activity
20092023
most citedOn the Dispersions of Three Network Information Theory Problems

138 citations · 1.5k across the 136 of their papers we have counts for

collaborators
Showing 2011Show all

7 papers · 1 filter

stat.ML2011★ 4 cited

Automatic Relevance Determination in Nonnegative Matrix Factorization with the β-Divergence

Vincent Y. F. Tan, Cédric Févotte

This paper addresses the estimation of the latent dimensionality in nonnegative matrix factorization (NMF) with the β-divergence. The β-divergence is a family of cost functions tha…

cs.IT2011★ 1 cited

Moderate-Deviations of Lossy Source Coding for Discrete and Gaussian Sources

Vincent Y. F. Tan

We study the moderate-deviations (MD) setting for lossy source coding of stationary memoryless sources. More specifically, we derive fundamental compression limits of source codes…

cs.IT2011

Canonical Estimation in a Rare-Events Regime

Mesrob I. Ohannessian, Vincent Y. F. Tan, Munther A. Dahleh

We propose a general methodology for performing statistical inference within a `rare-events regime' that was recently suggested by Wagner, Viswanath and Kulkarni. Our approach allo…

cs.IT2011★ 11 cited

The Sender-Excited Secret Key Agreement Model: Capacity, Reliability and Secrecy Exponents

Tzu-Han Chou, Vincent Y. F. Tan, Stark C. Draper

We consider the secret key generation problem when sources are randomly excited by the sender and there is a noiseless public discussion channel. Our setting is thus similar to rec…

stat.ML2011★ 111 cited

High-dimensional structure estimation in Ising models: Local separation criterion

Animashree Anandkumar, Vincent Y. F. Tan, Furong Huang +1

We consider the problem of high-dimensional Ising (graphical) model selection. We propose a simple algorithm for structure estimation based on the thresholding of the empirical con…

cs.LG2011★ 65 cited

High-Dimensional Gaussian Graphical Model Selection: Walk Summability and Local Separation Criterion

Animashree Anandkumar, Vincent Y. F. Tan, Alan. S. Willsky

We consider the problem of high-dimensional Gaussian graphical model selection. We identify a set of graphs for which an efficient estimation algorithm exists, and this algorithm i…