Niki Kilbertus

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

I started my PhD in the Cambridge-Tübingen program in 2016 (prospective graduation in 2020), where I am co-supervised by Bernhard Schölkopf and Carl Rasmussen. My advisor is Adrian Weller.

I am a member of Pembroke College, funded by the Cambridge-Tübingen PhD fellowship with generous donations from Microsoft.

My background is in Physics and Mathematics. I was fortunate to spend time at Harvard, working with Paul Chesler and Wilke van der Schee, as well as at Stanford, working with William East and Tom Abel.

News

  • 05/2018: Two papers accepted at ICML 2018
  • 04/2018: I will join Amazon for a summer internship
  • 11/2017: "Learning Independent Causal Mechanisms" accepted at NIPS workshop on Learning Disentangled Representations
  • 11/2017: "ConvWave" accepted at NIPS workshop on Deep Learning for Physical Sciences
  • 09/2017: "Avoiding Discrimination Through Causal Reasoning" accepted at NIPS 2017

Selected Publications & Projects

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 [short talk] and PIMLAI 2018

[paper] [bibtex] [poster] [in the press: New Scientist, The Alan Turing Institute]

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

NIPS 2017

[paper] [bibtex] [poster] [in the press: MPI] [related grant: Digital Impact Grant by Stanford PACS]

ConvWave: Searching for Gravitational Waves with Fully Convolutional Neural Nets

Timothy Gebhard*, NK*, Giambattista Parascandolo, Ian Harry, Bernhard Schölkopf (* equal contribution)

NIPS 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, 2016

[book] [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 $\mathbb{R} \times S^3$

NK

[thesis (pdf, ~3.8MB)]

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

NK

[report] [code]

Talks

  • 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

Miscellaneous

Contact

[last] [dot] [first] [at] gmail [dot] com