DeepAI AI Chat
Log In Sign Up

Debiasing a First-order Heuristic for Approximate Bi-level Optimization

by   Valerii Likhosherstov, et al.

Approximate bi-level optimization (ABLO) consists of (outer-level) optimization problems, involving numerical (inner-level) optimization loops. While ABLO has many applications across deep learning, it suffers from time and memory complexity proportional to the length r of its inner optimization loop. To address this complexity, an earlier first-order method (FOM) was proposed as a heuristic that omits second derivative terms, yielding significant speed gains and requiring only constant memory. Despite FOM's popularity, there is a lack of theoretical understanding of its convergence properties. We contribute by theoretically characterizing FOM's gradient bias under mild assumptions. We further demonstrate a rich family of examples where FOM-based SGD does not converge to a stationary point of the ABLO objective. We address this concern by proposing an unbiased FOM (UFOM) enjoying constant memory complexity as a function of r. We characterize the introduced time-variance tradeoff, demonstrate convergence bounds, and find an optimal UFOM for a given ABLO problem. Finally, we propose an efficient adaptive UFOM scheme.


page 1

page 2

page 3

page 4


UFO-BLO: Unbiased First-Order Bilevel Optimization

Bilevel optimization (BLO) is a popular approach with many applications ...

Convergent First-Order Methods for Bi-level Optimization and Stackelberg Games

We propose an algorithm to solve a class of bi-level optimization proble...

Fair Representation Learning through Implicit Path Alignment

We consider a fair representation learning perspective, where optimal pr...

A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization

Bi-level optimization model is able to capture a wide range of complex l...

A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse

In this paper, we propose a new Hessian inverse free Fully Single Loop A...

Will Bilevel Optimizers Benefit from Loops

Bilevel optimization has arisen as a powerful tool for solving a variety...

Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity

Gradient methods have become mainstream techniques for Bi-Level Optimiza...