Limit Distribution Theory for the Smooth 1-Wasserstein Distance with Applications

• URL: http://arxiv.org/abs/2107.13494v2
• Date: Thu, 29 Jul 2021 13:39:02 GMT
• Title: Limit Distribution Theory for the Smooth 1-Wasserstein Distance with Applications
• Authors: Ritwik Sadhu and Ziv Goldfeld and Kengo Kato
• Abstract summary: smooth 1-Wasserstein distance (SWD) $W_1sigma$ was recently proposed as a means to mitigate the curse of dimensionality in empirical approximation. This work conducts a thorough statistical study of the SWD, including a high-dimensional limit distribution result.
• Score: 18.618590805279187
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The smooth 1-Wasserstein distance (SWD) $W_1^\sigma$ was recently proposed as a means to mitigate the curse of dimensionality in empirical approximation while preserving the Wasserstein structure. Indeed, SWD exhibits parametric convergence rates and inherits the metric and topological structure of the classic Wasserstein distance. Motivated by the above, this work conducts a thorough statistical study of the SWD, including a high-dimensional limit distribution result for empirical $W_1^\sigma$, bootstrap consistency, concentration inequalities, and Berry-Esseen type bounds. The derived nondegenerate limit stands in sharp contrast with the classic empirical $W_1$, for which a similar result is known only in the one-dimensional case. We also explore asymptotics and characterize the limit distribution when the smoothing parameter $\sigma$ is scaled with $n$, converging to $0$ at a sufficiently slow rate. The dimensionality of the sampled distribution enters empirical SWD convergence bounds only through the prefactor (i.e., the constant). We provide a sharp characterization of this prefactor's dependence on the smoothing parameter and the intrinsic dimension. This result is then used to derive new empirical convergence rates for classic $W_1$ in terms of the intrinsic dimension. As applications of the limit distribution theory, we study two-sample testing and minimum distance estimation (MDE) under $W_1^\sigma$. We establish asymptotic validity of SWD testing, while for MDE, we prove measurability, almost sure convergence, and limit distributions for optimal estimators and their corresponding $W_1^\sigma$ error. Our results suggest that the SWD is well suited for high-dimensional statistical learning and inference.

Related papers

• Non-asymptotic bounds for forward processes in denoising diffusions: Ornstein-Uhlenbeck is hard to beat [49.1574468325115]
  This paper presents explicit non-asymptotic bounds on the forward diffusion error in total variation (TV) We parametrise multi-modal data distributions in terms of the distance $R$ to their furthest modes and consider forward diffusions with additive and multiplicative noise.
  arXiv  Detail & Related papers  (2024-08-25T10:28:31Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Gaussian-Smoothed Sliced Probability Divergences [15.123608776470077]
  We show that smoothing and slicing preserve the metric property and the weak topology. We also derive other properties, including continuity, of different divergences with respect to the smoothing parameter.
  arXiv  Detail & Related papers  (2024-04-04T07:55:46Z)
• Statistical Efficiency of Distributional Temporal Difference Learning [24.03281329962804]
  We analyze the finite-sample performance of distributional temporal difference learning (CTD) and quantile temporal difference learning (QTD) For a $gamma$-discounted infinite-horizon decision process, we show that for NTD we need $tildeOleft(frac1varepsilon2p (1-gamma)2pright)$ to achieve an $varepsilon$-optimal estimator with high probability. We establish a novel Freedman's inequality in Hilbert spaces, which would be of independent interest.
  arXiv  Detail & Related papers  (2024-03-09T06:19:53Z)
• Estimation of entropy-regularized optimal transport maps between non-compactly supported measures [15.857723276537248]
  This paper addresses the problem of estimating entropy-regularized optimal transport maps with squared-Euclidean cost between source and target measures that are subGaussian.
  arXiv  Detail & Related papers  (2023-11-20T17:18:21Z)
• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models [49.81937966106691]
  We develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models. In contrast to prior works, our theory is developed based on an elementary yet versatile non-asymptotic approach.
  arXiv  Detail & Related papers  (2023-06-15T16:30:08Z)
• A High-dimensional Convergence Theorem for U-statistics with Applications to Kernel-based Testing [3.469038201881982]
  We prove a convergence theorem for U-statistics of degree two, where the data dimension $d$ is allowed to scale with sample size $n$. We apply our theory to two popular kernel-based distribution tests, MMD and KSD, whose high-dimensional performance has been challenging to study.
  arXiv  Detail & Related papers  (2023-02-11T12:49:46Z)
• High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize [55.0090961425708]
  We propose a new, simplified high probability analysis of AdaGrad for smooth, non- probability problems. We present our analysis in a modular way and obtain a complementary $mathcal O (1 / TT)$ convergence rate in the deterministic setting. To the best of our knowledge, this is the first high probability for AdaGrad with a truly adaptive scheme, i.e., completely oblivious to the knowledge of smoothness.
  arXiv  Detail & Related papers  (2022-04-06T13:50:33Z)
• Dimension-agnostic inference using cross U-statistics [33.17951971728784]
  We introduce an approach that uses variational representations of existing test statistics along with sample splitting and self-normalization. The resulting statistic can be viewed as a careful modification of degenerate U-statistics, dropping diagonal blocks and retaining off-diagonal blocks.
  arXiv  Detail & Related papers  (2020-11-10T12:21:34Z)
• On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification [101.0377583883137]
  Projection robust (PR) OT seeks to maximize the OT cost between two measures by choosing a $k$-dimensional subspace onto which they can be projected. Our first contribution is to establish several fundamental statistical properties of PR Wasserstein distances. Next, we propose the integral PR Wasserstein (IPRW) distance as an alternative to the PRW distance, by averaging rather than optimizing on subspaces.
  arXiv  Detail & Related papers  (2020-06-22T14:35:33Z)
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction [63.41789556777387]
  Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP) We show that the number of samples needed to yield an entrywise $varepsilon$-accurate estimate of the Q-function is at most on the order of $frac1mu_min (1-gamma)5varepsilon2+ fract_mixmu_min (1-gamma)$ up to some logarithmic factor.
  arXiv  Detail & Related papers  (2020-06-04T17:51:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.