Stochastic First-Order Methods with Non-smooth and Non-Euclidean Proximal Terms for Nonconvex High-Dimensional Stochastic Optimization
- URL: http://arxiv.org/abs/2406.19475v1
- Date: Thu, 27 Jun 2024 18:38:42 GMT
- Title: Stochastic First-Order Methods with Non-smooth and Non-Euclidean Proximal Terms for Nonconvex High-Dimensional Stochastic Optimization
- Authors: Yue Xie, Jiawen Bi, Hongcheng Liu,
- Abstract summary: When the non problem is by which the non problem is by whichity, the sample of first-order methods may depend linearly on the problem dimension, is for undesirable problems.
Our algorithms allow for the estimate of complexity using the distance of.
mathO (log d) / EuM4.
We prove that DISFOM can sharpen variance employing $mathO (log d) / EuM4.
- Score: 2.0657831823662574
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: When the nonconvex problem is complicated by stochasticity, the sample complexity of stochastic first-order methods may depend linearly on the problem dimension, which is undesirable for large-scale problems. In this work, we propose dimension-insensitive stochastic first-order methods (DISFOMs) to address nonconvex optimization with expected-valued objective function. Our algorithms allow for non-Euclidean and non-smooth distance functions as the proximal terms. Under mild assumptions, we show that DISFOM using minibatches to estimate the gradient enjoys sample complexity of $ \mathcal{O} ( (\log d) / \epsilon^4 ) $ to obtain an $\epsilon$-stationary point. Furthermore, we prove that DISFOM employing variance reduction can sharpen this bound to $\mathcal{O} ( (\log d)^{2/3}/\epsilon^{10/3} )$, which perhaps leads to the best-known sample complexity result in terms of $d$. We provide two choices of the non-smooth distance functions, both of which allow for closed-form solutions to the proximal step. Numerical experiments are conducted to illustrate the dimension insensitive property of the proposed frameworks.
Related papers
- Diffusion Stochastic Optimization for Min-Max Problems [33.73046548872663]
The optimistic gradient method is useful in addressing minimax optimization problems.
Motivated by the observation that the conventional version suffers from the need for a large batch size, we introduce and analyze a new formulation termed Samevareps-generativeOGOG.
arXiv Detail & Related papers (2024-01-26T01:16:59Z) - A Fully First-Order Method for Stochastic Bilevel Optimization [8.663726907303303]
We consider unconstrained bilevel optimization problems when only the first-order gradient oracles are available.
We propose a Fully First-order Approximation (F2SA) method, and study its non-asymptotic convergence properties.
We demonstrate even superior practical performance of the proposed method over existing second-order based approaches on MNIST data-hypercleaning experiments.
arXiv Detail & Related papers (2023-01-26T05:34:21Z) - A Newton-CG based barrier-augmented Lagrangian method for general
nonconvex conic optimization [77.8485863487028]
In this paper we consider finding an approximate second-order stationary point (SOSP) that minimizes a twice different subject general non conic optimization.
In particular, we propose a Newton-CG based-augmentedconjugate method for finding an approximate SOSP.
arXiv Detail & Related papers (2023-01-10T20:43:29Z) - Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation
Constrained Optimization [88.0031283949404]
Many real-world problems have complicated non functional constraints and use a large number of data points.
Our proposed method outperforms an existing method with the previously best-known result.
arXiv Detail & Related papers (2022-12-19T14:48:54Z) - Explicit Second-Order Min-Max Optimization Methods with Optimal Convergence Guarantee [86.05440220344755]
We propose and analyze inexact regularized Newton-type methods for finding a global saddle point of emphcon unconstrained min-max optimization problems.
We show that the proposed methods generate iterates that remain within a bounded set and that the iterations converge to an $epsilon$-saddle point within $O(epsilon-2/3)$ in terms of a restricted function.
arXiv Detail & Related papers (2022-10-23T21:24:37Z) - Gradient-Free Methods for Deterministic and Stochastic Nonsmooth
Nonconvex Optimization [94.19177623349947]
Non-smooth non optimization problems emerge in machine learning and business making.
Two core challenges impede the development of efficient methods with finitetime convergence guarantee.
Two-phase versions of GFM and SGFM are also proposed and proven to achieve improved large-deviation results.
arXiv Detail & Related papers (2022-09-12T06:53:24Z) - A Newton-CG based barrier method for finding a second-order stationary
point of nonconvex conic optimization with complexity guarantees [0.5922488908114022]
We consider finding an approximate second-order stationary point (SOSP) that minimizes a twice differentiable function intersection.
Our method is not only iteration, but also achieves $mincal O(epsilon/2) which matches the best known complexity.
arXiv Detail & Related papers (2022-07-12T17:21:45Z) - A Projection-free Algorithm for Constrained Stochastic Multi-level
Composition Optimization [12.096252285460814]
We propose a projection-free conditional gradient-type algorithm for composition optimization.
We show that the number of oracles and the linear-minimization oracle required by the proposed algorithm, are of order $mathcalO_T(epsilon-2)$ and $mathcalO_T(epsilon-3)$ respectively.
arXiv Detail & Related papers (2022-02-09T06:05:38Z) - Mean-Square Analysis with An Application to Optimal Dimension Dependence
of Langevin Monte Carlo [60.785586069299356]
This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance.
Our theoretical analysis is further validated by numerical experiments.
arXiv Detail & Related papers (2021-09-08T18:00:05Z) - Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions [84.49087114959872]
We provide the first non-asymptotic analysis for finding stationary points of nonsmooth, nonsmooth functions.
In particular, we study Hadamard semi-differentiable functions, perhaps the largest class of nonsmooth functions.
arXiv Detail & Related papers (2020-02-10T23:23:04Z)
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.