Low-Rank Constraints for Fast Inference in Structured ModelsDownload PDF

Published: 09 Nov 2021, Last Modified: 22 Oct 2023NeurIPS 2021 PosterReaders: Everyone
Keywords: structured prediction, generative models, graphical models, inference
Abstract: Structured distributions, i.e. distributions over combinatorial spaces, are commonly used to learn latent probabilistic representations from observed data. However, scaling these models is bottlenecked by the high computational and memory complexity with respect to the size of the latent representations. Common models such as Hidden Markov Models (HMMs) and Probabilistic Context-Free Grammars (PCFGs) require time and space quadratic and cubic in the number of hidden states respectively. This work demonstrates a simple approach to reduce the computational and memory complexity of a large class of structured models. We show that by viewing the central inference step as a matrix-vector product and using a low-rank constraint, we can trade off model expressivity and speed via the rank. Experiments with neural parameterized structured models for language modeling, polyphonic music modeling, unsupervised grammar induction, and video modeling show that our approach matches the accuracy of standard models at large state spaces while providing practical speedups.
Supplementary Material: pdf
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
Code: https://github.com/justinchiu/low-rank-models
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 3 code implementations](https://www.catalyzex.com/paper/arxiv:2201.02715/code)
12 Replies