Learning Curves for Analysis of Deep Networks
arXiv:2010.11029
Abstract
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.
arXiv commentImproved text and figure organization, additional experiments on optimization
References in corpus (7)
- Scaling Laws for Neural Language Models
- Deep Learning Scaling is Predictable, Empirically
- Rethinking Pre-training and Self-training
- Lookahead Optimizer: k steps forward, 1 step back
- A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks
- Spectrally-normalized margin bounds for neural networks
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark