Non-Iterative Recovery from Nonlinear Observations using Generative Models

• URL: http://arxiv.org/abs/2205.15749v2
• Date: Wed, 1 Jun 2022 03:04:56 GMT
• Title: Non-Iterative Recovery from Nonlinear Observations using Generative Models
• Authors: Jiulong Liu, Zhaoqiang Liu
• Abstract summary: We assume that the signal lies in the range of an $L$-Lipschitz continuous generative model with bounded $k$-dimensional inputs. Our reconstruction method is non-iterative (though approximating the projection step may use an iterative procedure) and highly efficient.
• Score: 14.772379476524407
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we aim to estimate the direction of an underlying signal from its nonlinear observations following the semi-parametric single index model (SIM). Unlike conventional compressed sensing where the signal is assumed to be sparse, we assume that the signal lies in the range of an $L$-Lipschitz continuous generative model with bounded $k$-dimensional inputs. This is mainly motivated by the tremendous success of deep generative models in various real applications. Our reconstruction method is non-iterative (though approximating the projection step may use an iterative procedure) and highly efficient, and it is shown to attain the near-optimal statistical rate of order $\sqrt{(k \log L)/m}$, where $m$ is the number of measurements. We consider two specific instances of the SIM, namely noisy $1$-bit and cubic measurement models, and perform experiments on image datasets to demonstrate the efficacy of our method. In particular, for the noisy $1$-bit measurement model, we show that our non-iterative method significantly outperforms a state-of-the-art iterative method in terms of both accuracy and efficiency.

Related papers

• von Mises Quasi-Processes for Bayesian Circular Regression [57.88921637944379]
  We explore a family of expressive and interpretable distributions over circle-valued random functions. The resulting probability model has connections with continuous spin models in statistical physics. For posterior inference, we introduce a new Stratonovich-like augmentation that lends itself to fast Markov Chain Monte Carlo sampling.
  arXiv  Detail & Related papers  (2024-06-19T01:57:21Z)
• Generative Principal Component Analysis [47.03792476688768]
  We study the problem of principal component analysis with generative modeling assumptions. Key assumption is that the underlying signal lies near the range of an $L$-Lipschitz continuous generative model with bounded $k$-dimensional inputs. We propose a quadratic estimator, and show that it enjoys a statistical rate of order $sqrtfracklog Lm$, where $m$ is the number of samples.
  arXiv  Detail & Related papers  (2022-03-18T01:48:16Z)
• Inverting brain grey matter models with likelihood-free inference: a tool for trustable cytoarchitecture measurements [62.997667081978825]
  characterisation of the brain grey matter cytoarchitecture with quantitative sensitivity to soma density and volume remains an unsolved challenge in dMRI. We propose a new forward model, specifically a new system of equations, requiring a few relatively sparse b-shells. We then apply modern tools from Bayesian analysis known as likelihood-free inference (LFI) to invert our proposed model.
  arXiv  Detail & Related papers  (2021-11-15T09:08:27Z)
• Sampling from Arbitrary Functions via PSD Models [55.41644538483948]
  We take a two-step approach by first modeling the probability distribution and then sampling from that model. We show that these models can approximate a large class of densities concisely using few evaluations, and present a simple algorithm to effectively sample from these models.
  arXiv  Detail & Related papers  (2021-10-20T12:25:22Z)
• Improved Prediction and Network Estimation Using the Monotone Single Index Multi-variate Autoregressive Model [34.529641317832024]
  We develop a semi-parametric approach based on the monotone single-index multi-variate autoregressive model (SIMAM) We provide theoretical guarantees for dependent data and an alternating projected gradient descent algorithm. We demonstrate the superior performance both on simulated data and two real data examples.
  arXiv  Detail & Related papers  (2021-06-28T12:32:29Z)
• The Generalized Lasso with Nonlinear Observations and Generative Priors [63.541900026673055]
  We make the assumption of sub-Gaussian measurements, which is satisfied by a wide range of measurement models. We show that our result can be extended to the uniform recovery guarantee under the assumption of a so-called local embedding property.
  arXiv  Detail & Related papers  (2020-06-22T16:43:35Z)
• Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks [78.76880041670904]
  In neural networks with binary activations and or binary weights the training by gradient descent is complicated. We propose a new method for this estimation problem combining sampling and analytic approximation steps. We experimentally show higher accuracy in gradient estimation and demonstrate a more stable and better performing training in deep convolutional models.
  arXiv  Detail & Related papers  (2020-06-04T21:51:21Z)
• Bayesian System ID: Optimal management of parameter, model, and measurement uncertainty [0.0]
  We evaluate the robustness of a probabilistic formulation of system identification (ID) to sparse, noisy, and indirect data. We show that the log posterior has improved geometric properties compared with the objective function surfaces of traditional methods.
  arXiv  Detail & Related papers  (2020-03-04T22:48:30Z)
• Statistical Outlier Identification in Multi-robot Visual SLAM using Expectation Maximization [18.259478519717426]
  This paper introduces a novel and distributed method for detecting inter-map loop closure outliers in simultaneous localization and mapping (SLAM) The proposed algorithm does not rely on a good initialization and can handle more than two maps at a time.
  arXiv  Detail & Related papers  (2020-02-07T06:34:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.