Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Intrinsic Dimension Estimation Using Wasserstein Distances

About

It has long been thought that high-dimensional data encountered in many practical machine learning tasks have low-dimensional structure, i.e., the manifold hypothesis holds. A natural question, thus, is to estimate the intrinsic dimension of a given population distribution from a finite sample. We introduce a new estimator of the intrinsic dimension and provide finite sample, non-asymptotic guarantees. We then apply our techniques to get new sample complexity bounds for Generative Adversarial Networks (GANs) depending only on the intrinsic dimension of the data.

Adam Block, Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin• 2021

Related benchmarks

TaskDatasetResultRank
Intrinsic Dimension EstimationMNIST
Intrinsic Dimension Estimate9.49
13
Intrinsic Dimension EstimationM5 manifold d=2
Mean Dimension Estimate2.35
10
Intrinsic Dimension EstimationM8 manifold d=2
Mean Dimension Estimate2.29
10
Intrinsic Dimension EstimationM10 Manifold (d=2)
Estimated Dimension2.44
10
Intrinsic Dimension EstimationManifold M5 (d=2) n=2000 (uniform samples)
Mean Dimension Estimate2.26
10
Intrinsic Dimension EstimationManifold M7 (d=2) n=2000 (uniform samples)
Mean Dimension Estimate2.44
10
Intrinsic Dimension EstimationManifold M9 d=2 n=2000 (uniform samples)
Mean Dimension Estimate2.29
10
Intrinsic Dimension EstimationManifold M10 d=2 n=2000 (uniform samples)
Mean Dimension Estimate2.31
10
Intrinsic Dimension EstimationMNL5(12) (n=2000)
Mean Dimension Estimate5.8
10
Intrinsic Dimension EstimationM6 manifold d=1
Mean Dimension Estimate2.21
10
Showing 10 of 54 rows

Other info

Follow for update