19 citations · 59 across the 11 of their papers we have counts for
14 papers
Direct and Indirect Effects -- An Information Theoretic Perspective
Gabriel Schamberg, William Chapman, Shang-Ping Xie +1
Information theoretic (IT) approaches to quantifying causal influences have experienced some popularity in the literature, in both theoretical and applied (e.g. neuroscience and cl…
On the Bias of Directed Information Estimators
Gabriel Schamberg, Todd P. Coleman
When estimating the directed information between two jointly stationary Markov processes, it is typically assumed that the recipient of the directed information is itself Markov of…
Construction and Analysis of Posterior Matching in Arbitrary Dimensions via Optimal Transport
Diego A. Mesa, Rui Ma, Siva K. Gorantla +1
The posterior matching scheme, for feedback encoding of a message point lying on the unit interval over memoryless channels, maximizes mutual information for an arbitrary number of…
Measuring Sample Path Causal Influences with Relative Entropy
Gabriel Schamberg, Todd P. Coleman
We present a sample path dependent measure of causal influence between time series. The proposed causal measure is a random sequence, a realization of which enables identification…
A Sample Path Measure of Causal Influence
Gabriel Schamberg, Todd P. Coleman
We present a sample path dependent measure of causal influence between two time series. The proposed measure is a random variable whose expected sum is the directed information. A…
Bayesian Lasso Posterior Sampling via Parallelized Measure Transport
Marcela Mendoza, Alexis Allegra, Todd P. Coleman
It is well known that the Lasso can be interpreted as a Bayesian posterior mode estimate with a Laplacian prior. Obtaining samples from the full posterior distribution, the Bayesia…
A Modularized Efficient Framework for Non-Markov Time Series Estimation
Gabriel Schamberg, Demba Ba, Todd P. Coleman
We present a compartmentalized approach to finding the maximum a-posteriori (MAP) estimate of a latent time series that obeys a dynamic stochastic model and is observed through noi…
Timing Channel: Achievable Rate in the Finite Block-Length Regime
Thomas J. Riedl, Todd P. Coleman, Andrew C. Singer
The exponential server timing channel is known to be the simplest, and in some sense canonical, queuing timing channel. The capacity of this infinite-memory channel is known. Here,…
Tractable Fully Bayesian Inference via Convex Optimization and Optimal Transport Theory
Sanggyun Kim, Diego Mesa, Rui Ma +1
We consider the problem of transforming samples from one continuous source distribution into samples from another target distribution. We demonstrate with optimal transport theory…
An Optimizer's Approach to Stochastic Control Problems with Nonclassical Information Structures
Ankur A. Kulkarni, Todd P. Coleman
We present an optimization-based approach to stochastic control problems with nonclassical information structures. We cast these problems equivalently as optimization prob- lems on…
Directed Information Graphs
Christopher J. Quinn, Negar Kiyavash, Todd P. Coleman
We propose a graphical model for representing networks of stochastic processes, the minimal generative model graph. It is based on reduced factorizations of the joint distribution…
Information-Theoretic Viewpoints on Optimal Causal Coding-Decoding Problems
Siva Gorantla, Todd Coleman
In this paper we consider an interacting two-agent sequential decision-making problem consisting of a Markov source process, a causal encoder with feedback, and a causal decoder. M…
Causal Dependence Tree Approximations of Joint Distributions for Multiple Random Processes
Christopher J. Quinn, Todd P. Coleman, Negar Kiyavash
We investigate approximating joint distributions of random processes with causal dependence tree distributions. Such distributions are particularly useful in providing parsimonious…
Bit-wise Unequal Error Protection for Variable Length Block Codes with Feedback
Baris Nakiboglu, Siva K. Gorantla, Lizhong Zheng +1
The bit-wise unequal error protection problem, for the case when the number of groups of bits is fixed, is considered for variable length block codes with feedback. An encod…