Publications

2024

A Cross-Moment Approach for Causal Effect Estimation

Y. Kivva; S. Salehkaleybar; N. Kiyavash 

2024. 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, Louisiana, USA, 2023-12-10 – 2023-12-16.

2023

Causal Effect Identification in Uncertain Causal Networks

S. Akbari; F. Jamshidi; E. Mokhtarian; M. J. Vowels; J. Etesami et al. 

2023. 37th Conference on Neural Information Processing Systems (NeurIPS 2023)., New Orlean, USA, 2023-12-10 – 2023-12-16.

A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models

E. Mokhtarian; S. Salehkaleybar; A. Ghassami; N. Kiyavash 

Journal Of Machine Learning Research. 2023. Vol. 24, num. 118, p. 354.

Causal imitability under context-specific independence relations

F. Jamshidi; S. Akbari; N. Kiyavash 

2023. 37th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023-12-10 – 2023-12-16.

On Identifiability of Conditional Causal Effects

Y. Kivva; J. Etesami; N. Kiyavash 

2023. Conference on Uncertainty in Artificial Intelligence, UAI 2013, Pittsburgh, PA, USA, 2023-07-31 – 2023-08-04. p. 1078 – 1086. DOI : https://doi.org/10.48550/arXiv.2306.11755.

Novel Ordering-based Approaches for Causal Structure Learning in the Presence of Unobserved Variables

 

2023. Thirty-Seventh AAAI Conference on Artificial Intelligence, Washington DC, USA,

2022

Momentum-Based Policy Gradient with Second-Order Information

S. Salehkaleybar; M. Khorasani; N. Kiyavash; N. He; P. Thiran 

2022

(Dis)assortative partitions on random regular graphs

F. Behrens; G. Arpino; Y. Kivva; L. Zdeborova 

Journal Of Physics A-Mathematical And Theoretical. 2022. Vol. 55, num. 39, p. 395004. DOI : 10.1088/1751-8121/ac8b46.

Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function

S. Masiha; S. Salehkaleybar; N. He; N. Kiyavash; P. Thiran 

2022. 

A Wasserstein-based measure of conditional dependence

J. Etesami; K. Zhang; N. Kiyavash 

Behaviormetrika. 2022. Vol. 49, num. 2, p. 343 – 362. DOI : 10.1007/s41237-022-00170-2.

Minimum Cost Intervention Design for Causal Effect Identification

S. Akbari; J. Etesami; N. Kiyavash 

2022. International Conference on Machine Learning 2022, Baltimore, USA, DOI : 10.48550/arxiv.2205.02232.

Causal Discovery in Probabilistic Networks with an Identifiable Causal Effect

S. Akbari; F. Jamshidi; E. Mokhtarian; M. J. Vowels; J. Etesami et al. 

ArXiv. 2022. DOI : 10.48550/arXiv.2208.04627.

Revisiting the General Identifiability Problem

Y. Kivva; E. Mokhtarian; J. Etesami; N. Kiyavash 

2022. Uncertainty in Artificial Intelligence, Eindhoven, Netherlands, August 2nd – August 4th, 2022. p. 1022 – 1030.

Causal Effect Identification with Context-specific Independence Relations of Control Variables

E. Mokhtarian; F. Jamshidi; J. Etesami; N. Kiyavash 

2022. International Conference on Artificial Intelligence and Statistics, ELECTR NETWORK, Mar 28-30, 2022.

2021

Editorial

A. Gandhi; N. Kiyavash; J. Wang 

Proceedings Of The Acm On Measurement And Analysis Of Computing Systems. 2021. Vol. 5, num. 2, p. 13. DOI : 10.1145/3466793.

Adversarial orthogonal regression: Two non-linear regressions for causal inference

M. R. Heydari; S. Salehkaleybar; K. Zhang 

Neural Networks. 2021. Vol. 143, p. 66 – 73. DOI : 10.1016/j.neunet.2021.05.018.

Optimal Adversarial Policies in the Multiplicative Learning System With a Malicious Expert

S. R. Etesami; N. Kiyavash; V. Leon; H. V. Poor 

Ieee Transactions On Information Forensics And Security. 2021. Vol. 16, p. 2276 – 2287. DOI : 10.1109/TIFS.2021.3052360.

Impact of Data Processing on Fairness in Supervised Learning

S. Khodadadian; A. Ghassami; N. Kiyavash 

2021. IEEE International Symposium on Information Theory (ISIT), ELECTR NETWORK, Jul 12-20, 2021. p. 2643 – 2648. DOI : 10.1109/ISIT45174.2021.9517766.

The KDD 2021 Workshop on Causal Discovery (CD2021)

Thuc Duy Le; J. Li; G. Cooper; S. Triantafyllou; E. Bareinboim et al. 

2021. 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), ELECTR NETWORK, Aug 14-18, 2021. p. 4141 – 4142. DOI : 10.1145/3447548.3469462.

2020

Graph Signal Processing: Foundations and Emerging Directions [From the Guest Editors]

A. G. Marques; N. Kiyavash; J. M. F. Moura; D. van de Ville; R. Willett 

Ieee Signal Processing Magazine. 2020. Vol. 37, num. 6, p. 11 – 13. DOI : 10.1109/MSP.2020.3020715.

Model-Augmented Conditional Mutual Information Estimation for Feature Selection

A. Yang; A. Ghassami; M. Raginsky; N. Kiyavash; E. Rosenbaum 

2020. 36th Conference on Uncertainty in Artificial Intelligence (UAI), Virtual Conference, August 3-6, 2020. p. 1139 – 1148.

LazyIter: A Fast Algorithm for Counting Markov Equivalent DAGs and Designing Experiments

A. AhmadiTeshnizi; S. Salehkaleybar; N. Kiyavash 

2020. 37th International Conference on Machine Learning (ICML 2020), Online, July 13-18, 2020. p. 125 – 133.

A Catalyst Framework for Minimax Optimization

J. Yang; S. Zhang; N. Kiyavash; N. He 

2020. 34th Conference on Neural Information Processing Systems (NeurIPS), ELECTR NETWORK, Dec 06-12, 2020.

Characterizing Distribution Equivalence and Structure Learning for Cyclic and Acyclic Directed Graphs

A. Ghassami; A. Yang; N. Kiyavash; K. Zhang 

2020. 37th International Conference on Machine Learning (ICML 2020), Online, July 13-17, 2021. p. 3494 – 3504.

Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems

J. Yang; N. Kiyavash; N. He 

2020. 34th Conference on Neural Information Processing Systems (NeurIPS 20, Vancouver, Canada, December 6-12, 2020.

Achievability of nearly-exact alignment for correlated Gaussian databases

O. E. Dai; N. Kiyavash; D. Cullina 

2020. 2020 IEEE International Symposium on Information Theory, Los Angeles, CA, USA, Virtual Conference, June 21-26, 2020. p. 1230 – 1235. DOI : 10.1109/ISIT44484.2020.9174507.

The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models

Y. Yang; N. Kiyavash; L. Song; N. He 

2020. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada, December 7-12, 2020.

Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables

S. Salehkaleybar; A. Ghassami; N. Kiyavash; K. Zhang 

Journal Of Machine Learning Research. 2020. Vol. 21.

2019

Learning Positive Functions with Pseudo Mirror Descent

Y. Yang; H. Wang; N. Kiyavash; N. He 

2019. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, December 8-14, 2019. p. 14144 – .

Learning Hawkes Processes Under Synchronization Noise

W. Trouleau; J. Etesami; M. Grossglauser; N. Kiyavash; P. Thiran 

2019. 36th International Conference on Machine Learning, Long Beach, California, USA, June 9-15, 2019. p. 6325 – .

Analysis of a Canonical Labeling Algorithm for the Alignment of Correlated Erdős-Rényi Graphs

O. E. Dai; D. Cullina; N. Kiyavash; M. Grossglauser 

2019. Joint International Conference on Measurement and Modeling of Computer Systems – SIGMETRICS ’19, Phoenix, AZ, USA, June, 2019. p. 36:1 – 36:25. DOI : 10.1145/3326151.

Database Alignment with Gaussian Features

O. E. Dai; D. Cullina; N. Kiyavash 

2019. AISTATS, Naha, Okinawa, Japan, April 16-18, 2019. p. 3225 – 3233.

Counting and Sampling from Markov Equivalent DAGs Using Clique Trees

A. E. Ghassami; S. Salehkaleybar; N. Kiyavash; K. Zhang 

2019. Thirty-Third AAAI Conference on Artificial Intelligence – AAAI 2019, Honolulu, Hawaii, USA, January 27 – February 1, 2019. p. 3664 – 3671. DOI : 10.1609/aaai.v33i01.33013664.