Niki Kilbertus

Identifiability Challenges in Sparse Linear Ordinary Differential Equations

Causal Partial Identification with Data Augmentation

Hybrid Symbolic-Neural Models for Dynamical Systems

An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation

Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processes

Generative Intervention Models for Causal Perturbation Modeling

Learning Representations of Instruments for Partial Identification of Treatment Effects

Learning Representations of Instruments for Partial Identification of Treatment Effects

Projected Neural Differential Equations for Learning Constrained Dynamics