Optimal linear estimation under unknown nonlinear transform
Author(s): Yi, X; Wang, Z; Caramanis, C; Liu, H
DownloadTo refer to this page use:
http://arks.princeton.edu/ark:/88435/pr1hp29
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yi, X | - |
dc.contributor.author | Wang, Z | - |
dc.contributor.author | Caramanis, C | - |
dc.contributor.author | Liu, H | - |
dc.date.accessioned | 2021-10-11T14:16:59Z | - |
dc.date.available | 2021-10-11T14:16:59Z | - |
dc.date.issued | 2015 | en_US |
dc.identifier.citation | Yi, Xinyang, Zhaoran Wang, Constantine Caramanis, and Han Liu. "Optimal linear estimation under unknown nonlinear transform." In Advances in neural information processing systems 28, pp. 1549-1557. 2015. | en_US |
dc.identifier.issn | 1049-5258 | - |
dc.identifier.uri | http://papers.nips.cc/paper/6013-optimal-linear-estimation-under-unknown-nonlinear-transform | - |
dc.identifier.uri | http://arks.princeton.edu/ark:/88435/pr1hp29 | - |
dc.description.abstract | Linear regression studies the problem of estimating a model parameter β∗∈\Rp, from n observations {(yi,xi)}ni=1 from linear model yi=⟨\xi,β∗⟩+ϵi. We consider a significant generalization in which the relationship between ⟨xi,β∗⟩ and yi is noisy, quantized to a single bit, potentially nonlinear, noninvertible, as well as unknown. This model is known as the single-index model in statistics, and, among other things, it represents a significant generalization of one-bit compressed sensing. We propose a novel spectral-based estimation procedure and show that we can recover β∗ in settings (i.e., classes of link function f) where previous algorithms fail. In general, our algorithm requires only very mild restrictions on the (unknown) functional relationship between yi and ⟨xi,β∗⟩. We also consider the high dimensional setting where β∗ is sparse, and introduce a two-stage nonconvex framework that addresses estimation challenges in high dimensional regimes where p≫n. For a broad class of link functions between ⟨xi,β∗⟩ and yi, we establish minimax lower bounds that demonstrate the optimality of our estimators in both the classical and high dimensional regimes. | en_US |
dc.format.extent | 1549 - 1557 | en_US |
dc.language.iso | en_US | en_US |
dc.relation.ispartof | Advances in Neural Information Processing Systems | en_US |
dc.rights | Author's manuscript | en_US |
dc.title | Optimal linear estimation under unknown nonlinear transform | en_US |
dc.type | Conference Article | en_US |
pu.type.symplectic | http://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceeding | en_US |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
OptimalLinearEstimNonlinTransform.pdf | 414.23 kB | Adobe PDF | View/Download |
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.