# Learning Curves for Analysis of Deep Networks

arXiv: https://arxiv.org/abs/2010.11029 · HTML: https://mlsanity.com/paper/2010.11029/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 20 of 20)

- [Learning Curve Theory](https://mlsanity.com/paper/2102.04074/) (2021)
- [The Shape of Learning Curves: a Review](https://mlsanity.com/paper/2103.10948/) (2021)
- [Data Scaling Laws in NMT: The Effect of Noise and Architecture](https://mlsanity.com/paper/2202.01994/) (2022)
- [How Much More Data Do I Need? Estimating Requirements for Downstream Tasks](https://mlsanity.com/paper/2207.01725/) (2022)
- [Optimizing Data Collection for Machine Learning](https://mlsanity.com/paper/2210.01234/) (2022)
- [Delegated Classification](https://mlsanity.com/paper/2306.11475/) (2023)
- [Multi-annotator Deep Learning: A Probabilistic Framework for Classification](https://mlsanity.com/paper/2304.02539/) (2023)
- [Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting](https://mlsanity.com/paper/2401.10359/) (2024)
- [Distilling Symbolic Priors for Concept Learning into Neural Networks](https://mlsanity.com/paper/2402.07035/) (2024)
- [A Meta-Learning Approach to Predicting Performance and Data Requirements](https://mlsanity.com/paper/2303.01598/) (2023)
- [Impact of dataset size and long-term ECoG-based BCI usage on deep learning decoders performance](https://mlsanity.com/paper/2209.03789/) (2022)
- [A Probabilistic Method to Predict Classifier Accuracy on Larger Datasets given Small Pilot Data](https://mlsanity.com/paper/2311.18025/) (2023)
- [Unraveling overoptimism and publication bias in ML-driven science](https://mlsanity.com/paper/2405.14422/) (2024)
- [A Survey of Learning Curves with Bad Behavior: or How More Data Need Not Lead to Better Performance](https://mlsanity.com/paper/2211.14061/) (2022)
- [Simple Control Baselines for Evaluating Transfer Learning](https://mlsanity.com/paper/2202.03365/) (2022)
- [LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought](https://mlsanity.com/paper/2505.15657/) (2025)
- [Strategies and impact of learning curve estimation for CNN-based image classification](https://mlsanity.com/paper/2310.08470/) (2023)
- [Unlocking Futures: A Natural Language Driven Career Prediction System for Computer Science and Software Engineering Students](https://mlsanity.com/paper/2405.18139/) (2024)
- [Data-Efficient Challenges in Visual Inductive Priors: A Retrospective](https://mlsanity.com/paper/2506.08612/) (2025)
- [How many samples to label for an application given a foundation model? Chest X-ray classification study](https://mlsanity.com/paper/2510.11553/) (2025)

## Abstract (arXiv)

Learning curves model a classifier's test error as a function of the number of training samples. Prior works show that learning curves can be used to select model parameters and extrapolate performance. We investigate how to use learning curves to evaluate design choices, such as pretraining, architecture, and data augmentation. We propose a method to robustly estimate learning curves, abstract their parameters into error and data-reliance, and evaluate the effectiveness of different parameterizations. Our experiments exemplify use of learning curves for analysis and yield several interesting observations.