Timezone: »

 
Poster
Variational Auto-Regressive Gaussian Processes for Continual Learning
Sanyam Kapoor · Theofanis Karaletsos · Thang Bui

Thu Jul 22 09:00 AM -- 11:00 AM (PDT) @ Virtual
in Poster Session 5 »

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.

Keywords: Gaussian Processes and Bayesian non-parametrics
[ Slides] 

Author Information

Sanyam Kapoor (New York University)
Theofanis Karaletsos (Facebook)
Thang Bui (University of Sydney)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors