# Finding the Muses: Identifying Coresets through Loss Trajectories

Source: [Finding the Muses: Identifying Coresets through Loss Trajectories](<https://www.sota2.com/research/paper/68fa77621e209131cea72dbd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:17:49.742Z

Authors: Manish Nagaraj, Deepak Ravikumar, Efstathia Soufleri, Kaushik Roy

Published: 2025-03-12T18:11:16.000Z

## Abstract

Deep learning models achieve state-of-the-art performance across domains but face scalability challenges in real-time or resource-constrained scenarios. To address this, we propose Loss Trajectory Correlation (LTC), a novel metric for coreset selection that identifies critical training samples driving generalization. $LTC$ quantifies the alignment between training sample loss trajectories and validation set loss trajectories, enabling the construction of compact, representative subsets. Unlike traditional methods with computational and storage overheads that are infeasible to scale to large datasets, $LTC$ achieves superior efficiency as it can be computed as a byproduct of training. Our results on CIFAR-100 and ImageNet-1k show that $LTC$ consistently achieves accuracy on par with or surpassing state-of-the-art coreset selection methods, with any differences remaining under 1%. LTC also effectively transfers across various architectures, including ResNet, VGG, DenseNet, and Swin Transformer, with minimal performance degradation (\<2%). Additionally, LTC offers insights into training dynamics, such as identifying aligned and conflicting sample behaviors, at a fraction of the computational cost of traditional methods. This framework paves the way for scalable coreset selection and efficient dataset optimization.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.09721>)

[PDF](<https://arxiv.org/pdf/2503.09721.pdf>)
