Learning Deep Kernels for Non-Parametric Two-Sample Tests

Abstract

We propose a class of kernel-based two-sample tests, which aim to determine whether two sets of samples are drawn from the same distribution. Our tests are constructed from kernels parameterized by deep neural nets, trained to maximize test power. These tests adapt to variations in distribution smoothness and shape over space, and are especially suited to high dimensions and complex data. By contrast, the simpler kernels used in prior kernel testing work are spatially homogeneous, and adaptive only in lengthscale. We explain how this scheme includes popular classifier-based two-sample tests as a special case, but improves on them in general. We provide the first proof of consistency for the proposed adaptation method, which applies both to kernels on deep features and to simpler radial basis kernels or multiple kernel learning. In experiments, we establish the superior performance of our deep kernels in hypothesis testing on benchmark and real-world data. The code of our deep-kernel-based two sample tests is available at https://github.com/fengliu90/DK-for-TST.

Cited by in corpus (24)

• M${}^3$Care: Learning with Missing Modalities in Multimodal Healthcare Data
• A Kernel Two-Sample Test for Functional Data
• Bilateral Dependency Optimization: Defending Against Model-inversion Attacks
• Benchmarking Simulation-Based Inference
• Vicinal and categorical domain adaptation
• Sliced Kernelized Stein Discrepancy
• Methods for Quantifying Dataset Similarity: a Review, Taxonomy and Comparison
• MMD Aggregated Two-Sample Test
• Learning from a Complementary-label Source Domain: Theory and Algorithms
• Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings
• Learning Kernel Tests Without Data Splitting
• Classification Logit Two-sample Testing by Neural Networks
• Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation
• Higher Order Kernel Mean Embeddings to Capture Filtrations of Stochastic Processes
• Learning Smooth Representation for Unsupervised Domain Adaptation
• Two-sample Test with Kernel Projected Wasserstein Distance
• Model-agnostic out-of-distribution detection using combined statistical tests
• Emotion Transfer Using Vector-Valued Infinite Task Learning
• Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data
• Kernel Hypothesis Testing with Set-valued Data
• Neural Dependency Coding inspired Multimodal Fusion
• A Witness Two-Sample Test
• A fast and effective kernel two-sample test for large-scale data
• High-Dimensional Non-Parametric Density Estimation in Mixed Smooth Sobolev Spaces