mlsanityData to 7 Oct 2026

Learning Curves for Analysis of Deep Networks

arXiv 2010.11029 ↗First posted 21 Oct 2020cs.LG cs.CV stat.MLcited by 20

Not on the map. Why?

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.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 6; 2023: 5; 2024: 4; 2025: 3.

20 papers.

Sort:

  1. 2021Learning Curve Theorycited by 79
  2. 2021The Shape of Learning Curves: a Reviewcited by 67
  3. 2022Data Scaling Laws in NMT: The Effect of Noise and Architecturecited by 55
  4. 2022How Much More Data Do I Need? Estimating Requirements for Downstream Taskscited by 22
  5. 2022Optimizing Data Collection for Machine Learningcited by 15
  6. 2023Delegated Classificationcited by 10
  7. 2023Multi-annotator Deep Learning: A Probabilistic Framework for Classificationcited by 8
  8. 2024Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfittingcited by 6
  9. 2024Distilling Symbolic Priors for Concept Learning into Neural Networkscited by 5
  10. 2023A Meta-Learning Approach to Predicting Performance and Data Requirementscited by 4
  11. 2022Impact of dataset size and long-term ECoG-based BCI usage on deep learning decoders performancecited by 3
  12. 2023A Probabilistic Method to Predict Classifier Accuracy on Larger Datasets given Small Pilot Datacited by 3
8 more
  1. 2024Unraveling overoptimism and publication bias in ML-driven sciencecited by 3
  2. 2022A Survey of Learning Curves with Bad Behavior: or How More Data Need Not Lead to Better Performancecited by 2
  3. 2022Simple Control Baselines for Evaluating Transfer Learningcited by 1
  4. 2025LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thoughtcited by 1
  5. 2023Strategies and impact of learning curve estimation for CNN-based image classificationcited by 0
  6. 2024Unlocking Futures: A Natural Language Driven Career Prediction System for Computer Science and Software Engineering Studentscited by 0
  7. 2025Data-Efficient Challenges in Visual Inductive Priors: A Retrospectivecited by 0
  8. 2025How many samples to label for an application given a foundation model? Chest X-ray classification studycited by 0