory of Lipschitz continuous functions. Although Clarke generalized differentiation theory is applicable for nonconvex functions, convexity still plays a crucial role in Clarke subdifferential calculus. In the mid 1970's, Mordukhovich developed another generalized differentiation theory for nonc…

2013-08-04math.OC

非光滑非凸优化问题的随机Bregman次梯度方法

Stochastic Bregman Subgradient Methods for Nonsmooth Nonconvex Optimization Problems

本文研究目标函数缺乏Clarke正则性时的随机Bregman次梯度方法，通过微分包含建立收敛性，提出非精确求解与动量集成机制，并验证其在训练非光滑神经网络中的有效性。

2025-05-29math.OC

使用Mifflin线搜索的非光滑非凸优化下降次梯度方法

A descent subgradient method using Mifflin line search for nonsmooth nonconvex optimization

提出一种用于局部Lipschitz非光滑非凸优化的下降次梯度算法，通过迭代近似Goldstein次微分并采用Mifflin线搜索两点变体寻找下降方向，证明了全局收敛性且无需算法修改即可处理非凸性。

2023-04-08math.OC

非光滑非凸函数的去中心化随机子梯度法的收敛性

Convergence of Decentralized Stochastic Subgradient-based Methods for Nonsmooth Nonconvex functions

State Key Laboratory of Scientific and Engineering Computing, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, and University of Chinese Academy of Sciences, China（国家科学工程计算重点实验室，数学系统科学学院，中国科学院，中国科学院大学）

本文提出一个统一去中心化随机子梯度法的框架，为非光滑非凸函数的收敛性提供理论保证，并通过实验验证其在非光滑神经网络训练中的有效性。

2026-01-06cs.LGmath.OC

随机次梯度下降可逃离弱凸函数上的主动严格鞍点

Stochastic Subgradient Descent Escapes Active Strict Saddles on Weakly Convex Functions

该研究在非光滑随机优化中证明，在可定义弱凸函数类中通有成立的Verdier分层与角度条件下，随机次梯度下降不会收敛到主动严格鞍点，而会收敛到局部极小值点。

2023-07-25math.OCstat.ML

非光滑非凸随机重球法

Nonsmooth nonconvex stochastic heavy ball

本文研究非光滑非凸随机重球法的收敛性，结合半代数假设、非光滑微积分与微分包含，证明随机初始化可避免人为临界点并收敛至 Clarke 临界点。

2024-01-23math.OC

非光滑非凸优化中带通信压缩的分布式随机次梯度类方法

Decentralized Stochastic Subgradient-type Methods with Communication Compression for Nonsmooth Nonconvex Optimization

针对非光滑非凸分布式优化问题，提出统一框架整合多种带压缩的随机次梯度方法，证明全局收敛性，并开发基于符号正则化和梯度跟踪动量的新方法。

2026-07-03cs.AIcs.LGmath.OC

A Constraint Dissolving Approach for Nonsmooth Optimization over the Stiefel Manifold

This paper focus on the minimization of a possibly nonsmooth objective function over the Stiefel manifold. The existing approaches either lack efficiency or can only tackle prox-friendly objective functions. We propose a constraint dissolving function named NCDF and show that it has the same first-order stationary points and local minimizers as the original problem in a neighborhood of the Stiefel manifold. Furthermore, we show that the Clarke subdifferential of NCDF is easy to achieve from the Clarke subdifferential of the objective function. Therefore, various existing approaches for unconst…

2023-01-20math.OC

构造二元函数的次梯度：由方向导数出发

Constructing a subgradient from directional derivatives for functions of two variables

本文证明对局部Lipschitz且方向可微的二元函数，可由四个罗盘方向导数构造次梯度，适用于非凸与凸情形，并给出对偶几何结果及示例，但不适用于高维。

2020-06-08cs.NAmath.NAmath.OC

Stochastic Subgradient Descent on a Generic Definable Function Converges to a Minimizer

It was previously shown by Davis and Drusvyatskiy that every Clarke critical point of a generic, semialgebraic (and more generally definable in an o-minimal structure), weakly convex function is lying on an active manifold and is either a local minimum or an active strict saddle. In the first part of this work, we show that when the weak convexity assumption fails a third type of point appears: a sharply repulsive critical point. Moreover, we show that the corresponding active manifolds satisfy the Verdier and the angle conditions which were introduced by us in our previous work. In the second…

2022-02-10math.OCstat.ML

On the complexity of nonsmooth automatic differentiation

Toulouse School of Economics（图卢兹经济学院）；Université de Toulouse（图卢兹大学）；Thales LAS France（法国泰勒斯激光系统公司）；IRIT, CNRS（法国国家科学研究中心信息与电信研究所）；Institut Universitaire de France (IUF)（法国大学研究院）

Using the notion of conservative gradient, we provide a simple model to estimate the computational costs of the backward and forward modes of algorithmic differentiation for a wide class of nonsmooth programs. The overhead complexity of the backward mode turns out to be independent of the dimension when using programs with locally Lipschitz semi-algebraic or definable elementary functions. This considerably extends Baur-Strassen's smooth cheap gradient principle. We illustrate our results by establishing fast backpropagation results of conservative gradients through feedforward neural networks…

2023-02-06cs.AIcs.LGcs.NA