Functional Bilevel Optimization for Machine Learning
This work addresses a bottleneck in optimization for machine learning practitioners by enabling more flexible model choices, though it appears incremental as it builds on existing bilevel optimization frameworks.
The paper tackles bilevel optimization in machine learning by introducing a functional perspective that avoids strong convexity assumptions, enabling the use of over-parameterized neural networks as inner functions, and demonstrates benefits in instrumental regression and reinforcement learning tasks.
In this paper, we introduce a new functional point of view on bilevel optimization problems for machine learning, where the inner objective is minimized over a function space. These types of problems are most often solved by using methods developed in the parametric setting, where the inner objective is strongly convex with respect to the parameters of the prediction function. The functional point of view does not rely on this assumption and notably allows using over-parameterized neural networks as the inner prediction function. We propose scalable and efficient algorithms for the functional bilevel optimization problem and illustrate the benefits of our approach on instrumental regression and reinforcement learning tasks.