AI Paper Atlas

Research map / Continual learning / Online and replay-based

Functional Regularisation for Continual Learning with Gaussian Processes

Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh

ICLR 2020 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 86 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use trace-term optimisation instead of random selection for inducing points (ablation)FRCL · Permuted-MNIST, 10 points/taskaccuracy: 48.2% { $\pm$ 4.0} -> 61.7% { $\pm$ 1.8}Improved
Use trace-term optimisation instead of random selection for inducing points (ablation)FRCL · Split-MNIST, 2 points/taskaccuracy: 59.8% { $\pm$ 8.0} -> 82.0% { $\pm$ 5.0}Improved
Use trace-term optimisation instead of random selection for inducing points (ablation)FRCL · Omniglot, 1 point/chartest accuracy: 69.74 { $\pm$ 1.1} -> 72.02 { $\pm$ 1.3}Improved
Use trace-term optimisation instead of random selection for inducing points (ablation)FRCL · Omniglot, 3 points/chartest accuracy: {\bf 81.42} { $\pm$ 1.2} -> 81.01 { $\pm$ 1.1}Hurt
Increase inducing points from 1 to 3 per character (ablation)FRCL (Trace) · Omniglottest accuracy: 72.02 { $\pm$ 1.3} -> 81.01 { $\pm$ 1.1}Improved
Increase inducing points from 1 to 3 per character (ablation)FRCL (Random) · Omniglottest accuracy: 69.74 { $\pm$ 1.1} -> {\bf 81.42} { $\pm$ 1.2}Improved
Use trace-term rather than random inducing point selection (ablation)FRCL · Permuted-MNIST, 200 points/taskaccuracy: 94.2% { $\pm$ 0.1} -> 94.3% { $\pm$ 0.2}No clear effect
Use function-space posterior summaries and KL regularisation instead of an explicit replay bufferFRCL versus replay baseline · Permuted-MNIST, 200 points/taskaccuracy: 82.3% { $\pm$ 0.3} -> 94.3% { $\pm$ 0.2}Improved
Use function-space posterior summaries and KL regularisation instead of an explicit replay bufferFRCL versus replay baseline · Split-MNIST, 40 points/taskaccuracy: 95.8% { $\pm$ 1.1} -> 97.8% { $\pm$ 0.7}Improved
Use function-space posterior summaries and KL regularisation instead of an explicit replay bufferFRCL versus replay baseline · Omniglot, 1 point/chartest accuracy: 42.73 { $\pm$ 1.2} -> 72.02 { $\pm$ 1.3}Improved
Use function-space posterior summaries and KL regularisation instead of an explicit replay bufferFRCL versus replay baseline · Omniglot, 3 points/chartest accuracy: 65.32 { $\pm$ 1.1} -> 81.01 { $\pm$ 1.1}Improved
Use FRCL trace selection rather than VCL with random coresetOmniglot MLP · Omniglot, 3 points/chartest accuracy: 51.64 { $\pm$ 1.0} -> 53.86 { $\pm$ 2.3}Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy