# Improving information retention in large scale online continual learning

arXiv: https://arxiv.org/abs/2210.06401 · HTML: https://mlsanity.com/paper/2210.06401/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 12 Oct 2022.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [YFCC100M: The New Data in Multimedia Research](https://mlsanity.com/paper/1503.01817/) (2015)
- [Non-stationary Stochastic Optimization](https://mlsanity.com/paper/1307.5449/) (2013)
- [The CLEAR Benchmark: Continual LEArning on Real-World Imagery](https://mlsanity.com/paper/2201.06289/) (2022)
- [Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data](https://mlsanity.com/paper/2108.09020/) (2021)
- [A Variational Analysis of Stochastic Gradient Algorithms](https://mlsanity.com/paper/1602.02666/) (2016)
- [Drinking from a Firehose: Continual Learning with Web-scale Natural Language](https://mlsanity.com/paper/2007.09335/) (2020)

## Built on by (most cited first, 3 of 3)

- [Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?](https://mlsanity.com/paper/2305.09275/) (2023)
- [TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Models](https://mlsanity.com/paper/2604.15756/) (2026)
- [Formalizing Forgetting: Theory of Forgetting for Online Continual Learning](https://mlsanity.com/paper/2610.14787/) (2026)

## Abstract (arXiv)

Given a stream of data sampled from non-stationary distributions, online continual learning (OCL) aims to adapt efficiently to new data while retaining existing knowledge. The typical approach to address information retention (the ability to retain previous knowledge) is keeping a replay buffer of a fixed size and computing gradients using a mixture of new data and the replay buffer. Surprisingly, the recent work (Cai et al., 2021) suggests that information retention remains a problem in large scale OCL even when the replay buffer is unlimited, i.e., the gradients are computed using all past data. This paper focuses on this peculiarity to understand and address information retention. To pinpoint the source of this problem, we theoretically show that, given limited computation budgets at each time step, even without strict storage limit, naively applying SGD with constant or constantly decreasing learning rates fails to optimize information retention in the long term. We propose using a moving average family of methods to improve optimization for non-stationary objectives. Specifically, we design an adaptive moving average (AMA) optimizer and a moving-average-based learning rate schedule (MALR). We demonstrate the effectiveness of AMA+MALR on large-scale benchmarks, including Continual Localization (CLOC), Google Landmarks, and ImageNet. Code will be released upon publication.