Classification Logit Two-sample Testing by Neural Networks

Abstract

The recent success of generative adversarial networks and variational learning suggests training a classifier network may work well in addressing the classical two-sample problem. Network-based tests have the computational advantage that the algorithm scales to large samples. This paper proposes a two-sample statistic which is the difference of the logit function, provided by a trained classification neural network, evaluated on the testing set split of the two datasets. Theoretically, we prove the testing power to differentiate two sub-exponential densities given that the network is sufficiently parametrized. When the two densities lie on or near to low-dimensional manifolds embedded in possibly high-dimensional space, the needed network complexity is reduced to only scale with the intrinsic dimensionality. Both the approximation and estimation error analysis are based on a new result of near-manifold integral approximation. In experiments, the proposed method demonstrates better performance than previous network-based tests using classification accuracy as the two-sample statistic, and compares favorably to certain kernel maximum mean discrepancy tests on synthetic datasets and hand-written digit datasets.

References in corpus (14)

• A Mean Field View of the Landscape of Two-Layers Neural Networks
• Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes
• On Exact Computation with an Infinitely Wide Neural Net
• Generative Moment Matching Networks
• Intrinsic dimension of data representations in deep neural networks
• Optimal approximation of continuous functions by very deep ReLU networks
• Deep Network Approximation Characterized by Number of Neurons
• Nonlinear Approximation via Compositions
• Learning Deep Kernels for Non-Parametric Two-Sample Tests
• Fast Two-Sample Testing with Analytic Representations of Probability Measures
• Deep ReLU network approximation of functions on a manifold
• Elimination of All Bad Local Minima in Deep Learning
• Two-sample Statistics Based on Anisotropic Kernels
• Topological properties of the set of functions generated by neural networks of fixed size

Cited by in corpus (3)

• Convergence of flow-based generative models via proximal gradient descent in Wasserstein space
• Methods for Quantifying Dataset Similarity: a Review, Taxonomy and Comparison
• Finite-Sample Two-Group Composite Hypothesis Testing via Machine Learning