Minimax rate of distribution estimation on unknown submanifolds under adversarial losses
From MaRDI portal
(Redirected from Publication:6177323)
Abstract: Statistical inference from high-dimensional data with low-dimensional structures has recently attracted lots of attention. In machine learning, deep generative modeling approaches implicitly estimate distributions of complex objects by creating new samples from the underlying distribution, and have achieved great success in generating synthetic realistic-looking images and texts. A key step in these approaches is the extraction of latent features or representations (encoding) that can be used for accurately reconstructing the original data (decoding). In other words, low-dimensional manifold structure is implicitly assumed and utilized in the distribution modeling and estimation. To understand the benefit of low-dimensional manifold structure in generative modeling, we build a general minimax framework for distribution estimation on unknown submanifold under adversarial losses, with suitable smoothness assumptions on the target distribution and the manifold. The established minimax rate elucidates how various problem characteristics, including intrinsic dimensionality of the data and smoothness levels of the target distribution and the manifold, affect the fundamental limit of high-dimensional distribution estimation. To prove the minimax upper bound, we construct an estimator based on a mixture of locally fitted generative models, which is motivated by the partition of unity technique from differential geometry and is necessary to cover cases where the underlying data manifold does not admit a global parametrization. We also propose a data-driven adaptive estimator that is shown to simultaneously attain within a logarithmic factor of the optimal rate over a large collection of distribution classes.
Recommendations
- Minimax Estimation of Discrete Distributions Under <inline-formula> <tex-math notation="LaTeX">$\ell _{1}$ </tex-math></inline-formula> Loss
- Tight minimax rates for manifold estimation under Hausdorff loss
- Minimax adaptive estimation in manifold inference
- On adaptive minimax density estimation on R^d
- Minimax rates for estimating the dimension of a manifold
- Minimax rate adaptive estimation over continuous hyper-parameters
- Minimax invariant estimation of a continuous distribution function under entropy loss
- scientific article; zbMATH DE number 6999890
- Density estimation on an unknown submanifold
Cites work
- A kernel two-sample test
- Bayesian manifold regression
- Boundary regularity of maps with convex potentials. II
- Cramer-Wold auto-encoder
- Deconvolution for the Wasserstein metric and geometric inference
- Density estimation on an unknown submanifold
- High-dimensional statistics. A non-asymptotic viewpoint
- scientific article; zbMATH DE number 52737 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 7626743 (Why is no real title available?)
- scientific article; zbMATH DE number 5681750 (Why is no real title available?)
- Inferential Wasserstein Generative Adversarial Networks
- Information-theoretic determination of minimax rates of convergence
- Integral Probability Metrics and Their Generating Classes of Functions
- Introduction to nonparametric estimation
- Introduction to Smooth Manifolds
- Manifold estimation and singular deconvolution under Hausdorff loss
- Measure estimation on manifolds: an optimal transport approach
- Minimax estimation of kernel mean embeddings
- Minimax estimation of smooth densities in Wasserstein distance
- Minimax manifold estimation
- Minimax rate of distribution estimation on unknown submanifolds under adversarial losses
- Nearly unbiased variable selection under minimax concave penalty
- Nonasymptotic rates for manifold, tangent space and curvature estimation
- On a Problem of Adaptive Estimation in Gaussian White Noise
- On Local Intrinsic Dimension Estimation and Its Applications
- Optimal Transport
- Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
- Some theoretical properties of GANs
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Cited in
(12)- scientific article; zbMATH DE number 6999890 (Why is no real title available?)
- Minimax rate of distribution estimation on unknown submanifolds under adversarial losses
- Emerging directions in Bayesian computation
- Wasserstein upper bounds of L^p-norms for multivariate densities in Besov spaces
- Wasserstein generative adversarial networks are minimax optimal distribution estimators
- Lipschitz-regularized gradient flows and generative particle algorithms for high-dimensional scarce data
- Doubly robust conditional independence testing with generative neural networks
- Density estimation using the perceptron
- Rates of convergence for nonparametric estimation of singular distributions using generative adversarial networks
- Diffeomorphic measure matching with kernels for generative modeling
- On reverse inequalities for Besov integral probability metrics between smooth densities
- Statistical Quantile Learning for Large Additive Latent Variable Models
This page was built for publication: Minimax rate of distribution estimation on unknown submanifolds under adversarial losses
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6177323)
