17 citations · 42 across the 15 of their papers we have counts for
16 papers
Prediction with eventual almost sure guarantees
Changlong Wu, Narayana Santhanam
We study the problem of sequentially predicting properties of a probabilistic model and its next outcome over an infinite horizon, with the goal of ensuring that the predictions in…
Almost Uniform Sampling From Neural Networks
Changlong Wu, Narayana Prasad Santhanam
Given a length sample from and a neural network with a fixed architecture with weights, neurons, linear threshold activation functions, and binary output…
Thermodynamic Computing
Tom Conte, Erik DeBenedictis, Natesh Ganesh +36
The hardware and software foundations laid in the first half of the 20th Century enabled the computing technologies that have transformed the world, but these foundations are now u…
Tail redundancy and its characterization of compression of memoryless sources
Maryam Hosseini, Narayana Santhanam
We formalize the tail redundancy of a collection of distributions over a countably infinite alphabet, and show that this fundamental quantity characterizes the asymptotic per-symbo…
Redundancy of unbounded memory Markov classes with continuity conditions
Changlong Wu, Maryam Hosseini, Narayana Santhanam
We study the redundancy of universally compressing strings generated by a binary Markov source without any bound on the memory. To better understand the connec…
Community Detection Using Slow Mixing Markov Models
Ramezan Paravi Torghabeh, Narayana Prasad Santhanam
The task of \emph{community detection} in a graph formalizes the intuitive task of grouping together subsets of vertices such that vertices within clusters are connected tighter th…
Data driven weak universal consistency
N. Santhanam, V. Anantharam, W. Szpankowski
Many current applications in data science need rich model classes to adequately represent the statistics that may be driving the observations. But rich model classes may be too com…
Universal compression of Gaussian sources with unknown parameters
A. Orlitsky, N. Santhanam
For a collection of distributions over a countable support set, the worst case universal compression formulation by Shtarkov attempts to assign a universal distribution over the su…
Redundancy of Exchangeable Estimators
Narayana P. Santhanam, Anand D. Sarwate, Jae Oh Woo
Exchangeable random partition processes are the basis for Bayesian approaches to statistical inference in large alphabet settings. On the other hand, the notion of the pattern of a…
On redundancy of memoryless sources over countable alphabets
Maryam Hosseini, Narayana Santhanam
The minimum average number of bits need to describe a random variable is its entropy, assuming knowledge of the underlying statistics On the other hand, universal compression suppo…
Stationary and Transition Probabilities in Slow Mixing, Long Memory Markov Processes
Meysam Asadi, Ramezan Paravi Torghabeh, Narayana P. Santhanam
We observe a length- sample generated by an unknown,stationary ergodic Markov process (\emph{model}) over a finite alphabet . Given any string of symbols f…
Agnostic insurability of model classes
Narayana Santhanam, Venkat Anantharam
Motivated by problems in insurance, our task is to predict finite upper bounds on a future draw from an unknown distribution over the set of natural numbers. We can only use pa…
Optimal Lempel-Ziv based lossy compression for memoryless data: how to make the right mistakes
Narayana Santhanam, Dharmendra Modha
Compression refers to encoding data using bits, so that the representation uses as few bits as possible. Compression could be lossless: i.e. encoded data can be recovered exactly f…
On Modeling Profiles instead of Values
Alon Orlitsky, Narayana Santhanam, Krishnamurthy Viswanathan +1
We consider the problem of estimating the distribution underlying an observed sample of data. Instead of maximum likelihood, which maximizes the probability of the ob served values…
Alternating Markov Chains for Distribution Estimation in the Presence of Errors
Farzad Farnoud, Narayana P. Santhanam, Olgica Milenkovic
We consider a class of small-sample distribution estimators over noisy channels. Our estimators are designed for repetition channels, and rely on properties of the runs of the obse…
Information-theoretic limits of selecting binary graphical models in high dimensions
Narayana Santhanam, Martin J. Wainwright
The problem of graphical model selection is to correctly estimate the graph structure of a Markov random field given samples from the underlying distribution. We analyze the inform…