Timezone: »

 
Continual Learning via Function-Space Variational Inference: A Unifying View
Tim G. J. Rudner · Freddie Bickford Smith · Qixuan Feng · Yee-Whye Teh · Yarin Gal

@
in Subset Selection in Machine Learning: From Theory to Applications »

Continual learning is the process of developing new abilities while retaining existing ones. Sequential Bayesian inference is a natural framework for this, but applying it successfully to deep neural networks remains a challenge. We propose continual function-space variational inference (C-FSVI), in which the variational distribution over functions induced by stochastic model parameters is encouraged to match the variational distribution over functions induced by stochastic parameters inferred on previous tasks. Unlike approaches that explicitly penalize changes in the model parameters, function-space regularization allows parameters to vary widely during training, resulting in greater flexibility to fit new data. C-FSVI improves on existing approaches to function-space regularization by performing inference entirely in function space and without relying on carefully selected coreset points. We show that C-FSVI outperforms alternative methods based on parameter-space and function-space regularization on a range of tasks.

Author Information

Tim G. J. Rudner (University of Oxford)

I am a PhD Candidate in the Department of Computer Science at the University of Oxford, where I conduct research on probabilistic machine learning with Yarin Gal and Yee Whye Teh. My research interests span **Bayesian deep learning**, **variational inference**, and **reinforcement learning**. I am particularly interested in uncertainty quantification in deep learning, reinforcement learning as probabilistic inference, and probabilistic transfer learning. I am also a **Rhodes Scholar** and an **AI Fellow** at Georgetown University's Center for Security and Emerging Technology.

Freddie Bickford Smith (University of Oxford)
Qixuan Feng (University of Oxford)
Yee-Whye Teh (Oxford and DeepMind)
Yarin Gal (University of Oxford)

More from the Same Authors