Noether networks: meta-learning useful conserved quantities

F Alet, D Doblar, A Zhou… - Advances in …, 2021 - proceedings.neurips.cc
Advances in Neural Information Processing Systems, 2021proceedings.neurips.cc
Progress in machine learning (ML) stems from a combination of data availability,
computational resources, and an appropriate encoding of inductive biases. Useful biases
often exploit symmetries in the prediction problem, such as convolutional networks relying
on translation equivariance. Automatically discovering these useful symmetries holds the
potential to greatly improve the performance of ML systems, but still remains a challenge. In
this work, we focus on sequential prediction problems and take inspiration from Noether's …
Abstract
Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often exploit symmetries in the prediction problem, such as convolutional networks relying on translation equivariance. Automatically discovering these useful symmetries holds the potential to greatly improve the performance of ML systems, but still remains a challenge. In this work, we focus on sequential prediction problems and take inspiration from Noether's theorem to reduce the problem of finding inductive biases to meta-learning useful conserved quantities. We propose Noether Networks: a new type of architecture where a meta-learned conservation loss is optimized inside the prediction function. We show, theoretically and experimentally, that Noether Networks improve prediction quality, providing a general framework for discovering inductive biases in sequential problems.
proceedings.neurips.cc
以上显示的是最相近的搜索结果。 查看全部搜索结果