Chris Wendler

E-MAIL
ADDRESS Universitätstrasse 6, 8092 Zürich, Switzerland
ROOM CAB H 81.2

I am a PhD student advised by Markus Püschel and collaborating with Dan Alistarh. My research interests lie in machine learning and mathematics. Currently, I am working on geometric deep learning, set function learning and generalized signal processing.



Student Projects

  • Manuel Nowack, Master’s thesis 2022
    Compiler Flag Optimization using Fourier-sparse Set Functions
    [pdf]

  • Simon Ebner, Bachelor’s thesis 2022
    setFTs: A package for Fourier transforms on set functions and its application to compiler flag optimization
    [pdf] [code] [pypi]

  • Enrico Brusoni, Bachelor’s thesis 2022
    Learning Set Functions that are Sparse in Better Non-Orthogonal Fourier Bases
    [pdf]

  • Tierry Hörmann, Master’s thesis 2022
    Compiler Flag Optimization using Fourier-sparse Poset Functions
    [pdf]

  • Felipa Schwarz, Bachelor’s thesis 2021
    Fourier Analysis of Activations in Neural Networks
    [pdf] [code]

  • Hugo Polsinelli, Master’s thesis 2020
    Lattice Convolutional Neural Networks
    [pdf] [code]

  • Felix Sarnthein-Lotichius, Bachelor’s thesis 2019
    Jordan Chevalley Decomposition - Implementation and Numerical Analysis
    [pdf] [code]

  • Panagiotis Misiakos, Summer fellow 2019
    Diagonalizable Shift and Filters for Directed Graphs Based on the Jordan-Chevalley Decomposition
    [pdf]

Projects

  • Graph transformer based on depth first search codes [code]
  • Self-supervised learning for genotype-phenotype data [code]
  • Using large language model embeddings as targets [code]

Publications

2022

Causal Fourier Analysis on Directed Acyclic Graphs and Posets
Bastian Seifert, Chris Wendler, Markus Püschel
arXiv:2209.07970 [pdf]

Fourier Analysis-based Iterative Combinatorial Auctions
Jakob Weissteiner, Chris Wendler, Sven Seuken, Ben Lubin, Markus Püschel
Proc. International Joint Conference on Artificial Intelligence (IJCAI) [pdf] [poster] [code]

Learning Fourier-Sparse Functions on DAGs
Bastian Seifert, Chris Wendler, Markus Püschel
ICLR Workshop on the Elements of Reasoning: Objects, Structure, and Causality [pdf] [poster]

Instance-wise algorithm configuration with graph neural networks
Romeo Valentin, Claudio Ferrari, Jérémy Scheurer, Andisheh Amrollahi, Chris Wendler, Max B. Paulus
Proc. of the machine learning for combinatorial optimization NeurIPS 2021 competition [pdf]

2021

Discrete Signal Processing on Meet/Join Lattices
Markus Püschel, Bastian Seifert, Chris Wendler
Trans. on Signal Processing [pdf]

Wiener Filter on Meet/Join Lattices
Bastian Seifert, Chris Wendler, Markus Püschel
Proc. International Conference on Acoustics, Speech, and Signal Processing (ICASSP) [pdf]

Learning Set Functions that are Sparse in Non-Orthogonal Fourier Bases
Chris Wendler, Andisheh Amrollahi, Bastian Seifert, Andreas Krause, Markus Püschel
Proc. AAAI Conference on Artificial Intelligence [pdf] [poster] [video] [code]

Discrete Signal Processing with Set Functions
Markus Püschel, Chris Wendler
Trans. on Signal Processing [pdf]

2020

Diagonalizable Shift and Filters for Directed Graphs Based on the Jordan-Chevalley Decomposition
Panagiotis Misiakos, Chris Wendler, Markus Püschel
Proc. International Conference on Acoustics, Speech, and Signal Processing (ICASSP) [pdf]

2019

Powerset Convolutional Neural Networks
Chris Wendler, Dan Alistarh, Markus Püschel
Proc. Neural Information Processing Systems (NeurIPS) [pdf] [poster] [code]

Sampling Signals on Meet/Join Lattices
Chris Wendler, Markus Püschel
Proc. Global Conference on Signal and Information Processing (GlobalSIP) [pdf] [slides] [code]

Teaching

Education

Bachelor (B.Sc.) in Mathematics, University of Innsbruck, Austria
advisor Markus Haltmeier, Thesis
July 2017
Master (M.Sc.) in Computer Science, University of Innsbruck, Austria
advisor Szedmák Sándor, Thesis
September 2016
Bachelor (B.Sc.) in Computer Science, University of Innsbruck, Austria
advisor Justus Piater, Thesis
November 2013