On Linear Separability of the MNIST Handwritten Digits Dataset
It addresses a fundamental but unclear issue for researchers and practitioners using MNIST as a benchmark, though it is incremental in nature.
This paper tackled the unresolved question of whether the MNIST handwritten digits dataset is linearly separable, conducting a comprehensive empirical investigation and reporting findings on pairwise and one-vs-rest separability across training, test, and combined sets.
The MNIST dataset containing thousands of handwritten digit images is still a fundamental benchmark for evaluating various pattern-recognition and image-classification models. Linear separability is a key concept in many statistical and machine-learning techniques. Despite the long history of the MNIST dataset and its relative simplicity in size and resolution, the question of whether the dataset is linearly separable has never been fully answered -- scientific and informal sources share conflicting claims. This paper aims to provide a comprehensive empirical investigation to address this question, distinguishing pairwise and one-vs-rest separation of the training, the test and the combined sets, respectively. It reviews the theoretical approaches to assessing linear separability, alongside state-of-the-art methods and tools, then systematically examines all relevant assemblies, and reports the findings.