Optimizing Likelihood-free Inference using Self-supervised Neural Symmetry Embeddings
This work addresses efficiency in parameter estimation for physical problems, but it is incremental as it builds on existing likelihood-free inference techniques.
The paper tackles the problem of slow likelihood-free inference by marginalizing physical symmetries using self-supervised neural embeddings, resulting in faster convergence and fewer parameters compared to methods without such embeddings.
Likelihood-free inference is quickly emerging as a powerful tool to perform fast/effective parameter estimation. We demonstrate a technique of optimizing likelihood-free inference to make it even faster by marginalizing symmetries in a physical problem. In this approach, physical symmetries, for example, time-translation are learned using joint-embedding via self-supervised learning with symmetry data augmentations. Subsequently, parameter inference is performed using a normalizing flow where the embedding network is used to summarize the data before conditioning the parameters. We present this approach on two simple physical problems and we show faster convergence in a smaller number of parameters compared to a normalizing flow that does not use a pre-trained symmetry-informed representation.