# 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 machine learning in October 2017, where I am co-supervised by Bernhard Schölkopf at the Max Planck Institute for Intelligent Systems and Carl Rasmussen and Adrian Weller in the machine learning group at the University of Cambridge. I am a member of Pembroke College and funded by the Cambridge-Tübingen PhD fellowship with generous donations from Microsoft. My prospective graduation year is 2020.

Prior, I obtained an M.Sc. in both Mathematics and Physics from the University of Regensburg. During my studies I spent time at the High Energy Theory Group at Harvard, where I worked with Paul Chesler and Wilke van der Schee on simulating holographic planar shock collisions, as well as at the Kavli Institute for Particle Astrophysics and Cosmology at Stanford, where I worked with William East and Tom Abel on simulations of gravitational wave formation during preheating.

## Selected Publications & Projects

**Avoiding Discrimination Through Causal Reasoning**

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

NIPS 2017

[paper][bibtex][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

**Learning Independent Causal Mechanisms**

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

NIPS 2017 Workshop on Learning Disentangled Representations

[paper]

**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 $\mathbb{R} \times S^3$**

**NK**

[thesis (pdf, ~3.8MB)]

## 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* - University of Cambridge (Cambridge, UK):
*Introduction to the Minimum Description Length Principle*

## Miscellaneous

- I organized the first external CamTue workshop in November 2017 on Mallorca.
- I thoroughly enjoy teaching, was active in the Schülerzirkel Mathematik in Regensburg, tutored courses on cryptography, web applications, electrodynamics, waves and optics, mathematical methods in physics, was lecturer of a semi-annual course on
*Computer- and Microcontroller-Technology*, and co-lectured the course Green-IT at the summer academy 2016 in Leysin, organized by the German Academic Scholarship Foundation. - I enjoy building things, for example: Babyzen - A flexible sensor BoosterPack [codeproject article][short video][report (pdf)] or some things here.