paper-with-me

홈 › Papers

Testing and Learning on Distributions with Symmetric Noise Invariance

2017-03-22 · NeurIPS 2017 12 · Ho Chung Leon Law, Christopher Yau, Dino Sejdinovic

Kernel embeddings of distributions and the Maximum Mean Discrepancy (MMD), the resulting distance between distributions, are useful tools for fully nonparametric two-sample testing and learning on distributions. However, it is rarely that all possible differences between samples are of interest -- discovered differences can be due to different types of measurement noise, data collection artefacts or other irrelevant sources of variability. We propose distances between distributions which encode invariance to additive symmetric noise, aimed at testing whether the assumed true underlying processes differ. Moreover, we construct invariant features of distributions, leading to learning algorithms robust to the impairment of the input distributions with symmetric additive noise.

📄 PDF Abstract BibTeX arXiv:1703.07596

Code (0)

등록된 구현이 없습니다.

Tasks

Two-sample testing

Similar Papers 제목 키워드 기반

Searching for Topological Symmetry in Data Haystack

2016-03-11 · Kallol Roy, Anh Tong, Jaesik Choi

Finding interesting symmetrical topological structures in high-dimensional systems is an important problem in statistical machine learning. Limited amount of available high-dimensional data and its sensitivity to noise p…

Attainability of Two-Point Testing Rates for Finite-Sample Location Estimation

2025-02-09 · Spencer Compton, Gregory Valiant

LeCam's two-point testing method yields perhaps the simplest lower bound for estimating the mean of a distribution: roughly, if it is impossible to well-distinguish a distribution centered at $\mu$ from the same distribu…

Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off

2024-02-22 · Futa Waseda, Ching-Chun Chang, Isao Echizen

Adversarial training often suffers from a robustness-accuracy trade-off, where achieving high robustness comes at the cost of accuracy. One approach to mitigate this trade-off is leveraging invariance regularization, whi…

Adversarial DefenseKnowledge DistillationRepresentation LearningSelf-Supervised Learning

Effect-Invariant Mechanisms for Policy Generalization

2023-06-19 · Sorawit Saengkyongam, Niklas Pfister, Predrag Klasnja, Susan Murphy 외

Policy learning is an important component of many real-world learning systems. A major challenge in policy learning is how to adapt efficiently to unseen environments or tasks. Recently, it has been suggested to exploit …

Hilbert geometry of the symmetric positive-definite bicone: Application to the geometry of the extended Gaussian family

2025-08-20 · Jacek Karwowski, Frank Nielsen arxiv

The extended Gaussian family is the closure of the Gaussian family obtained by completing the Gaussian family with the counterpart elements induced by degenerate covariance or degenerate precision matrices, or a mix of b…