I'm a group leader at HelmholtzAI in Munich and a TUM Junior Fellow working on causality and socially beneficial machine learning.
I obtained my PhD in the Cambridge-Tübingen program co-supervised by Bernhard Schölkopf, Carl Rasmussen, and Adrian Weller. I was an Ellis student and member of Pembroke College, funded by the Cambridge-Tübingen PhD fellowship with generous donations from Microsoft.
During my PhD I interned at Deepmind, Google, and Amazon.
I grew up in Austria, studied Physics and Math in Regensburg, and was fortunate to spend time at Harvard and Stanford during my studies.
News
04/2021: Organizing an ICML workshop on the Neglected Assumptions in Causal Inference
04/2021: Yay, number three, Zhufeng Li, joined us as PhD student 🎉
03/2021: Super excited about Kirtan Padh having joined the group as PhD student 🎉
11/2020: Very happy that Elisabeth Ailer joined the group as my first PhD student 🎉
09/2020: I joined HelmholtzAI in Munich as a group leader
09/2020: A class of algorithms for general instrumental variable models @NeurIPS 2020
09/2020: I successfully defended my PhD =)
09/2020: Exploration in two-stage recommender systems @RecSys 2020 Workshop REVEAL
08/2020: Organizing a NeurIPS workshop on Consequential Decision Making in Dynamic Environments
06/2020: My Google intern project on membership inference attacks was open-sourced at tensorflow/privacy (blog post).
Students
Elisabeth Ailer (PhD candidate)
Kirtan Padh (PhD candidate)
Zhufeng Li (PhD candidate)
Alexander Reisach (MSc student)
Selected Publications & Projects
Exploration in two-stage recommender systems
Jiri Hron*, Karl Krauth*, Michael I. Jordan, NK (* equal contribution)
ACM RecSys 2020 Workshop on Bandit and Reinforcement Learning from User Interactions (REVEAL 2020)
NeurIPS 2020 Workshop on Consequential Decisions in Dynamic Environments
NeurIPS 2020 Workshop on Challenges of Real-World RL
A class of algorithms for general instrumental variable models
NK, Matt J. Kusner, Ricardo Silva
[paper] [code] [talk video]
NeurIPS 2020
Is Independence all you need? On the Generalization of Representations Learned from Correlated Data
Frederik Träuble, Elliot Creager, NK, Anirudh Goyal, Francesco Locatello, Bernhard Schölkopf, Stefan Bauer
[paper]
Fair decisions despite imperfect predictions
NK, Manuel Gomez-Rodriguez, Bernhard Schölkopf, Krikamol Muandet, Isabel Valera
AISTATS 2020
The sensitivity of counterfactual fairness to unmeasured confounding
NK, Philip Ball, Matt J. Kusner, Adrian Weller, Ricardo Silva
UAI 2019
Convolutional neural networks: a magic bullet for gravitational-wave detection?
Timothy Gebhard*, NK*, Ian Harry, Bernhard Schölkopf (* equal contribution)
Physical Review D, 2019
[paper] [bibtex] [code] [data generation] [DOI]
Improving consequential decision making under imperfect predictions
NK, Manuel Gomez-Rodriguez, Bernhard Schölkopf, Krikamol Muandet, Isabel Valera
[paper]
KDD 2019 Workshop on Data Collection, Curation, and Labeling for Mining and Learning (DCCL)
Generalization in anti-causal learning
NK*, Giambattista Parascandolo*, Bernhard Schölkopf (* equal contribution)
NeurIPS 2018 Workshop on Critiquing and correcting trends in machine learning
[paper]
Blind Justice: Fairness with Encrypted Sensitive Attributes
NK, Adrià Gascón, Matt J. Kusner, Michael Veale, Krishna P. Gummadi, Adrian Weller
ICML 2018
also at: FATML 2018 [talk] and PIMLAI 2018
Learning Independent Causal Mechanisms
Giambattista Parascandolo, NK, Mateo Rojas-Carulla, Bernhard Schölkopf
ICML 2018
also at: NIPS 2017 Workshop on Learning Disentangled Representations
Avoiding Discrimination Through Causal Reasoning
NK, Mateo Rojas-Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, Bernhard Schölkopf
NeurIPS 2017
ConvWave: Searching for Gravitational Waves with Fully Convolutional Neural Nets
Timothy Gebhard*, NK*, Giambattista Parascandolo, Ian Harry, Bernhard Schölkopf (* equal contribution)
NeurIPS 2017 Workshop on Deep Learning for Physical Sciences
PhD Thesis
Beyond traditional assumptions in fair machine learning
NK
PhD Thesis @ University of Cambridge
[thesis pdf (arxiv)]
Physics & Math
Universal Hydrodynamic Flow in Holographic Planar Shock Collisions
Paul Chesler, NK, Wilke van der Schee
Journal for High Energy Physics, 2015
[paper, arxiv version] [detailed project report (pdf, ~1MB)]
Master Thesis Mathematics: Numerical Analysis of Causal Fermion Systems on R x S^3
NK
[thesis (pdf, ~3.8MB)]
Book
News mentions and science communication
Interview with Digital Impact 4Q4 (2020)
Digital Impact covering Fairensics in Closing the Fairness Gap in Machine Learning (2020)
Interviews for podcasts at Hessischer Rundfunk (HR) about fairness and explainability in AI [German only] (2020)
Brief interview at SWR2 about AI [German only] (2020)
Final report of our Digital Impact Grant project Avoiding Discrimination in Automated Decision Making and Machine Learning
KI-Newcomer; MPI News (2019)
Psychologie Heute: Der faire Algorithmus (2019)
Die ZEIT: Wenn Maschinen kalt entscheiden (2019)
MPI news: Blind Justice -- Researchers take new approach to machine learning fairness by applying privacy methods (2018)
The Alan Turing Institute: Can justice be blind when it comes to machine learning? (2018)
Second Nexus: Niki Kilbertus of Max Planck Institute for Intelligent Systems Has a Plan to Remove Bias From AIs (2018)
New Scientist: How to stop artificial intelligence being so racist and sexist (2018)
Financial Times: Finding a fair way to tame the bigoted bots (2018)
MPI news: The Question is Why -- Algorithms learn a Sense of Fairness (2017)
Matt, Adrià, and Adrian talked about our work in three different episodes of The Talking Machines podcast (2018, 2019)
Activities
Co-organizing a workshop on the Neglected Assumptions in Causal Inference @ ICML2021
Co-organizing a workshop on Consequential Decisions in Dynamic Environments @ NeurIPS2020
Co-organized the Human Centric Machine Learning workshop @ NeurIPS2019
Co-organized the Privacy Preserving Machine Learning workshop @ NeurIPS2018
Organized the CamTue workshop on Tenerife in 2018 and on Mallorca in 2017
Contact
