Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients

By Yu Chen, Tom Diethe, Neil D. Lawrence. 2019

15 citations recorded by the source corpus.

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). coresets, containing knowledge of data distributions of previous tasks. Here, we show that Bayesian continual learning can be facilitated in terms of these two means through the use of natural gradients and Stein gradients respectively.

Subfields: Artificial Intelligence, Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Optimization & Training

Citations in the corpus

Toward Understanding Catastrophic Forgetting in Continual Learning (2019, methodology): “Several algorithms have been developed for utilizing coresets, including gradient episodic memory (GEM) [27], averaged GEM [9], coreset VCL [29], and Stein gradients coreset [10].”
Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning (2021, background): “Memory Aware Synapses (MAS) [2] estimates importance weights in an unsupervised manner, while Variational Continual Learning (VCL) [28] introduces a variational framework that spawned some Bayesian-based works [32, 8, 1, 7].”
Meta-Consolidation for Continual Learning (2020, background): “One line of work [88, 38, 47, 2, 16, 71, 56, 13, 79, 42] constrains the parameters of the deep network trained on Task A to not change much while learning a new Task B, while another - replay-based methods - store [63, 48, 14, 66, 9, 3, 4, 22] or generate [74, 81, 46, 45] examples of previous tasks ”
Uncertainty-guided Continual Learning with Bayesian Neural Networks (2019, methodology): “For Bayesian methods, we compare against VCL and its variations named as VCL with Variational Adam (VCL-Vadam), VCL with Adam and Gaussian natural gradients (VCL-GNG).”
Drinking From a Firehose: Continual Learning With Web-Scale Natural Language (2020, methodology): “leverage a data-driven prior from past tasks to regularize the current task [4], [12], [13], [14], [15], [16], [17], [18], [19], [20], [21], [22], [23], [24], [25].”