Publications

## Books

### 2019

Beyond Backprop: Online Alternating Minimization with Auxiliary Variables

Anna Choromanska*, Benjamin Cowen*, Sadhana Kumaravel*, Ronny Luss*, Mattia Rigotti*, Irina Rish*, Brian Kingsbury, Paolo DiAchille, Viatcheslav Gurev, Ravi Tejwani, Djallel Bouneffouf

International Conference on Machine Learning (ICML 2019) Code is available here.

Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference

Matthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, Gerald Tesauro

International Conference on Learning Representations (ICLR-2019)

Kernelized Hashcode Representations for Biomedical Relation Extraction

Garg, Sahil, Aram Galstyan, Greg Ver Steeg, Irina Rish, Guillermo Cecchi, and Shuyang Gao

Thirty-third AAAI conference on Artificial Intelligence (AAAI-2019), 2019

Predicting conversion to psychosis in clinical high risk patients using resting-state functional MRI features

J. McDonnell, W. Hord, J. Reinen, P. Polosecki, I. Rish and G. Cecchi

SPIE Medical Imaging 2019: Biomedical Applications in Molecular, Structural, and Functional Imaging, pp. 109532A

### 2018

Dialogue Modeling Via Hash Functions

S. Garg, A. Galstyan, I. Rish, G.A. Cecchi, S. Gao

Linguistic and Cognitive Approaches to Dialog Agents (LaCATODA) 2018 IJCAI/ICML Workshop

Baseline multimodal information predicts future motor impairment in premanifest Huntington's disease

E. Castro, P. Polosecki, I. Rish, D. Pustina, JH Warner, A. Wood, C. Sampaio, GA Cecchi

NeuroImage - Clinical, 2018

Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM

German Abrevaya, Aleksandr Aravkin, Guillermo Cecchi, Irina Rish, Pablo Polosecki, Peng Zheng, Silvina Dawson

arXiv:1805.09874 [stat.ML], 2018

Contextual Bandit with Adaptive Feature Extraction

Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf, Irina Rish

Proc of IEEE ICDM-2020 Workshop on Data Science and Big Data Analytics, 2018

Variable Selection in Gaussian Markov Random Fields

Jean Honorio, Dimitris Samaras, Irina Rish, Guillermo A. Cecchi

Book chapter in Log-Linear Models, Extensions and Applications, MIT Press, 2018

### 2017

Learning Neural Markers of Schizophrenia Disorder Using Recurrent Neural Networks

Jumana Dakka, Pouya Bashivan, Mina Gheiratmand, Irina Rish, Shantenu Jha, Russell Greiner

NIPS 2017 workshop on Machine Learning for Health (ML4H), arXiv preprint arXiv:1712.00512

Bandit Models of Human Behavior: Reward Processing in Mental Disorders

Djallel Bouneffouf, Irina Rish, Guillermo A. Cecchi

Artificial General Intelligence (AGI-2017)

P. Polosecki, E. Castro, A. Wood, J. H. Warner, I. Rish and G. A. Cecchi

IBM Journal of Research and Development 61(2/3), IEEE , 2017

Attentive Bandit: Contextual Bandit with Restricted Context

Djallel Bouneffouf, Irina Rish, Raphael Feraud and Guillermo Cecchi

International Joint Conference on Artificial Intelligence (IJCAI-2017)

Learning stable and predictive network-based patterns of schizophrenia and its clinical symptoms

Mina Gheiratmand, Irina Rish, Guillermo A Cecchi, Matthew RG Brown, Russell Greiner, Pablo I Polosecki, Pouya Bashivan, Andrew J Greenshaw, Rajamannar Ramasubbu, Serdar M Dursun

npj Schizophrenia 3(1), 22, Nature Publishing Group, 2017

Neurogenesis-Inspired Dictionary Learning: Online Model Adaption in a Changing World

Sahil Garg, Irina Rish, Guillermo A. Cecchi, Aurelie Lozano

International Joint Conference on Artificial Intelligence (IJCAI-2017). Extended verion arXiv:1701.06106

Computing the structure of language for neuropsychiatric evaluation

G. A. Cecchi, V. Gurev, S.J. Heisig, R. Norel, I. Rish, S. R. Schrecke

IBM Journal of Research and Development 61(2/3), IEEE, 2017

Holographic brain: Distributed versus local activation patterns in fMRI

I. Rish and G.A. Cecchi

IBM Journal of Research and Development 61(2/3), IEEE, 2017

Learning Discriminative Functional Network Features of Schizophrenia

Mina Gheiratmand, Irina Rish, Guillermo Cecchi, Matthew Brown, Russell Greiner, Pouya Bashivan, Pablo Polosecki, Serdar Dursun

SPIE Medical Imaging, 2017

Functional Network Disruptions in Schizophrenia

Irina Rish and Guillermo A. Cecchi

Book chapter, Biological Networks and Pathway Analysis, edited by Y. Nikolsky and T. Tatarinova , Springer, 2017

### 2016

Irina Rish, Pouya Bashivan, Guillermo A. Cecchi, Rita Z. Goldstein

SPIE Medical Imaging, 2016

Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks

Pouya Bashivan, Irina Rish, Mohammed Yeasin, Noel Codella

ICLR 2016 : International Conference on Learning Representations 2016

### 2015

Variable-Selection Emerges on Top in Empirical Comparison of Whole-Genome Complex-Trait Prediction Methods

D. C. Haws, I. Rish, S. Teyssedre, D. He, A. C. Lozano, P. Kambadur, Z. Karaman, L. Parida

PLoS ONE 10(10), e0138903, 2015

Mental State Recognition via Wearable EEG

Pouya Bashivan, Irina Rish, Steve Heisig

NIPS Workshop on Machine Learning and Interpretation in Neuroimaging (MLINI2015)

MINT: Mutual Information based Transductive Feature Selection for Genetic Trait Prediction

He, D., Rish, I. Haws, D. and Parida, L.

IEEE/ACM Transactions on Computational Biology and Bioinformatics pp. 99, 2015

Turing a la Freud: Test for an Automated Psychiatrist

G.A. Cecchi and I. Rish

Beyond the Turing Test - AAAI 2015 Workshop

### 2014

Sparse Modeling: Theory, Algorithms and Applications

Irina Rish and Genady Grabarnik

Chapman & Hall/CRC Machine Learning & Pattern Recognition, 2014

Practical Applications of Sparse Modeling

Irina Rish, Guillermo A. Cecchi, Aurelie Lozano and Alexandru Niculescu-Mizil

MIT Press, 2014

Augmented Human: Human OS for Improved Mental Function

Steve Heisig, Guillermo Cecchi, Ravi Rao and Irina Rish

AAAI 2014 Workshop on Cognitive Computing and Augmented Human Intelligence

Abstract

D.He, I. Rish, L. Parida

In Proc of SIAM Data Mining (SDM), 2014

Abstract

Reliability Estimation and Enhancement via Spatial Smoothing in Sparse fMRI Modeling

Carroll, Melissa K., Guillermo A. Cecchi, Irina Rish, Rahul Garg, Marwan Baliki, and A. Vania Apkarian

Practical Applications of Sparse Modeling, pp. 123-150, MIT Press, 2014

Abstract

### 2013

MINT: Mutual Information based Transductive Feature Selection for Genetic Trait Prediction

D. He, I. Rish, D. Haws, S.Teyssedre, Z. Karaman, L. Parida

The Seventh International Workshop on Machine Learning in Systems Biology (MLSB 2013),

Abstract

Functional MRI Analysis with Sparse Models

I. Rish

Invited paper at NECTAR track of the European Conference on Machine Learning (ECML-2013)

Abstract

Sparse Signal Recovery with Exponential-Family Noise

Irina Rish and Genady Grabarnik

Book chapter, Compressed Sensing & Sparse Filtering, Springer, 2013

Abstract

Schizophrenia as a network disease: disruption of emergent brain function in patients with auditory hallucinations

I. Rish, G. Cecchi, B. Thyreau, B. Thirion, M. Plaze, M. L. Paillere-Martinot, C. Martelli, J. L. Martinot, J. B. Poline

PLoS ONE 8(1), e50625, 2013

### 2012

Edited by Georg Langs, Irina Rish, Moritz Grosse-Wentrup, Brian Murphy

Springer, 2012

Sparse regression analysis of task-relevant information distribution in the brain

Irina Rish, Guillermo A Cecchi, Kyle Heuton, Marwan N Baliki, A Vania Apkarian

SPIE Medical Imaging, 2012

Abstract

Predictive dynamics of human pain perception

G. A. Cecchi, L. Huang, J. A. Hashmi, M. Baliki, M. V. Centeno, I. Rish, A. V. Apkarian

PLoS Comput. Biol. 8(10), e1002719, 2012

Schizophrenia classification using functional network features

Irina Rish, Guillermo A Cecchi, Kyle Heuton

SPIE Medical Imaging, pp. 83170W--83170W, 2012

Abstract

Variable Selection for Gaussian Graphical Models

Jean Honorio, Dimitris Samaras, Irina Rish, Guillermo Cecchi

AISTATS, 2012

Abstract

### 2011

Adult neurogenesis as efficient sparsification

I. Rish, G. Cecchi, A. Lozano, R. Rao

Neuroscience 2011 (SfN meeting), November 12-16

Abstract

### 2010

Sparse Markov Net Learning with Priors on Regularization Parameters

Katya Scheinberg, Irina Rish, Narges Bani Asadi

in Proceedings of The Eleventh International Symposium on Artificial Intelligence and Mathematics (ISAIM 2010), pp. 112--122

Abstract

Sparse regression models of pain perception

Irina Rish, Guillermo A Cecchi, Marwan N Baliki, A Vania Apkarian

Brain Informatics, pp. 212--223, Springer, 2010

Abstract

Learning sparse Gaussian Markov networks using a greedy coordinate ascent approach

Katya Scheinberg, Irina Rish

European Conference on Machine Learning and Knowledge Discovery in Databases (ECML-PKDD), pp. 196--212, Springer, 2010

Abstract

### 2009

Isometry-enforcing data transformations for improving sparse model learning

Avishy Carmi, Irina Rish, Guillermo Cecchi, Dimitri Kanevsky, Bhuvana Ramabhadran

IBM Tech Report RC24801, Tech. Rep. RC 24801, Human Language Technologies, IBM, 2009

Discriminative network models of schizophrenia

Guillermo Cecchi, Irina Rish, Benjamin Thyreau, Bertrand Thirion, Marion Plaze, Marie-Laure Paillere-Martinot, Catherine Martelli, Jean-Luc Martinot, Jean-Baptiste Poline

Advances in Neural Information Processing Systems (NIPS 2009) , pp. 252--260, Citeseer

Prediction and interpretation of distributed neural activity with sparse models

Melissa K Carroll, Guillermo A Cecchi, Irina Rish, Rahul Garg, A Ravishankar Rao

NeuroImage 44(1), 112--122, Elsevier, 2009

SINCO-a greedy coordinate ascent method for sparse inverse covariance selection problem

Katya Scheinberg, Irina Rish

preprint, 2009

Map approach to learning sparse Gaussian Markov networks

N Bani Asadi, I Rish, K Scheinberg, D Kanevsky, B Ramabhadran

Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on, pp. 1721--1724

Sparse signal recovery with exponential-family noise

Irina Rish, Genady Grabarnik

Communication, Control, and Computing, 2009. Allerton 2009. 47th Annual Allerton Conference on, pp. 60--66

### 2008

A New Family of Extended Baum-Welch Update Rules

Dimitri Kanevsky, Daniel Povey, Bhuvana Ramabhadran, Irina Rish, Tara Sainath

2008

Closed-form supervised dimensionality reduction with generalized linear models

Irina Rish, Genady Grabarnik, Guillermo Cecchi, Francisco Pereira, Geoffrey J Gordon

Proceedings of the 25th international conference on Machine learning, pp. 832--839, 2008

### 2007

Evaluation of optimization methods for network bottleneck diagnosis

Alina Beygelzimer, Jeff Kephart, Irina Rish

Autonomic Computing, 2007. ICAC'07. Fourth International Conference on, pp. 20--20, IEEE

Blind source separation approach to performance diagnosis and dependency discovery

Gaurav Chandalia, Irina Rish

Proceedings of the 7th ACM SIGCOMM conference on Internet measurement, pp. 259--264, 2007

Empirical study of topology effects on diagnosis in computer networks

Natalia Odintsova, Irina Rish

Mobile Adhoc and Sensor Systems, 2007. MASS 2007. IEEE Internatonal Conference on, pp. 1--6

Estimating end-to-end performance by collaborative prediction with active sampling

Irina Rish, Gerald Tesauro

Integrated Network Management, 2007. IM'07. 10th IFIP/IEEE International Symposium on, pp. 294--303

### 2006

Automated Knowledge Elicitation and Flowchart Optimization for Problem Diagnosis

Alina Beygelzimer, Mark Brodie, Jonathan Lenchner, Irina Rish

UAI-06 Workshop on Applications of Bayesian Networks, 2006

Information-theoretic approaches to cost-efficient diagnosis

Irina Rish

Proc. Information Theory and Applications Inaugural Work., San Diego, CA, 2006

Bayesian learning of Markov network structure

Aleks Jakulin, Irina Rish

ECML 2006, pp. 198--209, Springer

Active Sampling Approaches in Systems Management Applications

Irina Rish

SysML Workshop at SIGMETRICS-06 , Citeseer, 2006

### 2005

Improving network robustness by edge modification

Alina Beygelzimer, Geoffrey Grinstein, Ralph Linsker, Irina Rish

Physica A: Statistical Mechanics and its Applications 357(3), 593--612, Elsevier, 2005

Efficient test selection in active diagnosis via entropy approximation

Alice X Zheng, Irina Rish, Alina Beygelzimer

UAI-2005

Multi-fault diagnosis in dynamic systems

Natalia Odintsova, Irina Rish, Sheng Ma

Proceedings of the 9th IFIP/IEEE International Symposium on Integrated Network Management (IM 2005, Poster-CD)

Test-based diagnosis: Tree and matrix representations

Alina Beygelzimer, Mark Brodie, Sheng Ma, Irina Rish

Integrated Network Management, 2005. IM 2005. 2005 9th IFIP/IEEE International Symposium on, pp. 529--542

Self-healing in large-scale systems: parallel and distributed diagnostic architectures

Loewenstern Odintsova D N S. Guo I. Rish

Technical Report, 2005

Multifault Diagnosis in Dynamic Systems

N Odintsova, I Rish, S Ma

Integrated management (IM-2005), Nice, France

Adaptive diagnosis in distributed systems

I. Rish, M. Brodie, S. Ma, N. Odintsova, A. Beygelzimer, G. Grabarnik, K. Hernandez

IEEE Trans Neural Netw 16(5), 1088--1109, 2005

Distributed systems diagnosis using belief propagation

Irina Rish

Proc. Allerton Conf. Communication, Control and Computing, Monticello, IL, Citeseer, 2005

Self-healing in large-scale systems: parallel and distributed diagnostic architectures

D Loewenstern N Odintsova S Guo, Irina Rish, David Loewenstern

Technical Report, Technical report, IBM TJ Watson Research Center, 2005

### 2004

Kikuchi-Bayes: Factorized models for approximate classification in closed form

Aleks Jakulin, Irina Rish, Ivan Bratko

Technical Report, Technical Report RC23314, IBM, 2004

Statistical models for unequally spaced time series

Emre Erdogan, Sheng Ma, Alina Beygelzimer, Irina Rish

Proceedings of the Fifth SIAM International Conference on Data Mining, SIAM, 2004

A Beygelmizer, Geoffrey Grinstein, Ralph Linsker, Irina Rish

Proceedings of International Conference on Autonomic Computing, pp. 322--323, 2004

Multifault Diagnosis in Dynamic Systems

N Odintsova, I Rish, S Ma

Technical Report RC23385, 2004

Real-time problem determination in distributed systems using active probing

Irina Rish, Mark Brodie, Natalia Odintsova, Sheng Ma, Genady Grabarnik

Network Operations and Management Symposium, 2004. NOMS 2004. IEEE/IFIP, pp. 133--146

### 2003

Critical event prediction for proactive management in large-scale computer clusters

Ramendra K Sahoo, Adam J Oliner, Irina Rish, Manish Gupta, Jos\'e E Moreira, Sheng Ma, Ricardo Vilalta, Anand Sivasubramaniam

Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 426--435, ACM, 2003

Autonomic computing features for large-scale server management and control

RK Sahoo, I Rish, AJ Oliner, M Gupta, JE Moreira, S Ma, R Vilalta, A Sivasubramaniam

AIAC Workshop, IJCAI 2003

Problem Diagnosis in Distributed Systems using Active Probing

Irina Rish, Mark Brodie, Natalia Odintsova, Sheng Ma, Genady Grabarnik

UAI-2003 workshop on Bayesian Modeling Applications

A decomposition of classes via clustering to explain and improve naive Bayes (Best Paper Award)

Ricardo Vilalta, Irina Rish

Machine Learning: ECML 2003, pp. 444--455, Springer

Mini-buckets: A general scheme for bounded inference

Rina Dechter, Irina Rish

Journal of the ACM (JACM) 50(2), 107--153, ACM, 2003

Active probing strategies for problem diagnosis in distributed systems

Mark Brodie, Irina Rish, Sheng Ma, Natalia Odintsova, Alina Beygelzimer

Proceedings of the The Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-03), Acapulco, Mexico, pp. 1337--1338, LAWRENCE ERLBAUM ASSOCIATES LTD, 2003

Approximability of probability distributions

Alina Beygelzimer, Irina Rish

Advances in Neural Information Processing Systems 16 (NIPS-2003), MIT Press

### 2002

Using sensitivity analysis for selective parameter update in Bayesian network learning

Haiqin Wang, Irina Rish, Sheng Ma

Information Refinement and Revision for Decision Making: Modeling for Diagnostics, Prognostics and Prediction, AAAI 2002 Spring Symposium, Technical Report SS-02-03, pp. 29--36

Approximability and the Effective Width of Probability Distributions

Alina Beygelzimer, Irina Rish

IBM Technical Report RC22558, 2002

Efficient fault diagnosis using probing

Irina Rish, Mark Brodie, Sheng Ma

Proceedings of 2002 AAAI Spring Symposium on Information Refinement and Revision for Decision Making: Modeling for Diagnostics, Prognostics, and Prediction, Stanford, Palo Alto

Intelligent probing: a Cost-Efficient Approach to Fault Diagnosis in Computer Networks

I. Rish, M. Brodie, S. Ma

IBM Systems Journal, 41(3), pp 372-385 41(3), 372--385, 2002

On the importance of using treewidth as a model-selection criterion for learning Bayesian networks

A. Beygelzimer, I. Rish

Proceedings of the 7th Valencia International Meeting on Bayesian Statistics, 2002

Inference complexity as a model-selection criterion for learning bayesian networks

Alina Beygelzimer, Irina Rish

Proceedings of the Eighth International Conference on Principles of Knowledge Representation and Reasoning (KR2002), Toulouse, France, pp. 558--567, Morgan Kaufmann Publishers; 1998

Strategies for problem determination using probing

Mark Brodie, Irina Rish, Sheng Ma, Alina Beygelzimer, Natalia Odintsova

IBM Technical Report, 2002

Accuracy vs. efficiency trade-offs in probabilistic diagnosis

Irina Rish, Mark Brodie, Sheng Ma

Proceedings of AAAI-2002, Edmonton, Alberta, Canada, pp. 560--566, Menlo Park, CA; Cambridge, MA; London; AAAI Press; MIT Press; 1999

Using adaptive probing for real-time problem diagnosis in distributed computer systems

I Rish, M Brodie, S Ma, G Grabarnik, N Odintsova

Proceedings AAAI-02/KDD-02/UAI-02 workshop on Real-Time Decision Support and Diagnosis Systems, Edmonton, Alberta, Canada, 2002

### 2001

An analysis of data characteristics that affect naive Bayes performance

Irina Rish, Joseph Hellerstein, Thathachar Jayram

IBM Technical Report RC21993, 2001

An empirical study of the naive Bayes classifier

Irina Rish

Proceedings of IJCAI-2001 workshop on Empirical Methods in AI (also, IBM Technical Report RC22230), pp. 41--46

Optimizing probe selection for fault localization

Mark Brodie, Irina Rish, Sheng Ma

Proceedings of Distributed Systems Operation and Management (DSOM-2001)

A unified framework for evaluation metrics in classification using decision trees

Ricardo Vilalta, Mark Brodie, Daniel Oblinger, Irina Rish

Machine Learning: ECML 2001, pp. 503--514, Springer

Efficient fault diagnosis using local inference

I. Rish, M. Brodie, H. Wang, S. Ma

IBM Technical Report RC22229, 2001

### 2000

Advances in Bayesian Learning.

I. Rish

Proceedings of the 2000 International Conference on Artificial Intelligence (IC-AI'2000), Las Vegas, Nevada

Resolution vs. search; Two strategies for SAT

I. Rish, R. Dechter

Journal of Automated Reasoning, 24(1/2), pp.225-275, 2000

Recognizing end-user transactions in performance management

Joseph L Hellerstein, TS Jayram, Irina Rish, others

Proceedings of AAAI-2000, Austin, Texas, pp. 596--602, IBM TJ Watson Research Center

### 1999

Efficient reasoning in graphical models

Irina Rish

Ph.D. thesis, Information and Computer Science, University of California, Irvine, 1999

### 1998

On the impact of causal independence

Irina Rish, Rina Dechter

In Proceedings of 1998 AAAI Spring Symposium on Interactive and Mixed-Initiative Decision-Theoretic Systems, Technical report, Dept. Information and Computer Science, UCI

Empirical evaluation of approximation algorithms for probabilistic decoding

Irina Rish, Kalev Kask, Rina Dechter

Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence, pp. 455--463, 1998

### 1997

Summarizing CSP hardness with continuous probability distributions

Daniel Frost, Irina Rish, Lluis Vila

Proceedings of the Fourteenth National Conference on Artificial Intelligence (AAAI-97), pp. 327--333, Citeseer, 1997

Statistical analysis of backtracking on inconsistent CSPs

Irina Rish, Daniel Frost

Principles and Practice of Constraint Programming-CP97, pp. 150--162, Springer, 1997

A scheme for approximating probabilistic inference

Rind Dechter, Irina Rish

Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence, pp. 132--141, 1997

### 1996

Value iteration and policy iteration algorithms for Markov decision problem

Elena Pashenkova, Irina Rish, Rina Dechter

AAAI’96: Workshop on Structural Issues in Planning and Temporal Reasoning, Citeseer, 1996

Variable Independence in Markov Decision Problems

Irina Rish, Rina Dechter

Proceedings of AAAI-96 Workshop on Structural Issues in Planning and Temporal Reasoning, Portland, Oregon, 1996

To Guess or to Think? Hybrid Algorithms for SAT (Extended Abstract; full version TR attached)

I. Rish, R. Dechter

Proceedings of the International Conference on Principles and Practice of Constraint Programming (CP96), Cambridge, Massachusetts, 1996

### 1994

Empirical evaluation of two versions of the Davis-Putnam algorithm

Rina Dechter, Irina Rish

Proceedings of the AAAI-94 Workshop on Experimental Evaluation of Reasoning and Search Methods, Seattle, Washington, Citeseer, 1994

Directional Resolution: The Davis-Putnam Procedure, Revisited.

R. Dechter, I. Rish

Proceedings of the International Conference on Principles of Knowledge Representation and Reasoning (KR-94), pp. 134-145, 1994