Lawson Building 2142-J, West Lafayette, IN 47907

e-mail: jhonorio at purdue.edu

Modern statistical problems are high dimensional (big data). My research in this area focus on developing computationally and statistically efficient algorithms, understanding their behavior using concepts such as convergence, sample complexity, and privacy, and designing new modeling paradigms such as models rooted in game theory. My theoretical and algorithmic work is directly motivated by, and contributes to, applications in political science (affiliation and influence), neuroscience (brain disorders such as addiction), and genetics (diseases such as cancer). [vita]

Prior to joining Purdue, I was a postdoctoral associate at MIT CSAIL, working with Tommi Jaakkola. My Erdös number is 3: Jean Honorio → Tommi Jaakkola → Noga Alon → Paul Erdös.

Here is a note for prospective students that are considering working with me.

CS 59000-HLT: Hands-On Learning Theory: Fall 2017, also offered on Fall 2016 and Fall 2015

CS 69000-SML: Statistical Machine Learning II: Spring 2017

CS 52000: Computational Methods In Optimization: Spring 2016

Ghoshal A.,

(Under submission.)

Learning Sparse Potential Games in Polynomial Time and Sample Complexity. (Preprint)

Ghoshal A.,

(Under submission.)

Learning Bayes Networks Using Interventional Path Queries in Polynomial Time and Sample Complexity. (Preprint)

Bello K.,

(Under submission.)

Compositional Nonparametric Prediction: Statistical Efficiency and Greedy Regression Algorithm. (Preprint)

Xu Y.,

(Under submission.)

Statistically and Computationally Efficient Variance Estimator for Kernel Ridge Regression. (Preprint)

Liu M.,

(Under submission.)

Reconstructing a Bounded-Degree Directed Tree Using Path Queries. (Preprint)

Wang Z.,

(Under submission.)

On the Statistical Efficiency of L

(Under submission.) [code]

Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity.

Ghoshal A.,

Neural Information Processing Systems. California.

On the Sample Complexity of Learning Graphical Games.

Information Theoretic Limits for Linear Prediction with Graph-Structured Sparsity.

Barik A.,

Learning Graphical Games from Behavioral Data: Sufficient and Necessary Conditions.

Ghoshal A.,

Information-Theoretic Limits of Bayesian Network Structure Learning.

Ghoshal A.,

Ghoshal A.,

Structured Prediction: From Gaussian Perturbations to Linear-Time Principled Algorithms.

Information-Theoretic Lower Bounds for Recovery of Diffusion Network Structures.

Park K.,

Variable Selection in Gaussian Markov Random Fields.

Invited book chapter in

Edited by Aravkin A., Deng L., Heigold G., Jebara T., Kanevski D., Wright S. (to be published on December, 2016)

Predictive Sparse Modeling of fMRI Data for Improved Classification, Regression, and Visualization Using the k-Support Norm.

Belilovsky E., Gkirtzou K., Misyrlis M., Konova A.,

Integration of PCA with a Novel Machine Learning Method for Reparameterization and Assisted History Matching Geologically Complex Reservoirs.

Tight Bounds for the Expected Risk of Linear Classifiers and PAC-Bayes Finite-Sample Guarantees.

Classification on Brain Functional Magnetic Resonance Imaging: Dimensionality, Sample Size, Subject Variability and Noise.

Invited book chapter in

Edited by Chen C.,

Improving Interpretability of Graphical Models in fMRI Analysis via Variable-Selection.

Predicting Cross-task Behavioral Variables from fMRI Data Using the k-Support Norm.

Misyrlis M., Konova A., Blaschko M.,

Medical Image Computing and Computer-Assisted Intervention.

Methylphenidate Enhances Executive Function and Optimizes Prefrontal Function in Both Health and Cocaine Addiction.

Moeller S.,

Integration of Principal Component Analysis and Streamline Information for the History Matching of Channelized Reservoirs.

Chen C., Gao G.,

Two-Sided Exponential Concentration Bounds for Bayes Error Rate and Shannon Entropy.

fMRI Analysis of Cocaine Addiction Using k-Support Sparsity.

Gkirtzou K.,

fMRI Analysis with Sparse Weisfeiler-Lehman Graph Statistics.

Gkirtzou K.,

Medical Image Computing and Computer-Assisted Intervention,

Variable Selection for Gaussian Graphical Models.

Can a Single Brain Region Predict a Disorder?

Two-person Interaction Detection Using Body-Pose Features and Multiple Instance Learning.

Yun K.,

IEEE Computer Vision and Pattern Recognition,

Dopaminergic Involvement During Mental Fatigue in Health and Cocaine Addiction.

Moeller S., Tomasi D.,

Enhanced Midbrain Response at 6-month Follow-up in Cocaine Addiction, Association with Reduced Drug-related Choice.

Moeller S., Tomasi D., Woicik P., Maloney T., Alia-Klein N.,

Digital Analysis and Visualization of Swimming Motion.

Kirmizibayrak C.,

Digital Analysis and Visualization of Swimming Motion.

Kirmizibayrak C.,

Conference on Computer Animation and Social Agents,

Dopaminergic contribution to endogenous motivation during cognitive control breakdown.

Moeller S., Tomasi D.,

Simple Fully Automated Group Classification on Brain fMRI.

Disrupted Functional Connectivity with Dopaminergic Midbrain in Cocaine Abusers.

Tomasi D., Volkow N., Wang R.,

Oral Methylphenidate Normalizes Cingulate Activity in Cocaine Addiction During a Salient Cognitive Task.

Goldstein R., Woicik P., Maloney T., Tomasi D., Alia-Klein N., Shan J.,

Learning Brain fMRI Structure Through Sparseness and Local Constancy.

Neural Information Processing Systems,

A Functional Geometry of fMRI BOLD Signal Interactions.

Langs G., Samaras D., Paragios N.,

Neural Information Processing Systems,

Dopaminergic Response to Drug Words in Cocaine Addiction.

Goldstein R., Tomasi D., Alia-Klein N.,

Anterior Cingulate Cortex Hypoactivations to an Emotionally Salient Task in Cocaine Addiction.

Goldstein R., Alia-Klein N., Tomasi D.,

Langs G., Samaras D., Paragios N.,