paper-with-me

홈 › Papers

The Generalized Lasso with Nonlinear Observations and Generative Priors

2020-06-22 · NeurIPS 2020 12 · Zhaoqiang Liu, Jonathan Scarlett

In this paper, we study the problem of signal estimation from noisy non-linear measurements when the unknown $n$-dimensional signal is in the range of an $L$-Lipschitz continuous generative model with bounded $k$-dimensional inputs. We make the assumption of sub-Gaussian measurements, which is satisfied by a wide range of measurement models, such as linear, logistic, 1-bit, and other quantized models. In addition, we consider the impact of adversarial corruptions on these measurements. Our analysis is based on a generalized Lasso approach (Plan and Vershynin, 2016). We first provide a non-uniform recovery guarantee, which states that under i.i.d.~Gaussian measurements, roughly $O\left(\frac{k}{\epsilon^2}\log L\right)$ samples suffice for recovery with an $\ell_2$-error of $\epsilon$, and that this scheme is robust to adversarial noise. Then, we apply this result to neural network generative models, and discuss various extensions to other models and non-i.i.d.~measurements. Moreover, we show that our result can be extended to the uniform recovery guarantee under the assumption of a so-called local embedding property, which is satisfied by the 1-bit and censored Tobit models.

📄 PDF Abstract BibTeX arXiv:2006.12415

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing

2023-09-25 · NeurIPS 2023 11

In generative compressed sensing (GCS), we want to recover a signal $\mathbf{x}^* \in \mathbb{R}^n$ from $m$ measurements ($m\ll n$) using a generative prior $\mathbf{x}^*\in G(\mathbb{B}_2^k(r))$, where $G$ is typically…

compressed sensing

Projected Gradient Descent Algorithms for Solving Nonlinear Inverse Problems with Generative Priors

2022-09-21 · Zhaoqiang Liu, Jun Han

In this paper, we propose projected gradient descent (PGD) algorithms for signal estimation from noisy nonlinear measurements. We assume that the unknown $p$-dimensional signal lies near the range of an $L$-Lipschitz con…

LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements

2015-12-01 · NeurIPS 2015 12 · Christos Thrampoulidis, Ehsan Abbasi, Babak Hassibi

Consider estimating an unknown, but structured (e.g. sparse, low-rank, etc.), signal $x_0\in R^n$ from a vector $y\in R^m$ of measurements of the form $y_i=g_i(a_i^Tx_0)$, where the $a_i$'s are the rows of a known measur…

Penalized Likelihood Inference with Survey Data

2023-04-16 · Joann Jasiak, Purevdorj Tuvaandorj

This paper extends three Lasso inferential methods, Debiased Lasso, $C(\alpha)$ and Selective Inference to a survey environment. We establish the asymptotic validity of the inference procedures in generalized linear mode…

Survey

Distributed Reconstruction of Nonlinear Networks: An ADMM Approach

2014-03-28 · Wei Pan, Aivar Sootla, Guy-Bart Stan

In this paper, we present a distributed algorithm for the reconstruction of large-scale nonlinear networks. In particular, we focus on the identification from time-series data of the nonlinear functional forms and associ…

Time SeriesTime Series Analysis