Evaluating State-of-the-Art Classification Models Against Bayes Optimality

Abstract

Evaluating the inherent difficulty of a given data-driven classification problem is important for establishing absolute benchmarks and evaluating progress in the field. To this end, a natural quantity to consider is the \emph{Bayes error}, which measures the optimal classification error theoretically achievable for a given data distribution. While generally an intractable quantity, we show that we can compute the exact Bayes error of generative models learned using normalizing flows. Our technique relies on a fundamental result, which states that the Bayes error is invariant under invertible transformation. Therefore, we can compute the exact Bayes error of the learned flow models by computing it for Gaussian base distributions, which can be done efficiently using Holmes-Diaconis-Ross integration. Moreover, we show that by varying the temperature of the learned flow models, we can generate synthetic datasets that closely resemble standard benchmark datasets, but with almost any desired Bayes error. We use our approach to conduct a thorough investigation of state-of-the-art classification models, and find that in some -- but not all -- cases, these models are capable of obtaining accuracy very near optimal. Finally, we use our method to evaluate the intrinsic "hardness" of standard benchmark datasets, and classes within those datasets.

References in corpus (11)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• EMNIST: an extension of MNIST to handwritten letters
• Shake-Shake regularization
• SpinalNet: Deep Neural Network with Gradual Input
• Nonparametric Divergence Estimation with Applications to Machine Learning on Distributions
• Generalized Bhattacharyya and Chernoff upper bounds on Bayes error using quasi-arithmetic means
• Multivariate f-Divergence Estimation With Confidence
• Ensemble Estimation of Information Divergence
• Pretrained AI Models: Performativity, Mobility, and Change
• Understanding the Limitations of Conditional Generative Models
• Learning to Benchmark: Determining Best Achievable Misclassification Error from Training Data

Cited by in corpus (2)

• SpinalNet: Deep Neural Network with Gradual Input
• Uncertainty Aware Neural Network from Similarity and Sensitivity