New thesis explores causality for realistic AI decision-making

This thesis explores the intersection of causality and machine learning to address limitations in generalization and decision-making. It proposes a new framework for algorithmic recourse, focusing on realistic cost functions and temporal dimensions for policy evaluation. Additionally, it extends causal interventions to dynamical systems, linking process equilibria to Structural Causal Models for a more realistic representation of temporal dynamics. AI

IMPACT Enhances AI's ability to generalize and make robust decisions in dynamic environments.

RANK_REASON The item is an academic paper published on arXiv discussing theoretical advancements in machine learning and causality. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv Recommender
• Influence Flower
• machine learning
• ScienceCast
• Structural Causal Models

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →