English
Related papers

Related papers: Inference in Deep Networks in High Dimensions

200 papers

Phase retrieval refers to the problem of recovering a high-dimensional vector $\boldsymbol{x} \in \mathbb{C}^N$ from the magnitude of its linear transform $\boldsymbol{z} = A \boldsymbol{x}$, observed through a noisy channel. To improve the…

Computation · Statistics 2024-10-10 Hajime Ueda , Shun Katakami , Masato Okada

While loopy belief propagation (LBP) performs reasonably well for inference in some Gaussian graphical models with cycles, its performance is unsatisfactory for many others. In particular for some models LBP does not converge, and in…

Machine Learning · Statistics 2015-05-28 Ying Liu , Venkat Chandrasekaran , Animashree Anandkumar , Alan S. Willsky

We consider the estimation of an i.i.d. (possibly non-Gaussian) vector $\xbf \in \R^n$ from measurements $\ybf \in \R^m$ obtained by a general cascade model consisting of a known linear transform followed by a probabilistic componentwise…

Information Theory · Computer Science 2012-12-04 Ulugbek S. Kamilov , Sundeep Rangan , Alyson K. Fletcher , Michael Unser

The generalized linear model (GLM), where a random vector $\boldsymbol{x}$ is observed through a noisy, possibly nonlinear, function of a linear transform output $\boldsymbol{z}=\boldsymbol{Ax}$, arises in a range of applications such as…

Information Theory · Computer Science 2016-12-06 Philip Schniter , Sundeep Rangan , Alyson K. Fletcher

Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied…

Machine Learning · Computer Science 2016-06-06 Andriy Mnih , Karol Gregor

In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex…

Machine Learning · Computer Science 2023-11-10 Anshuk Uppal , Kristoffer Stensbo-Smidt , Wouter Boomsma , Jes Frellsen

The standard linear regression (SLR) problem is to recover a vector $\mathbf{x}^0$ from noisy linear observations $\mathbf{y}=\mathbf{Ax}^0+\mathbf{w}$. The approximate message passing (AMP) algorithm recently proposed by Donoho, Maleki,…

Information Theory · Computer Science 2018-07-24 Sundeep Rangan , Philip Schniter , Alyson K. Fletcher

Estimation of a vector from quantized linear measurements is a common problem for which simple linear techniques are suboptimal -- sometimes greatly so. This paper develops generalized approximate message passing (GAMP) algorithms for…

Information Theory · Computer Science 2015-03-24 Ulugbek Kamilov , Vivek K. Goyal , Sundeep Rangan

There exists recent work in computer vision, named VAR, that proposes a new autoregressive paradigm for image generation. Diverging from the vanilla next-token prediction, VAR structurally reformulates the image generation into a coarse to…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Sucheng Ren , Yaodong Yu , Nataniel Ruiz , Feng Wang , Alan Yuille , Cihang Xie

Deep Gaussian Processes (DGPs) are hierarchical generalizations of Gaussian Processes that combine well calibrated uncertainty estimates with the high flexibility of multilayer models. One of the biggest challenges with these models is that…

Machine Learning · Statistics 2018-11-13 Marton Havasi , José Miguel Hernández-Lobato , Juan José Murillo-Fuentes

Estimating a vector $\mathbf{x}$ from noisy linear measurements $\mathbf{Ax}+\mathbf{w}$ often requires use of prior knowledge or structural constraints on $\mathbf{x}$ for accurate reconstruction. Several recent works have considered…

Information Theory · Computer Science 2020-01-29 Alyson K. Fletcher , Sundeep Rangan , Subrata Sarkar , Philip Schniter

Deep feedforward neural networks (DFNNs) are a powerful tool for functional approximation. We describe flexible versions of generalized linear and generalized linear mixed models incorporating basis functions formed by a DFNN. The…

Computation · Statistics 2018-05-28 Minh-Ngoc Tran , Nghia Nguyen , David Nott , Robert Kohn

Generalized approximate message passing (GAMP) is a promising technique for unknown signal reconstruction of generalized linear models (GLM). However, it requires that the transformation matrix has independent and identically distributed…

Information Theory · Computer Science 2021-10-18 Feiyan Tian , Lei Liu , Xiaoming Chen

Multilayer (or deep) networks are powerful probabilistic models based on multiple stages of a linear transform followed by a non-linear (possibly random) function. In general, the linear transforms are defined by matrices and the non-linear…

Information Theory · Computer Science 2017-10-13 Galen Reeves

We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a…

Machine Learning · Statistics 2014-06-02 Danilo Jimenez Rezende , Shakir Mohamed , Daan Wierstra

Large neural networks trained on large datasets have become the dominant paradigm in machine learning. These systems rely on maximum likelihood point estimates of their parameters, precluding them from expressing model uncertainty. This may…

Machine Learning · Statistics 2024-05-01 Javier Antoran

We consider the estimation of an i.i.d.\ random vector observed through a linear transform followed by a componentwise, probabilistic (possibly nonlinear) measurement channel. A novel algorithm, called generalized approximate message…

Information Theory · Computer Science 2012-08-15 Sundeep Rangan

We consider the problem of signal estimation in generalized linear models defined via rotationally invariant design matrices. Since these matrices can have an arbitrary spectral distribution, this model is well suited for capturing complex…

Machine Learning · Statistics 2022-06-10 Ramji Venkataramanan , Kevin Kögler , Marco Mondelli

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Machine Learning · Statistics 2019-10-29 Raanan Y. Rohekar , Yaniv Gurwicz , Shami Nisimov , Gal Novik

The Bayesian paradigm has the potential to solve core issues of deep neural networks such as poor calibration and data inefficiency. Alas, scaling Bayesian inference to large weight spaces often requires restrictive approximations. In this…