Bilevel Learning with Inexact Stochastic Gradients
- URL: http://arxiv.org/abs/2412.12049v1
- Date: Mon, 16 Dec 2024 18:18:47 GMT
- Title: Bilevel Learning with Inexact Stochastic Gradients
- Authors: Mohammad Sadegh Salehi, Subhadip Mukherjee, Lindon Roberts, Matthias J. Ehrhardt,
- Abstract summary: Bilevel learning has gained prominence in machine learning, inverse problems, and imaging applications.
The large-scale nature of these problems has led to the development of inexact and computationally efficient methods.
- Score: 2.247833425312671
- License:
- Abstract: Bilevel learning has gained prominence in machine learning, inverse problems, and imaging applications, including hyperparameter optimization, learning data-adaptive regularizers, and optimizing forward operators. The large-scale nature of these problems has led to the development of inexact and computationally efficient methods. Existing adaptive methods predominantly rely on deterministic formulations, while stochastic approaches often adopt a doubly-stochastic framework with impractical variance assumptions, enforces a fixed number of lower-level iterations, and requires extensive tuning. In this work, we focus on bilevel learning with strongly convex lower-level problems and a nonconvex sum-of-functions in the upper-level. Stochasticity arises from data sampling in the upper-level which leads to inexact stochastic hypergradients. We establish their connection to state-of-the-art stochastic optimization theory for nonconvex objectives. Furthermore, we prove the convergence of inexact stochastic bilevel optimization under mild assumptions. Our empirical results highlight significant speed-ups and improved generalization in imaging tasks such as image denoising and deblurring in comparison with adaptive deterministic bilevel methods.
Related papers
- A First-order Generative Bilevel Optimization Framework for Diffusion Models [57.40597004445473]
Diffusion models iteratively denoise data samples to synthesize high-quality outputs.
Traditional bilevel methods fail due to infinite-dimensional probability space and prohibitive sampling costs.
We formalize this challenge as a generative bilevel optimization problem.
Our first-order bilevel framework overcomes the incompatibility of conventional bilevel methods with diffusion processes.
arXiv Detail & Related papers (2025-02-12T21:44:06Z) - qNBO: quasi-Newton Meets Bilevel Optimization [26.0555315825777]
Bilevel optimization, addressing challenges in hierarchical learning tasks, has gained significant interest in machine learning.
We introduce a general framework to address these computational challenges in a coordinated manner.
Specifically, we leverage quasi-Newton algorithms to accelerate the resolution of the lower-level problem while efficiently approximating the inverse Hessian-vector product.
arXiv Detail & Related papers (2025-02-03T05:36:45Z) - Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity [59.75300530380427]
We consider the problem of optimizing second-order smooth and strongly convex functions where the algorithm is only accessible to noisy evaluations of the objective function it queries.
We provide the first tight characterization for the rate of the minimax simple regret by developing matching upper and lower bounds.
arXiv Detail & Related papers (2024-06-28T02:56:22Z) - On the Communication Complexity of Decentralized Bilevel Optimization [40.45379954138305]
We propose two novel decentralized bilevel gradient descent algorithms based on simultaneous and alternating update strategies.
Our algorithms can achieve faster convergence rates and lower communication costs than existing methods.
This is the first time such favorable theoretical results have been achieved with mild assumptions in the heterogeneous setting.
arXiv Detail & Related papers (2023-11-19T14:56:26Z) - Scalable Bayesian Meta-Learning through Generalized Implicit Gradients [64.21628447579772]
Implicit Bayesian meta-learning (iBaML) method broadens the scope of learnable priors, but also quantifies the associated uncertainty.
Analytical error bounds are established to demonstrate the precision and efficiency of the generalized implicit gradient over the explicit one.
arXiv Detail & Related papers (2023-03-31T02:10:30Z) - Amortized Implicit Differentiation for Stochastic Bilevel Optimization [53.12363770169761]
We study a class of algorithms for solving bilevel optimization problems in both deterministic and deterministic settings.
We exploit a warm-start strategy to amortize the estimation of the exact gradient.
By using this framework, our analysis shows these algorithms to match the computational complexity of methods that have access to an unbiased estimate of the gradient.
arXiv Detail & Related papers (2021-11-29T15:10:09Z) - Inexact bilevel stochastic gradient methods for constrained and
unconstrained lower-level problems [0.0]
Two-level formula search optimization has become instrumental in a number of machine learning contexts.
New low-rank bi-level gradient methods are developed that do not require second-order derivatives.
arXiv Detail & Related papers (2021-10-01T18:20:14Z) - High Probability Complexity Bounds for Non-Smooth Stochastic Optimization with Heavy-Tailed Noise [51.31435087414348]
It is essential to theoretically guarantee that algorithms provide small objective residual with high probability.
Existing methods for non-smooth convex optimization have complexity bounds with dependence on confidence level.
We propose novel stepsize rules for two methods with gradient clipping.
arXiv Detail & Related papers (2021-06-10T17:54:21Z) - Convergence Properties of Stochastic Hypergradients [38.64355126221992]
We study approximation schemes for the hypergradient, which are important when the lower-level problem is empirical risk on a large dataset.
We provide numerical experiments to support our theoretical analysis and to show the advantage of using hypergradients in practice.
arXiv Detail & Related papers (2020-11-13T20:50:36Z) - Adaptive First-and Zeroth-order Methods for Weakly Convex Stochastic
Optimization Problems [12.010310883787911]
We analyze a new family of adaptive subgradient methods for solving an important class of weakly convex (possibly nonsmooth) optimization problems.
Experimental results indicate how the proposed algorithms empirically outperform its zerothorder gradient descent and its design variant.
arXiv Detail & Related papers (2020-05-19T07:44:52Z) - 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.