# Gradient-Matching Coresets for Rehearsal-Based Continual Learning

arXiv: https://arxiv.org/abs/2203.14544 · HTML: https://mlsanity.com/paper/2203.14544/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 28 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [On Exact Computation with an Infinitely Wide Neural Net](https://mlsanity.com/paper/1904.11955/) (2019)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [Coresets via Bilevel Optimization for Continual Learning and Streaming](https://mlsanity.com/paper/2006.03875/) (2020)
- [Online Coreset Selection for Rehearsal-based Continual Learning](https://mlsanity.com/paper/2106.01085/) (2021)
- [Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent](https://mlsanity.com/paper/1802.01737/) (2018)

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

- [Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning](https://mlsanity.com/paper/2311.13613/) (2023)
- [Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models](https://mlsanity.com/paper/2408.02085/) (2024)
- [Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models](https://mlsanity.com/paper/2408.15915/) (2024)
- [Domain-Generalization to Improve Learning in Meta-Learning Algorithms](https://mlsanity.com/paper/2508.09418/) (2025)

## Abstract (arXiv)

The goal of continual learning (CL) is to efficiently update a machine learning model with new data without forgetting previously-learned knowledge. Most widely-used CL methods rely on a rehearsal memory of data points to be reused while training on new data. Curating such a rehearsal memory to maintain a small, informative subset of all the data seen so far is crucial to the success of these methods. We devise a coreset selection method for rehearsal-based continual learning. Our method is based on the idea of gradient matching: The gradients induced by the coreset should match, as closely as possible, those induced by the original training dataset. Inspired by the neural tangent kernel theory, we perform this gradient matching across the model's initialization distribution, allowing us to extract a coreset without having to train the model first. We evaluate the method on a wide range of continual learning scenarios and demonstrate that it improves the performance of rehearsal-based CL methods compared to competing memory management strategies such as reservoir sampling.