Meta-learning Via Learned Loss

Abstract

Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process, with the view of producing models which train faster and more robustly. Concretely, we present a meta-learning method for learning parametric loss functions that can generalize across different tasks and model architectures. We develop a pipeline for meta-training such loss functions, targeted at maximizing the performance of the model trained under them. The loss landscape produced by our learned losses significantly improves upon the original task-specific losses in both supervised and reinforcement learning tasks. Furthermore, we show that our meta-learning framework is flexible enough to incorporate additional information at meta-train time. This information shapes the learned loss function such that the environment does not need to provide this in

Stats

• citations21
• S2 citations—
• github stars0
• HF likes0
• heat score10.07
• arxiv keybechtle2019meta

Related papers

• Unsupervised Meta-learning For Reinforcement Learning (2018)0.00
• Meta Reinforcement Learning With Latent Variable Gaussian Processes (2018)0.00
• Meta-trained Agents Implement Bayes-optimal Agents (2020)0.00
• Model Based Meta Learning Of Critics For Policy Gradients (2022)0.00
• Double Meta-learning For Data Efficient Policy Optimization In Non-stationary Environments (2020)0.00
• Improving Generalization In Meta Reinforcement Learning Using Learned Objectives (2019)0.00
• Meta-value Learning: A General Framework For Learning With Learning Awareness (2023)0.00
• Deep Online Learning Via Meta-learning: Continual Adaptation For Model-based RL (2018)0.00