2019

Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients

Chen, Yu, Diethe, Tom, Lawrence, Neil

Understand

Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner.

  • Conventional models tend to forget the knowledge of previous tasks while learning a new task, a phenomenon known as catastrophic forgetting.
  • When using Bayesian models in continual learning, knowledge from previous tasks can be retained in two ways: 1).
  • posterior distributions over the parameters, containing the knowledge gained from inference in previous tasks, which then serve as the priors for the following task; 2).

Built on

  • Stochastic variational inference

    Matthew D Hoffman, David M Blei, Chong Wang, and John Paisley · 2013

    Earlier work this paper cites.

  • Revisiting natural gradient for deep networks

    Razvan Pascanu and Yoshua Bengio · 2014

    Earlier work this paper cites.

  • Adam: A method for stochastic optimization

    Diederik P Kingma and Jimmy Lei Ba · 2014

    Earlier work this paper cites.

  • Coresets for scalable Bayesian logistic regression

    Jonathan Huggins, Trevor Campbell, and Tamara Broderick · 2016

    Earlier work this paper cites.

Similar

  • Stein variational gradient descent: A general purpose Bayesian inference algorithm

    Qiang Liu and Dilin Wang · 2016

    Cited alongside, same era.

  • Overcoming catastrophic forgetting in neural networks

    James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al · 2017

    Cited alongside, same era.

  • Continual learning through synaptic intelligence

    Friedemann Zenke, Ben Poole, and Surya Ganguli · 2017

    Cited alongside, same era.

  • Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms

    Original

    Han Xiao, Kashif Rasul, and Roland Vollgraf · 2017

    Cited alongside, same era.

Then

  • Bayesian compression for deep learning

    Christos Louizos, Karen Ullrich, and Max Welling · 2017

    Later among the works it cites.

  • Variational continual learning

    Cuong V Nguyen, Yingzhen Li, Thang D Bui, and Richard E Turner · 2018

    Later among the works it cites.

  • Bayesian coreset construction via greedy iterative geodesic ascent

    Original

    Trevor Campbell and Tamara Broderick · 2018

    Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…