Generic error bounds for the generalized Lasso with sub-exponential data

Author:

Genzel MartinORCID,Kipp Christian

Abstract

AbstractThis work performs a non-asymptotic analysis of the generalized Lasso under the assumption of sub-exponential data. Our main results continue recent research on the benchmark case of (sub-)Gaussian sample distributions and thereby explore what conclusions are still valid when going beyond. While many statistical features remain unaffected (e.g., consistency and error decay rates), the key difference becomes manifested in how the complexity of the hypothesis set is measured. It turns out that the estimation error can be controlled by means of two complexity parameters that arise naturally from a generic-chaining-based proof strategy. The output model can be non-realizable, while the only requirement for the input vector is a generic concentration inequality of Bernstein-type, which can be implemented for a variety of sub-exponential distributions. This abstract approach allows us to reproduce, unify, and extend previously known guarantees for the generalized Lasso. In particular, we present applications to semi-parametric output models and phase retrieval via the lifted Lasso. Moreover, our findings are discussed in the context of sparse recovery and high-dimensional estimation problems.

Funder

Bundesministerium für Bildung und Forschung

Deutsche Forschungsgemeinschaft

Publisher

Springer Science and Business Media LLC

Subject

Computational Mathematics,Radiology, Nuclear Medicine and imaging,Signal Processing,Algebra and Number Theory,Analysis

Reference66 articles.

1. Adamczak, R.: A note on the Hanson–Wright inequality for random vectors with dependencies. Electron. Commun. Probab. 20(72), 1–13 (2015)

2. Ai, A., Lapanowski, A., Plan, Y., Vershynin, R.: One-bit compressed sensing with non-Gaussian measurements. Linear Algebra Appl. 441, 222–239 (2014)

3. Amelunxen, D., Lotz, M., McCoy, M.B., Tropp, J.A.: Living on the edge: phase transitions in convex programs with random data. Inf. Infer. 3(3), 224–294 (2014)

4. Bakhshizadeh, M., Maleki, A., de la Pena, V.H.: Sharp concentration results for heavy-tailed distributions (2020). Preprint arXiv:2003.13819

5. Brillinger, D.R.: A generalized linear model with “Gaussian’’ regressor variables. In: Bickel, P.J., Doksum, K., Hodges, J. (eds.) A Festschrift For Erich L. Lehmann, pp. 97–114. Chapman and Hall/CRC, Boca Raton (1982)

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3