Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with a Nonconvex Lower-Level Objective
Yicong Jiang, Feihu Huang
原文摘要
Multi-objective bilevel optimization has wide applications in the AI area such as automated learning and multi-task meta-learning. Although some recent studies have investigated multi-objective bilevel optimization, many existing methods rely on the (strongly) convex lower level problems. In fact, these multi-objective bilevel learning problems are generally nonconvex, and particularly their lower level problems are nonconvex. To fill this gap, we propose a class of Multi-Objective Moreau Envelope based Hessian-free Algorithms (MOMEHA) for the multi-objective bilevel learning problems with a nonconvex lower level. Specifically, our method uses the Moreau envelope to formulate a multi-objective single-level relaxation that enforces lower-level first-order stationarity. In particular, our method retains computational advantages of being single-loop and Hessian-free in the multi-objective setting by incorporating a smooth weighted Tchebycheff scalarization. Furthermore, we propose a momentum variant of MOMEHA (i.e., MB-MOMEHA) for the stochastic multi-objective bilevel learning problems. Under the stated assumptions, we establish finite-iteration bounds on the Moreau gap and Pareto stationarity residuals under dynamically relaxed gap constraints in both deterministic and stochastic settings. Some experiments on few-shot meta-learning and neural architecture search demonstrate that our methods outperform the existing approaches in terms of Pareto front quality, validating their effectiveness and robustness.
math.OC · cs.LG