Bilevel Optimization for Machine Learning: Algorithm Design and Convergence Analysis

by   Kaiyi Ji, et al.

Bilevel optimization has become a powerful framework in various machine learning applications including meta-learning, hyperparameter optimization, and network architecture search. There are generally two classes of bilevel optimization formulations for machine learning: 1) problem-based bilevel optimization, whose inner-level problem is formulated as finding a minimizer of a given loss function; and 2) algorithm-based bilevel optimization, whose inner-level solution is an output of a fixed algorithm. For the first class, two popular types of gradient-based algorithms have been proposed for hypergradient estimation via approximate implicit differentiation (AID) and iterative differentiation (ITD). Algorithms for the second class include the popular model-agnostic meta-learning (MAML) and almost no inner loop (ANIL). However, the convergence rate and fundamental limitations of bilevel optimization algorithms have not been well explored. This thesis provides a comprehensive convergence rate analysis for bilevel algorithms in the aforementioned two classes. We further propose principled algorithm designs for bilevel optimization with higher efficiency and scalability. For the problem-based formulation, we provide a convergence rate analysis for AID- and ITD-based bilevel algorithms. We then develop acceleration bilevel algorithms, for which we provide shaper convergence analysis with relaxed assumptions. We also provide the first lower bounds for bilevel optimization, and establish the optimality by providing matching upper bounds under certain conditions. We finally propose new stochastic bilevel optimization algorithms with lower complexity and higher efficiency in practice. For the algorithm-based formulation, we develop a theoretical convergence for general multi-step MAML and ANIL, and characterize the impact of parameter selections and loss geometries on the their complexities.


Stochastic Multi-Level Compositional Optimization Algorithms over Networks with Level-Independent Convergence Rate

Stochastic multi-level compositional optimization problems cover many ne...

The Curse of Unrolling: Rate of Differentiating Through Optimization

Computing the Jacobian of the solution of an optimization problem is a c...

Will Bilevel Optimizers Benefit from Loops

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

A Constrained Optimization Approach to Bilevel Optimization with Multiple Inner Minima

Bilevel optimization has found extensive applications in modern machine ...

On the Iteration Complexity of Hypergradient Computation

We study a general class of bilevel problems, consisting in the minimiza...

Multi-Step Model-Agnostic Meta-Learning: Convergence and Improved Algorithms

As a popular meta-learning approach, the model-agnostic meta-learning (M...

Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning

In (Franceschi et al., 2018) we proposed a unified mathematical framewor...

Please sign up or login with your details

Forgot password? Click here to reset