paper-with-me

Papers

The Fourier Discrepancy Function

2021-02-05 · Auricchio Gennaro, Codegoni Andrea, Gualandi Stefano, Zambon Lorenzo

In this paper, we propose the Fourier Discrepancy Function, a new discrepancy to compare discrete probability measures. We show that this discrepancy takes into account the geometry of the underlying space. We prove that the Fourier Discrepancy is convex, twice differentiable, and that its gradient has an explicit formula. We also provide a compelling statistical interpretation. Finally, we study the lower and upper tight bounds for the Fourier Discrepancy in terms of the Total Variation distance.

📄 PDF Abstract BibTeX arXiv:2102.02979

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-class Classification

Similar Papers 제목 키워드 기반

A Fourier representation of kernel Stein discrepancy with application to Goodness-of-Fit tests for measures on infinite dimensional Hilbert spaces

2022-06-09 · George Wynne, Mikołaj Kasprzak, Andrew B. Duncan

Kernel Stein discrepancy (KSD) is a widely used kernel-based measure of discrepancy between probability measures. It is often employed in the scenario where a user has a collection of samples from a candidate probability…

valid

Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels

2014-12-29 · Haim Avron, Vikas Sindhwani, Jiyan Yang, Michael Mahoney

We consider the problem of improving the efficiency of randomized Fourier feature maps to accelerate training and testing speed of kernel methods on large datasets. These approximate feature maps arise as Monte Carlo app…

Fourier Features Let Agents Learn High Precision Policies with Imitation Learning

2026-06-10 · Balázs Gyenes, Emiliyan Gospodinov, Jan Frieling, Enrico Krohmer 외 arxiv

High-precision robotic manipulation requires fine-grained spatial reasoning that is often difficult to achieve with RGB-only policies due to depth ambiguity and perspective scale issues. Policies that leverage 3D informa…

Spatial ReasoningPoint Clouds

Sk-Unet Model with Fourier Domain for Mitosis Detection

2021-09-01 · Sen yang, Feng Luo, Jun Zhang, Xiyue Wang

Mitotic count is the most important morphological feature of breast cancer grading. Many deep learning-based methods have been proposed but suffer from domain shift. In this work, we construct a Fourier-based segmentatio…

Mitosis DetectionSegmentation

FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test

2014-05-12 · Ji Zhao, Deyu Meng

The maximum mean discrepancy (MMD) is a recently proposed test statistic for two-sample test. Its quadratic time complexity, however, greatly hampers its availability to large-scale applications. To accelerate the MMD ca…

Vocal Bursts Valence Prediction