ICML 2021spotlight36 citations

Variational Auto-Regressive Gaussian Processes for Continual Learning

Sanyam Kapoor, Theofanis Karaletsos, Thang D Bui

Abstract

Through sequential construction of posteriors on observing data online, Bayes’ theorem provides a natural framework for continual learning. We develop Variational Auto-Regressive Gaussian Processes (VAR-GPs), a principled posterior updating mechanism to solve sequential tasks in continual learning. By relying on sparse inducing point approximations for scalable posteriors, we propose a novel auto-regressive variational distribution which reveals two fruitful connections to existing results in Bayesian inference, expectation propagation and orthogonal inducing points. Mean predictive entropy estimates show VAR-GPs prevent catastrophic forgetting, which is empirically supported by strong performance on modern continual learning benchmarks against competitive baselines. A thorough ablation study demonstrates the efficacy of our modeling choices.

BibTeX
@InProceedings{pmlr-v139-kapoor21b,
  title = 	 {Variational Auto-Regressive Gaussian Processes for Continual Learning},
  author =       {Kapoor, Sanyam and Karaletsos, Theofanis and Bui, Thang D},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {5290--5300},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/kapoor21b/kapoor21b.pdf},
  url = 	 {https://proceedings.mlr.press/v139/kapoor21b.html},
  abstract = 	 {Through sequential construction of posteriors on observing data online, Bayes’ theorem provides a natural framework for continual learning. We develop Variational Auto-Regressive Gaussian Processes (VAR-GPs), a principled posterior updating mechanism to solve sequential tasks in continual learning. By relying on sparse inducing point approximations for scalable posteriors, we propose a novel auto-regressive variational distribution which reveals two fruitful connections to existing results in Bayesian inference, expectation propagation and orthogonal inducing points. Mean predictive entropy estimates show VAR-GPs prevent catastrophic forgetting, which is empirically supported by strong performance on modern continual learning benchmarks against competitive baselines. A thorough ablation study demonstrates the efficacy of our modeling choices.}
}
Variational Auto-Regressive Gaussian Processes for Continual Learning · ICML 2021