Výsledky vyhledávání - "Butler, Kurt"

Report

Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical Systems

Autor: Butler, Kurt, Waxman, Daniel, Djurić, Petar M.

Causal discovery with time series data remains a challenging yet increasingly important task across many scientific domains. Convergent cross mapping (CCM) and related methods have been proposed to study time series that are generated by dynamical sy

Externí odkaz: http://arxiv.org/abs/2410.23499

Zobrazit plný text záznamu

Report

On Counterfactual Interventions in Vector Autoregressive Models

Autor: Butler, Kurt, Iloska, Marija, Djuric, Petar M.

Counterfactual reasoning allows us to explore hypothetical scenarios in order to explain the impacts of our decisions. However, addressing such inquires is impossible without establishing the appropriate mathematical framework. In this work, we intro

Externí odkaz: http://arxiv.org/abs/2406.19573

Zobrazit plný text záznamu

Report

Explainable Learning with Gaussian Processes

Autor: Butler, Kurt, Feng, Guanchao, Djuric, Petar M.

The field of explainable artificial intelligence (XAI) attempts to develop methods that provide insight into how complicated machine learning methods make predictions. Many methods of explanation have focused on the concept of feature attribution, a

Externí odkaz: http://arxiv.org/abs/2403.07072

Zobrazit plný text záznamu

Report

Dagma-DCE: Interpretable, Non-Parametric Differentiable Causal Discovery

Autor: Waxman, Daniel, Butler, Kurt, Djuric, Petar M.

Publikováno v: IEEE Open Journal of Signal Processing, vol. 5, pp. 393-401, 2024

We introduce Dagma-DCE, an interpretable and model-agnostic scheme for differentiable causal discovery. Current non- or over-parametric methods in differentiable causal discovery use opaque proxies of ``independence'' to justify the inclusion or excl

Externí odkaz: http://arxiv.org/abs/2401.02930

Zobrazit plný text záznamu