Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves

Abstract

Much as replacing hand-designed features with learned functions has revolutionized how we solve perceptual tasks, we believe learned algorithms will transform how we train models. In this work we focus on general-purpose learned optimizers capable of training a wide variety of problems with no user-specified hyperparameters. We introduce a new, neural network parameterized, hierarchical optimizer with access to additional features such as validation loss to enable automatic regularization. Most learned optimizers have been trained on only a single task, or a small number of tasks. We train our optimizers on thousands of tasks, making use of orders of magnitude more compute, resulting in optimizers that generalize better to unseen tasks. The learned optimizers not only perform well, but learn behaviors that are distinct from existing first order optimizers. For instance, they generate update steps that have implicit regularization and adapt as the problem hyperparameters (e.g. batch size) or architecture (e.g. neural network width) change. Finally, these learned optimizers show evidence of being useful for out of distribution tasks such as training themselves from scratch.

References in corpus (9)

• The NumPy array: a structure for efficient numerical computation
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Emergence of Locomotion Behaviours in Rich Environments
• Deep Knowledge Tracing
• Neural Optimizer Search with Reinforcement Learning
• Unbiasing Truncated Backpropagation Through Time
• Automatic Differentiation of Algorithms for Machine Learning
• Reinforcement Learning for Learning Rate Control
• Using learned optimizers to make models robust to input noise