Projected gradient methods for nonconvex and stochastic optimization: new complexities and auto-conditioned stepsizes
- URL: http://arxiv.org/abs/2412.14291v1
- Date: Wed, 18 Dec 2024 19:34:16 GMT
- Title: Projected gradient methods for nonconvex and stochastic optimization: new complexities and auto-conditioned stepsizes
- Authors: Guanghui Lan, Tianjiao Li, Yangyang Xu,
- Abstract summary: We present a class of projected gradient (PG) methods for minimizing a smooth but not necessarily convex function over a convex compact set.
We first provide a novel analysis of the "vanilla" PG method, achieving the best-known iteration complexity for finding an approximate stationary point.
We then develop an "auto-conditioned" projected gradient (AC-PG) variant that achieves the same iteration complexity without requiring the input of the Lipschitz constant.
- Score: 19.353306324883125
- License:
- Abstract: We present a novel class of projected gradient (PG) methods for minimizing a smooth but not necessarily convex function over a convex compact set. We first provide a novel analysis of the "vanilla" PG method, achieving the best-known iteration complexity for finding an approximate stationary point of the problem. We then develop an "auto-conditioned" projected gradient (AC-PG) variant that achieves the same iteration complexity without requiring the input of the Lipschitz constant of the gradient or any line search procedure. The key idea is to estimate the Lipschitz constant using first-order information gathered from the previous iterations, and to show that the error caused by underestimating the Lipschitz constant can be properly controlled. We then generalize the PG methods to the stochastic setting, by proposing a stochastic projected gradient (SPG) method and a variance-reduced stochastic gradient (VR-SPG) method, achieving new complexity bounds in different oracle settings. We also present auto-conditioned stepsize policies for both stochastic PG methods and establish comparable convergence guarantees.
Related papers
- An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes [17.804065824245402]
In machine learning applications, each loss function is non-negative and can be expressed as the composition of a square and its real-valued square root.
We show how to apply the Gauss-Newton method or the Levssquardt method to minimize the average of smooth but possibly non-negative functions.
arXiv Detail & Related papers (2024-07-05T08:53:06Z) - Flattened one-bit stochastic gradient descent: compressed distributed optimization with controlled variance [55.01966743652196]
We propose a novel algorithm for distributed gradient descent (SGD) with compressed gradient communication in the parameter-server framework.
Our gradient compression technique, named flattened one-bit gradient descent (FO-SGD), relies on two simple algorithmic ideas.
arXiv Detail & Related papers (2024-05-17T21:17:27Z) - Cyclic Block Coordinate Descent With Variance Reduction for Composite
Nonconvex Optimization [26.218670461973705]
We propose methods for solving problems coordinate non-asymptotic gradient norm guarantees.
Our results demonstrate the efficacy of the proposed cyclic-reduced scheme in training deep neural nets.
arXiv Detail & Related papers (2022-12-09T19:17:39Z) - A Stochastic Proximal Method for Nonsmooth Regularized Finite Sum
Optimization [7.014966911550542]
We consider the problem of training a deep neural network with nonsmooth regularization to retrieve a sparse sub-structure.
We derive a new solver, called SR2, whose convergence and worst-case complexity are established without knowledge or approximation of the gradient's Lipschitz constant.
Experiments on network instances trained on CIFAR-10 and CIFAR-100 show that SR2 consistently achieves higher sparsity and accuracy than related methods such as ProxGEN and ProxSGD.
arXiv Detail & Related papers (2022-06-14T00:28:44Z) - Faster One-Sample Stochastic Conditional Gradient Method for Composite
Convex Minimization [61.26619639722804]
We propose a conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms.
The proposed method, equipped with an average gradient (SAG) estimator, requires only one sample per iteration. Nevertheless, it guarantees fast convergence rates on par with more sophisticated variance reduction techniques.
arXiv Detail & Related papers (2022-02-26T19:10:48Z) - COCO Denoiser: Using Co-Coercivity for Variance Reduction in Stochastic
Convex Optimization [4.970364068620608]
We exploit convexity and L-smoothness to improve the noisy estimates outputted by the gradient oracle.
We show that increasing the number and proximity of the queried points leads to better gradient estimates.
We also apply COCO in vanilla settings by plugging it in existing algorithms, such as SGD, Adam or STRSAGA.
arXiv Detail & Related papers (2021-09-07T17:21:09Z) - On the Convergence of Stochastic Extragradient for Bilinear Games with
Restarted Iteration Averaging [96.13485146617322]
We present an analysis of the ExtraGradient (SEG) method with constant step size, and present variations of the method that yield favorable convergence.
We prove that when augmented with averaging, SEG provably converges to the Nash equilibrium, and such a rate is provably accelerated by incorporating a scheduled restarting procedure.
arXiv Detail & Related papers (2021-06-30T17:51:36Z) - Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box
Optimization Framework [100.36569795440889]
This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information.
We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
arXiv Detail & Related papers (2020-12-21T17:29:58Z) - Balancing Rates and Variance via Adaptive Batch-Size for Stochastic
Optimization Problems [120.21685755278509]
In this work, we seek to balance the fact that attenuating step-size is required for exact convergence with the fact that constant step-size learns faster in time up to an error.
Rather than fixing the minibatch the step-size at the outset, we propose to allow parameters to evolve adaptively.
arXiv Detail & Related papers (2020-07-02T16:02:02Z) - Explicit Regularization of Stochastic Gradient Methods through Duality [9.131027490864938]
We propose randomized Dykstra-style algorithms based on randomized dual coordinate ascent.
For accelerated coordinate descent, we obtain a new algorithm that has better convergence properties than existing gradient methods in the interpolating regime.
arXiv Detail & Related papers (2020-03-30T20:44:56Z) - Towards Better Understanding of Adaptive Gradient Algorithms in
Generative Adversarial Nets [71.05306664267832]
Adaptive algorithms perform gradient updates using the history of gradients and are ubiquitous in training deep neural networks.
In this paper we analyze a variant of OptimisticOA algorithm for nonconcave minmax problems.
Our experiments show that adaptive GAN non-adaptive gradient algorithms can be observed empirically.
arXiv Detail & Related papers (2019-12-26T22:10:10Z)
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.