# Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates

arXiv: https://arxiv.org/abs/2010.00373 · HTML: https://mlsanity.com/paper/2010.00373/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2020.

## Built on by (most cited first, 30 of 34)

- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [How catastrophic can catastrophic forgetting be in linear regression?](https://mlsanity.com/paper/2205.09588/) (2022)
- [Computationally Budgeted Continual Learning: What Does Matter?](https://mlsanity.com/paper/2303.11165/) (2023)
- [Posterior Meta-Replay for Continual Learning](https://mlsanity.com/paper/2103.01133/) (2021)
- [The Ideal Continual Learner: An Agent That Never Forgets](https://mlsanity.com/paper/2305.00316/) (2023)
- [Learning where to learn: Gradient sparsity in meta and continual learning](https://mlsanity.com/paper/2110.14402/) (2021)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Low-rank extended Kalman filtering for online learning of neural networks from streaming data](https://mlsanity.com/paper/2305.19535/) (2023)
- [Preconditioned training of normalizing flows for variational inference in inverse problems](https://mlsanity.com/paper/2101.03709/) (2021)
- [Prototype-Guided Memory Replay for Continual Learning](https://mlsanity.com/paper/2108.12641/) (2021)
- [Online Continual Learning of End-to-End Speech Recognition Models](https://mlsanity.com/paper/2207.05071/) (2022)
- [Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning](https://mlsanity.com/paper/2309.06086/) (2023)
- [Continual Learning on Graphs: A Survey](https://mlsanity.com/paper/2402.06330/) (2024)
- [Continual Novelty Detection](https://mlsanity.com/paper/2106.12964/) (2021)
- [Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning](https://mlsanity.com/paper/2207.05742/) (2022)
- [Statistical mechanics of continual learning: variational principle and mean-field potential](https://mlsanity.com/paper/2212.02846/) (2022)
- [Bayesian continual learning and forgetting in neural networks](https://mlsanity.com/paper/2504.13569/) (2025)
- [Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations](https://mlsanity.com/paper/2205.11713/) (2022)
- [Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings](https://mlsanity.com/paper/2410.20768/) (2024)
- [Autoencoder-Based Hybrid Replay for Class-Incremental Learning](https://mlsanity.com/paper/2505.05926/) (2025)
- [Rethinking Continual Learning with Progressive Neural Collapse](https://mlsanity.com/paper/2505.24254/) (2025)
- [Martingale Posterior Neural Networks for Fast Sequential Decision Making](https://mlsanity.com/paper/2506.11898/) (2025)
- [Continual Learning with Invertible Generative Models](https://mlsanity.com/paper/2202.05694/) (2022)
- [Learning to Remember, Learn, and Forget in Attention-Based Models](https://mlsanity.com/paper/2602.09075/) (2026)
- [Lifelong Wandering: A realistic few-shot online continual learning setting](https://mlsanity.com/paper/2206.07932/) (2022)
- [Continual Learning with Pretrained Backbones by Tuning in the Input Space](https://mlsanity.com/paper/2306.02947/) (2023)
- [Variational Bayes for Federated Continual Learning](https://mlsanity.com/paper/2405.14291/) (2024)
- [Temporal-Difference Variational Continual Learning](https://mlsanity.com/paper/2410.07812/) (2024)
- [Prospective Learning in Retrospect](https://mlsanity.com/paper/2507.07965/) (2025)

## Abstract (arXiv)

Background: Catastrophic forgetting is the notorious vulnerability of neural networks to the changes in the data distribution during learning. This phenomenon has long been considered a major obstacle for using learning agents in realistic continual learning settings. A large body of continual learning research assumes that task boundaries are known during training. However, only a few works consider scenarios in which task boundaries are unknown or not well defined -- task agnostic scenarios. The optimal Bayesian solution for this requires an intractable online Bayes update to the weights posterior. Contributions: We aim to approximate the online Bayes update as accurately as possible. To do so, we derive novel fixed-point equations for the online variational Bayes optimization problem, for multivariate Gaussian parametric distributions. By iterating the posterior through these fixed-point equations, we obtain an algorithm (FOO-VB) for continual learning which can handle non-stationary data distribution using a fixed architecture and without using external memory (i.e. without access to previous data). We demonstrate that our method (FOO-VB) outperforms existing methods in task agnostic scenarios. FOO-VB Pytorch implementation will be available online.