Search Results for author: Ramji Venkataramanan

Found 12 papers, 2 papers with code

PCA Initialization for Approximate Message Passing in Rotationally Invariant Models

no code implementations NeurIPS 2021 Marco Mondelli, Ramji Venkataramanan

However, the existing analysis of AMP requires an initialization that is both correlated with the signal and independent of the noise, which is often unrealistic in practice.

Approximate Message Passing with Spectral Initialization for Generalized Linear Models

no code implementations7 Oct 2020 Marco Mondelli, Ramji Venkataramanan

We consider the problem of estimating a signal from measurements obtained via a generalized linear model.

Optimal Combination of Linear and Spectral Estimators for Generalized Linear Models

no code implementations7 Aug 2020 Marco Mondelli, Christos Thrampoulidis, Ramji Venkataramanan

This allows us to compute the Bayes-optimal combination of $\hat{\boldsymbol x}^{\rm L}$ and $\hat{\boldsymbol x}^{\rm s}$, given the limiting distribution of the signal $\boldsymbol x$.

Estimation of Low-Rank Matrices via Approximate Message Passing

1 code implementation6 Nov 2017 Andrea Montanari, Ramji Venkataramanan

In this paper we present a practical algorithm that can achieve Bayes-optimal accuracy above the spectral threshold.

Community Detection

Empirical Bayes Estimators for High-Dimensional Sparse Vectors

no code implementations28 Jul 2017 Pavan Srinath, Ramji Venkataramanan

An empirical Bayes shrinkage estimator, derived using a Bernoulli-Gaussian prior, is analyzed and compared with the well-known soft-thresholding estimator.

A strong converse bound for multiple hypothesis testing, with applications to high-dimensional estimation

no code implementations14 Jun 2017 Ramji Venkataramanan, Oliver Johnson

In statistical inference problems, we wish to obtain lower bounds on the minimax risk, that is to bound the performance of any possible estimator.

Active Learning Density Estimation +1

Multilayer Codes for Synchronization from Deletions

1 code implementation18 May 2017 Mahed Abroshan, Ramji Venkataramanan, Albert Guillen i Fabregas

Consider two remote nodes, each having a binary sequence.

Information Theory Information Theory

Finite Sample Analysis of Approximate Message Passing Algorithms

no code implementations6 Jun 2016 Cynthia Rush, Ramji Venkataramanan

The concentration inequality also indicates that the number of AMP iterations $t$ can grow no faster than order $\frac{\log n}{\log \log n}$ for the performance to be close to the state evolution predictions with high probability.

Cluster-Seeking James-Stein Estimators

no code implementations1 Feb 2016 K. Pavan Srinath, Ramji Venkataramanan

The JS-estimator shrinks the observed vector towards the origin, and the risk reduction over the ML-estimator is greatest for $\boldsymbol{\theta}$ that lie close to the origin.

Capacity-achieving Sparse Superposition Codes via Approximate Message Passing Decoding

no code implementations23 Jan 2015 Cynthia Rush, Adam Greig, Ramji Venkataramanan

Sparse superposition codes were recently introduced by Barron and Joseph for reliable communication over the AWGN channel at rates approaching the channel capacity.

Lossy Compression via Sparse Linear Regression: Computationally Efficient Encoding and Decoding

no code implementations7 Dec 2012 Ramji Venkataramanan, Tuhin Sarkar, Sekhar Tatikonda

The proposed encoding algorithm sequentially chooses columns of the design matrix to successively approximate the source sequence.

Lossy Compression via Sparse Linear Regression: Performance under Minimum-distance Encoding

no code implementations3 Feb 2012 Ramji Venkataramanan, Antony Joseph, Sekhar Tatikonda

We study a new class of codes for lossy compression with the squared-error distortion criterion, designed using the statistical framework of high-dimensional linear regression.

Cannot find the paper you are looking for? You can Submit a new open access paper.