Density estimation for Hellinger via minimum-distance estimators: mixtures of Gaussians, log-concave, and more

• URL: http://arxiv.org/abs/2606.11469v1
• Date: Tue, 09 Jun 2026 21:57:20 GMT
• Title: Density estimation for Hellinger via minimum-distance estimators: mixtures of Gaussians, log-concave, and more
• Abstract summary: We study the task of density estimation, where we hope to accurately estimate a probability density from $n$ samples.<n>We extend the minimum-distance estimator approach for learning within Hellinger distance.
• Score: 6.219565597575514
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the task of density estimation, where we hope to accurately estimate a probability density from $n$ samples. A textbook method for density estimation in total variation distance is the minimum-distance estimator approach, where we conclude both the algorithm and the analysis merely from bounding the VC dimension of a particular concept class (the so-called Yatracos class). While this technique has originally yielded sharp guarantees primarily for total variation distance, in this work we extend the minimum-distance estimator approach for learning within Hellinger distance. Our main observation is that we may produce an analogous recipe for Hellinger (where we only require bounding the VC dimension of a related concept class) by drawing connections to recent results yielding reverse data processing inequalities. This recipe is flexible enough to accommodate fast algorithms originally designed for total variation distance; by modifying the approach of Acharya et al. (2017) we conclude the first near-linear time algorithm for learning classes including univariate mixtures of log-concave densities and mixtures of Gaussians (with arbitrary variances), with near-optimal sample complexity.

Related papers

• Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal [9.766173684831324]
  We characterize the minimax optimal rates for all regimes, and identify phase transitions of the optimal rates as the samples per terminal vary from sparse to dense.<n>This fully solves the problem left open by previous works, whose scopes are limited to regimes with either dense samples or a single sample per terminal.<n>The optimal rates are immediate for various special cases such as density estimation, Gaussian, binary, Poisson and heteroskedastic regression models.
  arXiv  Detail & Related papers  (2025-01-14T06:41:55Z)
• Collaborative Heterogeneous Causal Inference Beyond Meta-analysis [68.4474531911361]
  We propose a collaborative inverse propensity score estimator for causal inference with heterogeneous data. Our method shows significant improvements over the methods based on meta-analysis when heterogeneity increases.
  arXiv  Detail & Related papers  (2024-04-24T09:04:36Z)
• Sobolev Space Regularised Pre Density Models [51.558848491038916]
  We propose a new approach to non-parametric density estimation that is based on regularizing a Sobolev norm of the density. This method is statistically consistent, and makes the inductive validation model clear and consistent.
  arXiv  Detail & Related papers  (2023-07-25T18:47:53Z)
• Linearized Wasserstein dimensionality reduction with approximation guarantees [65.16758672591365]
  LOT Wassmap is a computationally feasible algorithm to uncover low-dimensional structures in the Wasserstein space. We show that LOT Wassmap attains correct embeddings and that the quality improves with increased sample size. We also show how LOT Wassmap significantly reduces the computational cost when compared to algorithms that depend on pairwise distance computations.
  arXiv  Detail & Related papers  (2023-02-14T22:12:16Z)
• Density Ratio Estimation via Infinitesimal Classification [85.08255198145304]
  We propose DRE-infty, a divide-and-conquer approach to reduce Density ratio estimation (DRE) to a series of easier subproblems. Inspired by Monte Carlo methods, we smoothly interpolate between the two distributions via an infinite continuum of intermediate bridge distributions. We show that our approach performs well on downstream tasks such as mutual information estimation and energy-based modeling on complex, high-dimensional datasets.
  arXiv  Detail & Related papers  (2021-11-22T06:26:29Z)
• Kernel Density Estimation by Stagewise Algorithm with a Simple Dictionary [0.0]
  This paper studies kernel density estimation by stagewise algorithm with a simple dictionary on U-divergence. We randomly split an i.i.d. sample into two disjoint sets, one for constructing the kernels in the dictionary and the other for evaluating the estimator.
  arXiv  Detail & Related papers  (2021-07-27T17:05:06Z)
• Learning Optical Flow from a Few Matches [67.83633948984954]
  We show that the dense correlation volume representation is redundant and accurate flow estimation can be achieved with only a fraction of elements in it. Experiments show that our method can reduce computational cost and memory use significantly, while maintaining high accuracy.
  arXiv  Detail & Related papers  (2021-04-05T21:44:00Z)
• Efficient Interpolation of Density Estimators [23.154249845820306]
  We study the problem of space and time efficient evaluation of a nonparametric estimator that approximates an unknown density. Our result gives a new statistical perspective on the problem of fast evaluation of kernel density estimators in the presence of underlying smoothness.
  arXiv  Detail & Related papers  (2020-11-10T06:05:00Z)
• Learning Minimax Estimators via Online Learning [55.92459567732491]
  We consider the problem of designing minimax estimators for estimating parameters of a probability distribution. We construct an algorithm for finding a mixed-case Nash equilibrium.
  arXiv  Detail & Related papers  (2020-06-19T22:49:42Z)
• Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimation [23.38076756988258]
  We propose a new single-model based approach to quantify uncertainty in deep neural networks. We use a mean-field approximation formula to compute an analytically intractable integral. Empirically, the proposed approach performs competitively when compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-06-13T07:32:38Z)
• Scalable Distributed Approximation of Internal Measures for Clustering Evaluation [5.144809478361603]
  Internal measure for clustering evaluation is the silhouette coefficient, whose computation requires a quadratic number of distance calculations. We present the first scalable algorithm to compute such a rigorous approximation for the evaluation of clusterings based on any metric distances. We also prove that the algorithm can be adapted to obtain rigorous approximations of other internal measures of clustering quality, such as cohesion and separation.
  arXiv  Detail & Related papers  (2020-03-03T10:28:14Z)

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.