DeepAI AI Chat
Log In Sign Up

Tutorial on amortized optimization for learning to optimize over continuous domains

by   Brandon Amos, et al.

Optimization is a ubiquitous modeling tool that is often deployed in settings that repeatedly solve similar instances of the same problem. Amortized optimization methods use learning to predict the solutions to problems in these settings. This leverages the shared structure between similar problem instances. In this tutorial, we will discuss the key design choices behind amortized optimization, roughly categorizing 1) models into fully-amortized and semi-amortized approaches, and 2) learning methods into regression-based and objective-based. We then view existing applications through these foundations to draw connections between them, including for manifold optimization, variational inference, sparse coding, meta-learning, control, reinforcement learning, convex optimization, and deep equilibrium networks. This framing enables us easily see, for example, that the amortized inference in variational autoencoders is conceptually identical to value gradients in control and reinforcement learning as they both use fully-amortized models with a objective-based loss. The source code for this tutorial is available at


page 4

page 37

page 38


Meta-Model-Based Meta-Policy Optimization

Model-based reinforcement learning (MBRL) has been applied to meta-learn...

BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning

Meta-learning (a.k.a. learning to learn) has recently emerged as a promi...

Variational Adaptive-Newton Method for Explorative Learning

We present the Variational Adaptive Newton (VAN) method which is a black...

Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning

The goal of this paper is to provide a unifying view of a wide range of ...

An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization

Molecule optimization is an important problem in chemical discovery and ...

Accelerating Quadratic Optimization with Reinforcement Learning

First-order methods for quadratic optimization such as OSQP are widely u...

Reasoning and Generalization in RL: A Tool Use Perspective

Learning to use tools to solve a variety of tasks is an innate ability o...

Code Repositories


Tutorial on amortized optimization for learning to optimize over continuous domains

view repo