paper-with-me

Papers

On Implicit Bias in Overparameterized Bilevel Optimization

2022-12-28 · Paul Vicol, Jonathan Lorraine, Fabian Pedregosa, David Duvenaud, Roger Grosse

Many problems in machine learning involve bilevel optimization (BLO), including hyperparameter optimization, meta-learning, and dataset distillation. Bilevel problems consist of two nested sub-problems, called the outer and inner problems, respectively. In practice, often at least one of these sub-problems is overparameterized. In this case, there are many ways to choose among optima that achieve equivalent objective values. Inspired by recent studies of the implicit bias induced by optimization algorithms in single-level optimization, we investigate the implicit bias of gradient-based algorithms for bilevel optimization. We delineate two standard BLO methods -- cold-start and warm-start -- and show that the converged solution or long-run behavior depends to a large degree on these and other algorithmic choices, such as the hypergradient approximation. We also show that the inner solutions obtained by warm-start BLO can encode a surprising amount of information about the outer objective, even when the outer parameters are low-dimensional. We believe that implicit bias deserves as central a role in the study of bilevel optimization as it has attained in the study of single-level neural net optimization.

📄 PDF Abstract BibTeX arXiv:2212.14032

Code (0)

등록된 구현이 없습니다.

Tasks

Bilevel OptimizationDataset DistillationHyperparameter OptimizationMeta-Learning

Similar Papers 제목 키워드 기반

Amortized Implicit Differentiation for Stochastic Bilevel Optimization

2021-11-29 · ICLR 2022 4 · Michael Arbel, Julien Mairal

We study a class of algorithms for solving bilevel optimization problems in both stochastic and deterministic settings when the inner-level objective is strongly convex. Specifically, we consider algorithms based on inex…

Bilevel Optimization

Robust Implicit Regularization via Weight Normalization

2023-05-09 · Hung-Hsu Chou, Holger Rauhut, Rachel Ward

Overparameterized models may have many interpolating solutions; implicit regularization refers to the hidden preference of a particular optimization method towards a certain interpolating solution among the many. A by no…

Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization

2022-11-14 · Quan Xiao, Han Shen, Wotao Yin, Tianyi Chen

Stochastic bilevel optimization, which captures the inherent nested structure of machine learning problems, is gaining popularity in many recent applications. Existing works on bilevel optimization mostly consider either…

Bilevel Optimization

Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction

2021-06-28 · NeurIPS 2021 12 · Dominik Stöger, Mahdi Soltanolkotabi

Recently there has been significant theoretical progress on understanding the convergence and generalization of gradient-based methods on nonconvex losses with overparameterized models. Nevertheless, many aspects of opti…

Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study

2020-03-13 · NeurIPS 2020 12 · Assaf Dauber, Meir Feder, Tomer Koren, Roi Livni

The notion of implicit bias, or implicit regularization, has been suggested as a means to explain the surprising generalization ability of modern-days overparameterized learning algorithms. This notion refers to the tend…