Niki Kilbertus

kilbertus.niki@gmail.com

My mission is to build socially beneficial, robust, and theoretically substantiated machine learning systems.

I have open PhD positions, please apply!

I'm a group leader at HelmholtzAI in Munich looking for motivated PhD students interested in causality or socially beneficial machine learning (fairness, privacy, performativity, ...) More info here.

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

  • 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).

  • 03/2020: I joined Google for an internship on privacy-preserving machine learning

  • 01/2020: Fair decisions despite imperfect predictions @ AISTATS 2020

  • 12/2019: Honored to be one of the 10 "AI-newcomers" in Germany

  • 07/2019: Organizing a NeurIPS workshop on Human Centric Machine Learning

  • 06/2019: Improving consequential decisions under imperfect predictions @ KDD 2019 Workshop (DCCL)

  • 06/2019: Convolutional neural networks: a magic bullet for gravitational-wave detection? @ Physical Review D

  • 05/2019: The sensitivity of counterfactual fairness to unmeasured confounding @ UAI 2019

Selected Publications & Projects

Exploration in two-stage recommender systems

Jiri Hron*, Karl Krauth*, Michael I. Jordan, NK (* equal contribution)

[paper]

ACM RecSys 2020 Workshop on Bandit and Reinforcement Learning from User Interactions (REVEAL 2020)

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

[paper] [bibtex] [code]

AISTATS 2020

The sensitivity of counterfactual fairness to unmeasured confounding

NK, Philip Ball, Matt J. Kusner, Adrian Weller, Ricardo Silva

UAI 2019

[paper] [bibtex] [code]

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

[paper] [bibtex] [poster] [code]

Learning Independent Causal Mechanisms

Giambattista Parascandolo, NK, Mateo Rojas-Carulla, Bernhard Schölkopf

ICML 2018

also at: NIPS 2017 Workshop on Learning Disentangled Representations

[paper] [bibtex]

Avoiding Discrimination Through Causal Reasoning

NK, Mateo Rojas-Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, Bernhard Schölkopf

NeurIPS 2017

[paper] [bibtex] [poster]

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

[paper] [bibtex] [code] [poster]

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)]

Quod erat knobelandum

Clara Löh, Stefan Krauss, NK

Springer Spektrum, (1st edition: 2016, 2nd edition: 2019)

[springer] [amazon]

Master Thesis Physics: Numerical Analysis of Gravitational Wave Generation during Metric Preheating

NK

[thesis (pdf, ~12MB)] [code]

Master Thesis Mathematics: Numerical Analysis of Causal Fermion Systems on R x S^3

NK

[thesis (pdf, ~3.8MB)]

Physics Project: Sky-MoCa: The Skyrmion Phase in 3D Lattice Simulations

NK

[report] [code]

News mentions and science communication


Talks

  • Gaussian Process Summer School 2020, Causality Workshop: A class of general instrumental variable models

  • TU Munich (Germany): A class of general instrumental variable models

  • Albert Einstein Institute (Potsdam-Golm, Germany): Machine Learning powered CBC Search

  • Alan Turing Institute (London, UK): Fairness in Machine Learning

  • Max Planck Institute for Software Systems (Saarbrücken, Germany): Fairness in Machine Learning

  • Stanford University (CA, USA): Searching for Gravitational Waves with Machine Learning

  • University of Regensburg (Regensburg, Germany): Fully Convolutional Networks for Gravitational Wave Searches

  • Microsoft Research (Cambridge, UK): Learning Independent Causal Mechanisms

  • Amazon Research (Cambridge, UK): Blind Justice: Fairness with Encrypted Sensitive Attributes

Service to the community

Contact