Stochastic Subgradient Methods with Guaranteed Global Stability in Nonsmooth Nonconvex Optimization
- URL: http://arxiv.org/abs/2307.10053v4
- Date: Sat, 12 Oct 2024 08:04:20 GMT
- Title: Stochastic Subgradient Methods with Guaranteed Global Stability in Nonsmooth Nonconvex Optimization
- Authors: Nachuan Xiao, Xiaoyin Hu, Kim-Chuan Toh,
- Abstract summary: We first investigate a general framework for subgradient methods, where the corresponding differential inclusion admits a coercive Lyapunov function.
We develop an improved analysis to apply proposed framework to establish the global stability of a wide range of subgradient methods, where the corresponding Lyapunov functions are possibly non-coercive.
- Score: 3.0586855806896045
- License:
- Abstract: In this paper, we focus on providing convergence guarantees for stochastic subgradient methods in minimizing nonsmooth nonconvex functions. We first investigate the global stability of a general framework for stochastic subgradient methods, where the corresponding differential inclusion admits a coercive Lyapunov function. We prove that, for any sequence of sufficiently small stepsizes and approximation parameters, coupled with sufficiently controlled noises, the iterates are uniformly bounded and asymptotically stabilize around the stable set of its corresponding differential inclusion. Moreover, we develop an improved analysis to apply our proposed framework to establish the global stability of a wide range of stochastic subgradient methods, where the corresponding Lyapunov functions are possibly non-coercive. These theoretical results illustrate the promising potential of our proposed framework for establishing the global stability of various stochastic subgradient methods.
Related papers
- On the Selection Stability of Stability Selection and Its Applications [2.263635133348731]
This paper seeks to broaden the use of an established stability estimator to evaluate the overall stability of the stability selection framework.
We suggest that the stability estimator offers two advantages: it can serve as a reference to reflect the robustness of the outcomes obtained and help identify an optimal regularization value to improve stability.
arXiv Detail & Related papers (2024-11-14T00:02:54Z) - Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models [57.52124921268249]
We propose a Trust Sequential Quadratic Programming method to find both first and second-order stationary points.
To converge to first-order stationary points, our method computes a gradient step in each iteration defined by minimizing a approximation of the objective subject.
To converge to second-order stationary points, our method additionally computes an eigen step to explore the negative curvature the reduced Hessian matrix.
arXiv Detail & Related papers (2024-09-24T04:39:47Z) - A Unified Theory of Stochastic Proximal Point Methods without Smoothness [52.30944052987393]
Proximal point methods have attracted considerable interest owing to their numerical stability and robustness against imperfect tuning.
This paper presents a comprehensive analysis of a broad range of variations of the proximal point method (SPPM)
arXiv Detail & Related papers (2024-05-24T21:09:19Z) - FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse
optimisation on Measures [1.9950682531209156]
This paper presents a novel algorithm that leverages Gradient Descent strategies in conjunction with Random Features to augment the scalability of Conic Particle Gradient Descent (CPGD)
We provide rigorous proofs demonstrating the following key findings: (i) The total variation norms of the solution measures along the descent trajectory remain bounded, ensuring stability and preventing undesirable divergence; (ii) We establish a global convergence guarantee with a convergence rate of $mathcalO(log(K)/sqrtK)$ over $K$, showcasing the efficiency and effectiveness of our algorithm; (iii) Additionally, we analyze and establish
arXiv Detail & Related papers (2023-12-10T20:41:43Z) - Fully Stochastic Trust-Region Sequential Quadratic Programming for
Equality-Constrained Optimization Problems [62.83783246648714]
We propose a sequential quadratic programming algorithm (TR-StoSQP) to solve nonlinear optimization problems with objectives and deterministic equality constraints.
The algorithm adaptively selects the trust-region radius and, compared to the existing line-search StoSQP schemes, allows us to utilize indefinite Hessian matrices.
arXiv Detail & Related papers (2022-11-29T05:52:17Z) - Stability and Generalization for Markov Chain Stochastic Gradient
Methods [49.981789906200035]
We provide a comprehensive generalization analysis of MC-SGMs for both minimization and minimax problems.
We establish the optimal excess population risk bounds for both smooth and non-smooth cases.
We develop the first nearly optimal convergence rates for convex-concave problems both in expectation and with high probability.
arXiv Detail & Related papers (2022-09-16T15:42:51Z) - KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed
Stability in Nonlinear Dynamical Systems [66.9461097311667]
We propose a model-based reinforcement learning framework with formal stability guarantees.
The proposed method learns the system dynamics up to a confidence interval using feature representation.
We show that KCRL is guaranteed to learn a stabilizing policy in a finite number of interactions with the underlying unknown system.
arXiv Detail & Related papers (2022-06-03T17:27:04Z) - A Local Convergence Theory for the Stochastic Gradient Descent Method in
Non-Convex Optimization With Non-isolated Local Minima [0.0]
Non-isolated minima presents a unique challenge that has remained under-explored.
In this paper, we study the local convergence of the gradient descent method to non-isolated global minima.
arXiv Detail & Related papers (2022-03-21T13:33:37Z) - Fine-Grained Analysis of Stability and Generalization for Stochastic
Gradient Descent [55.85456985750134]
We introduce a new stability measure called on-average model stability, for which we develop novel bounds controlled by the risks of SGD iterates.
This yields generalization bounds depending on the behavior of the best model, and leads to the first-ever-known fast bounds in the low-noise setting.
To our best knowledge, this gives the firstever-known stability and generalization for SGD with even non-differentiable loss functions.
arXiv Detail & Related papers (2020-06-15T06:30:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.