42 citations · 197 across the 45 of their papers we have counts for
28 papers · 1 filter
Identifiability from Stationary Covariance in Linear SDEs with Reciprocal Interactions and Latent Variables
Ana Leticia Garcez Vicente, Saber Salehkaleybar
Continuous-time stochastic differential equations (SDEs) provide a natural framework for modeling interacting dynamical systems. A central causal question is whether causal effects…
Differentiable Structure Learning for Cyclic Linear Gaussian Models with Latent Confounders
Sadegh Khorasani, Ali Najar, Saber Salehkaleybar +1
We study causal structure learning from observational data in linear Gaussian structural causal models in the presence of directed cycles and an unknown number of exogenous latent…
One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady State
Saber Salehkaleybar
We study the problem of recovering the parameters of a multivariate Ornstein-Uhlenbeck (OU) process from steady-state observational and interventional data. In many applications, s…
The Role of Causality in Algorithmic Recourse
Srikanth Avasarala, Varun Gupta, Shahin Jabbari +2
Algorithmic recourse aims to provide individuals with actionable changes to improve their predicted outcomes in high-stakes classification settings, such as loan and mortgage appli…
Data-Driven and Cycle-Agnostic Covariate Selection for Nonparametric Causal Effect Estimation
Ana Leticia Garcez Vicente, Gijs van Seeventer, Saber Salehkaleybar
Estimating causal effects from observational data requires identifying valid adjustment sets. This task is especially challenging in realistic settings where latent confounding and…
Learning Subgroups with Maximum Treatment Effects without Causal Heuristics
Lincen Yang, Zhong Li, Matthijs van Leeuwen +1
Discovering subgroups with the maximum average treatment effect is crucial for targeted decision making in domains such as precision medicine, public policy, and education. While m…
Fusing Rewards and Preferences in Reinforcement Learning
Sadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash +1
We present Dual-Feedback Actor (DFA), a reinforcement learning algorithm that fuses both individual rewards and pairwise preferences (if available) into a single update rule. DFA u…
Hierarchical Reinforcement Learning with Targeted Causal Interventions
Sadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash +1
Hierarchical reinforcement learning (HRL) improves the efficiency of long-horizon reinforcement-learning tasks with sparse rewards by decomposing the task into a hierarchy of subgo…
Multi-Domain Causal Discovery in Bijective Causal Models
Kasra Jalaldoust, Saber Salehkaleybar, Negar Kiyavash
We consider the problem of causal discovery (a.k.a., causal structure learning) in a multi-domain setting. We assume that the causal functions are invariant across the domains, whi…
ACTIVA: Amortized Causal Effect Estimation via Variational Autoencoders
Andreas Sauter, Saber Salehkaleybar, Frank van Harmelen +2
Predicting post-intervention distributions from observational data is central to many scientific and decision-making problems, but remains challenging due to causal ambiguity, rest…
Soft Preference Optimization: Aligning Language Models to Expert Distributions
Arsalan Sharifnassab, Saber Salehkaleybar, Sina Ghiassian +2
We propose Soft Preference Optimization (SPO), a method for aligning generative models, such as Large Language Models (LLMs), with human preferences, without the need for a reward…
MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
Arsalan Sharifnassab, Saber Salehkaleybar, Richard Sutton
We address the challenge of optimizing meta-parameters (hyperparameters) in machine learning, a key factor for efficient training and high model performance. Rather than relying on…
Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data
Yuqin Yang, Saber Salehkaleybar, Negar Kiyavash
We study the problem of identifying the unknown intervention targets in structural causal models where we have access to heterogeneous data collected from multiple environments. Th…
Efficiently Escaping Saddle Points for Policy Optimization
Sadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash +2
Policy gradient (PG) is widely used in reinforcement learning due to its scalability and good performance. In recent years, several variance-reduced PG methods have been proposed w…
Fast Causal Orientation Learning in Directed Acyclic Graphs
Ramin Safaeian, Saber Salehkaleybar, Mahmoud Tabandeh
Causal relationships among a set of variables are commonly represented by a directed acyclic graph. The orientations of some edges in the causal DAG can be discovered from observat…
Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function
Saeed Masiha, Saber Salehkaleybar, Niao He +2
We study the performance of Stochastic Cubic Regularized Newton (SCRN) on a class of functions satisfying gradient dominance property with which holds in a wide range o…
A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models
Ehsan Mokhtarian, Saber Salehkaleybar, AmirEmad Ghassami +1
We study experiment design for unique identification of the causal graph of a simple SCM, where the graph may contain cycles. The presence of cycles in the structure introduces maj…
Momentum-Based Policy Gradient with Second-Order Information
Saber Salehkaleybar, Sadegh Khorasani, Negar Kiyavash +2
Variance-reduced gradient estimators for policy gradient methods have been one of the main focus of research in the reinforcement learning in recent years as they allow acceleratio…
Order Optimal Bounds for One-Shot Federated Learning over non-Convex Loss Functions
Arsalan Sharifnassab, Saber Salehkaleybar, S. Jamaloddin Golestani
We consider the problem of federated learning in a one-shot setting in which there are machines, each observing sample functions from an unknown distribution on non-convex…
Order Optimal One-Shot Distributed Learning
Arsalan Sharifnassab, Saber Salehkaleybar, S. Jamaloddin Golestani
We consider distributed statistical optimization in one-shot setting, where there are machines each observing i.i.d. samples. Based on its observed samples, each machine th…
Interventional Experiment Design for Causal Structure Learning
AmirEmad Ghassami, Saber Salehkaleybar, Negar Kiyavash
It is known that from purely observational data, a causal DAG is identifiable only up to its Markov equivalence class, and for many ground truth DAGs, the direction of a large port…
Adversarial Orthogonal Regression: Two non-Linear Regressions for Causal Inference
M. Reza Heydari, Saber Salehkaleybar, Kun Zhang
We propose two nonlinear regression methods, named Adversarial Orthogonal Regression (AdOR) for additive noise models and Adversarial Orthogonal Structural Equation Model (AdOSE) f…
Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables
Saber Salehkaleybar, AmirEmad Ghassami, Negar Kiyavash +1
We consider the problem of learning causal models from observational data generated by linear non-Gaussian acyclic causal models with latent variables. Without considering the effe…
One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Them
Saber Salehkaleybar, Arsalan Sharifnassab, S. Jamaloddin Golestani
We consider distributed statistical optimization in one-shot setting, where there are machines each observing i.i.d. samples. Based on its observed samples, each machine se…