Prof. Dr. Isabel Valera & Miriam Rateike

Welcome, Organization, Ethical ML, Causality Intro

Readings: Pearl Primer, Chapter 1&2

ONLINE (link will be shared in due time)

Prof. Dr. Isabel Valera & Amir-Hossein Karimi

Causality: Interventions & Counterfactuals

Readings: Pearl Primer, Chapter 3&4

ONLINE (link will be shared in due time)

Readings:

1. CXPlain: Causal Explanations for Model Interpretation under Uncertainty (Patrick Schwab, Walter Karlen, NeurIPS2019)

2. Explaining the Behavior of Black-Box Prediction Algorithms with Causal Learning (Numair Sani, Daniel Malinsky,Ilya Shpitser, arXiv 2020)

ONLINE (link will be shared in due time)

Readings:

3. Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice (David Watson, Limor Gultchin,Ankur Taly, Luciano Floridi, UAI 2021)

4. Algorithmic recourse under imperfect causal knowledge: a probabilistic approach (Amir-Hossein Karimi, Julius vonK ̈ugelgen, Bernhard Sch ̈olkopf, Isabel Valera, NeurIPS 2020)

ONLINE (link will be shared in due time)

ONLINE (link will be shared in due time)

Readings:

1. Avoiding Discrimination through Causal Reasoning (Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo,Moritz Hardt, Dominik Janzing, Bernhard Schölkopf, NeurIPS 2017)

2. Counterfactual Fairness (Matt Kusner, Joshua Loftus, Chris Russell, Ricardo Silva, NeurIPS 2017)

ONLINE (link will be shared in due time)

Readings:

3. Path-Specific Counterfactual Fairness (Silvia Chiappa, AAAI 2019)

4. The Sensitivity of Counterfactual Fairness to Unmeasured Confounding (Niki Kilbertus, Philip J. Ball, Matt J. Kusner, Adrian Weller, Ricardo Silva, UAI 2020)

ONLINE (link will be shared in due time)

ONLINE (link will be shared in due time)

Readings:

1. The risks of invariant risk minimization (Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski, ICLR 2021)

2. Invariant policy optimization: Towards stronger generalization in reinforcement learning (Anoopkumar Sonar, Vincent Pacelli, Anirudha Majumdar, PMLR 2021)

ONLINE (link will be shared in due time)

Readings:

3. Domain adaptation by using causal inference to predict invariant conditional distributions (Sara Magliacane, Thijs van Ommen, Tom Claassen, Stephan Bongers, Philip Versteeg, Joris M. Mooij, NeurIPS 2018) - Nice link to learn about d-separation.

4. A Causal View on Robustness of Neural Networks (Cheng Zhang, Kun Zhang, Yingzhen Li, NeurIPS 2020)

ONLINE (link will be shared in due time)

ONLINE (link will be shared in due time)