# Continual Learning from the Perspective of Compression

arXiv: https://arxiv.org/abs/2006.15078 · HTML: https://mlsanity.com/paper/2006.15078/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2020.

## Built on by (most cited first, 4 of 4)

- [Sequential Learning Of Neural Networks for Prequential MDL](https://mlsanity.com/paper/2210.07931/) (2022)
- [Variational Density Propagation Continual Learning](https://mlsanity.com/paper/2308.11801/) (2023)
- [Dynamic Continual Learning: Harnessing Parameter Uncertainty for Improved Network Adaptation](https://mlsanity.com/paper/2501.10861/) (2025)
- [Forgetting is Everywhere](https://mlsanity.com/paper/2511.04666/) (2025)

## Abstract (arXiv)

Connectionist models such as neural networks suffer from catastrophic forgetting. In this work, we study this problem from the perspective of information theory and define forgetting as the increase of description lengths of previous data when they are compressed with a sequentially learned model. In addition, we show that continual learning approaches based on variational posterior approximation and generative replay can be considered as approximations to two prequential coding methods in compression, namely, the Bayesian mixture code and maximum likelihood (ML) plug-in code. We compare these approaches in terms of both compression and forgetting and empirically study the reasons that limit the performance of continual learning methods based on variational posterior approximation. To address these limitations, we propose a new continual learning method that combines ML plug-in and Bayesian mixture codes.