Dr. Saber Salehkaleybar ~ Explanatory Data Analysis

Explanatory Data Analysis group

Dr. Saber Salehkaleybar

Assistant professor

Saber Salehkaleybar is an assistant professor at the Leiden Institute of Advanced Computer Science (LIACS), Leiden University. Prior to this, he worked as a research scientist in the School of Computer and Communication Sciences (IC) and College of Management of Technology (CDM) at École Polytechnique Fédérale de Lausanne. His research interests include causal inference, stochastic optimization, and reinforcement learning. He is particularly interested in causal discovery, experiment design, and applications of causality in generative AI. Additionally, he is focused on developing efficient optimization algorithms for training large learning models.

Selected recent publications

2026
	van Seeventer, G & Salehkaleybar, S Sign Identifiability of Causal Effects in Stationary Stochastic Dynamical Systems. In: Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence (UAI 2026), pp 6091-6124, PMLR, 2026.
	Salehkaleybar, S One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady State. In: Proceedings of the International Conference on Machine Learning (ICML 2026), 2026.
	Masiha, S, Salehkaleybar, S, He, N, Kiyavash, N & Thiran, P Optimal Local Convergence Rates of Stochastic First-Order Methods under Local Alpha-PL. In: Proceedings of the 29th International Conference on Artificial Intelligence and Statistics (AISTATS 2026), pp 3007-3015, PMLR, 2026.
	Sharifnassab, A, Salehkaleybar, S & Schuurmans, D Soft Preference Optimization: Aligning Language Models to Expert Distributions. Transactions on Machine Learning Research (TMLR), 2026.
	Yang, L, Li, Z, van Leeuwen, M & Salehkaleybar, S Learning Subgroups with Maximum Treatment Effects Without Causal Heuristics. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2026), pp 27565-27573, 2026.
2025
	Sharifian, E, Salehkaleybar, S & Kiyavash, N Near-Optimal Experiment Design in Linear non-Gaussian Cyclic Models. In: Proceedings of the Conference on Neural Information Processing Systems (NeurIPS 2025), 2025.
	Khorasani, S, Salehkaleybar, S, Kiyavash, N, He, N & Grossglauser, M Efficiently Escaping Saddle Points for Non-Convex Policy Optimization. In: Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI 2025), 2025.
	Kivva, Y, Akbari, S, Salehkaleybar, S & Kiyavash, N Causal Effect Identification in Heterogeneous Environments from Higher-Order Moments. In: Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI 2025), 2025.
	Sharifnassab, A, Salehkaleybar, S & Sutton, R MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters. In: Proceedings of the International Conference on Machine Learning (ICML 2025), 2025.
	Tramontano, D, Kivva, Y, Salehkaleybar, S, Kiyavash, N & Drton, M Causal Effect Identification in LiNGAM from Higher-Order Cumulants. In: Proceedings of the International Conference on Machine Learning (ICML 2025), 2025.
	Khorasani, S, Salehkaleybar, S, Kiyavash, N & Grossglauser, M Hierarchical Reinforcement Learning with Targeted Causal Interventions. In: Proceedings of the International Conference on Machine Learning (ICML 2025), 2025.
	Jalaldoust, K, Salehkaleybar, S & Kiyavash, N Multi-Domain Causal Discovery in Bijective Causal Models. In: Proceedings of the Conference on Causal Learning and Reasoning (CLeaR 2025), 2025.
2024
	Tramontano, D, Kivva, Y, Salehkaleybar, S, Drton, M & Kiyavash, N Causal Effect Identification in LiNGAM Models with Latent Confounders. In: Proceedings of the International Conference on Machine Learning (ICML 2024), 2024.
	Yang, Y, Salehkaleybar, S & Kiyavash, N Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data. In: International Conference on Artificial Intelligence and Statistics, pp 3187-3195, PMLR, 2024.
	Salehkaleybar, S, Khorasani, S, Kiyavash, N, He, N & Thiran, P A unified experiment design approach forcyclic and acyclic causal models. Transactions on Machine Learning Research vol.1(1), pp 1-1, 2024.
	Salehkaleybar, S, Khorasani, M, Kiyavash, N, He, N & Thiran, P Momentum-Based Policy Gradient with Second-Order Information. Transactions on Machine Learning Research, 2024.