# A Negative Result on Gradient Matching for Selective Backprop

arXiv: https://arxiv.org/abs/2312.05021 · HTML: https://mlsanity.com/paper/2312.05021/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 8 Dec 2023.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Deep Learning on a Data Diet: Finding Important Examples Early in Training](https://mlsanity.com/paper/2107.07075/) (2021)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training](https://mlsanity.com/paper/2103.00123/) (2021)
- [Online Batch Selection for Faster Training of Neural Networks](https://mlsanity.com/paper/1511.06343/) (2015)
- [Accelerating Deep Learning by Focusing on the Biggest Losers](https://mlsanity.com/paper/1910.00762/) (2019)
- [Variance Reduction in SGD by Distributed Importance Sampling](https://mlsanity.com/paper/1511.06481/) (2015)
- [No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models](https://mlsanity.com/paper/2307.06440/) (2023)
- [Importance Sampling for Minibatches](https://mlsanity.com/paper/1602.02283/) (2016)
- [Biased Importance Sampling for Deep Neural Network Training](https://mlsanity.com/paper/1706.00043/) (2017)

## Abstract (arXiv)

With increasing scale in model and dataset size, the training of deep neural networks becomes a massive computational burden. One approach to speed up the training process is Selective Backprop. For this approach, we perform a forward pass to obtain a loss value for each data point in a minibatch. The backward pass is then restricted to a subset of that minibatch, prioritizing high-loss examples. We build on this approach, but seek to improve the subset selection mechanism by choosing the (weighted) subset which best matches the mean gradient over the entire minibatch. We use the gradients w.r.t. the model's last layer as a cheap proxy, resulting in virtually no overhead in addition to the forward pass. At the same time, for our experiments we add a simple random selection baseline which has been absent from prior work. Surprisingly, we find that both the loss-based as well as the gradient-matching strategy fail to consistently outperform the random baseline.