AutoLoss: Learning Discrete Schedules for Alternate Optimization

Abstract

Many machine learning problems involve iteratively and alternately optimizing different task objectives with respect to different sets of parameters. Appropriately scheduling the optimization of a task objective or a set of parameters is usually crucial to the quality of convergence. In this paper, we present AutoLoss, a meta-learning framework that automatically learns and determines the optimization schedule. AutoLoss provides a generic way to represent and learn the discrete optimization schedule from metadata, allows for a dynamic and data-driven schedule in ML problems that involve alternating updates of different parameters or from different loss objectives. We apply AutoLoss on four ML tasks: d-ary quadratic regression, classification using a multi-layer perceptron (MLP), image generation using GANs, and multi-task neural machine translation (NMT). We show that the AutoLoss controller is able to capture the distribution of better optimization schedules that result in higher quality of convergence on all four tasks. The trained AutoLoss controller is generalizable -- it can guide and improve the learning of a new task model with different specifications, or on different datasets.

arXiv comment19-pages manuscripts. The first two authors contributed equally

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Neural Architecture Search with Reinforcement Learning
• Improved Training of Wasserstein GANs
• Improved Techniques for Training GANs
• Effective Approaches to Attention-based Neural Machine Translation
• Efficient Neural Architecture Search via Parameter Sharing
• A Survey on Multi-Task Learning
• Gradient-based Hyperparameter Optimization through Reversible Learning
• Learning to reinforcement learn
• Device Placement Optimization with Reinforcement Learning
• Neural Optimizer Search with Reinforcement Learning
• A Complete Recipe for Stochastic Gradient MCMC
• Distral: Robust Multitask Reinforcement Learning
• Learning to Learn without Gradient Descent by Gradient Descent
• Learning to Optimize
• Exploiting Linguistic Resources for Neural Machine Translation Using Multi-task Learning

Cited by in corpus (10)

• Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism
• Adaptive Scheduling for Multi-Task Learning
• Automated Self-Supervised Learning for Graphs
• Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection
• AutoLoss: Automated Loss Function Search in Recommendations
• On Effective Scheduling of Model-based Reinforcement Learning
• CCMN: A General Framework for Learning with Class-Conditional Multi-Label Noise
• Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
• T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging
• Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation