Till Speicher

PhD Student

MPI-SWS

About me

I am a final-year PhD student at MPI-SWS, Germany, advised by Krishna Gummadi.
My current research focus is on understanding the properties of representations in deep neural networks. Previously, I have worked on topics related to fairness in algorithmic decision making.
I obtained a Bachelor's degree in Computer Science from Saarland University.
In my free time, I am active as a triathlete.

Publications

Image inputs being fed to two DNNs to generate representations

Pointwise Representational Similarity

Camila Kolling, Till Speicher, Vedant Nanda, Mariya Toneva, Krishna P. Gummadi

Preprint, 2023

Paper

Clipart of a neural network with nodes in multiple colors

Diffused Redundancy in Pre-trained Representations

Vedant Nanda, Till Speicher, John P. Dickerson, Soheil Feizi, Krishna P. Gummadi, Adrian Weller

NeurIPS 2023

Paper

Measuring Representational Robustness of Neural Networks Through Shared Invariances

Vedant Nanda, Till Speicher, Camila Kolling, John P. Dickerson, Krishna P. Gummadi, Adrian Weller

ICML 2022, accepted as oral presentation

Paper

A Venn diagram showing pairwise sets of dog, zebra and cat classes

Unifying Model Explainability and Robustness via Machine-Checkable Concepts

Vedant Nanda, Till Speicher, John P. Dickerson, Krishna P. Gummadi, Muhammad Bilal Zafar

Preprint, 2020

Paper

A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices

Till Speicher, Hoda Heidari, Nina Grgic-Hlaca, Krishna P. Gummadi, Adish Singla, Adrian Weller, Muhammad Bilal Zafar

KDD '18: The 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2018

Paper

Multicolored figures separated into different groups

Potential for Discrimination in Online Targeted Advertising

Till Speicher, Muhammad Ali, Giridhari Venkatadri, Filipe Nunes Ribeiro, George Arvanitakis, Fabrício Benevenuto, Krishna P. Gummadi, Patrick Loiseau, Alan Mislove

Conference on Fairness, Accountability, and Transparency - FAccT 2018

Paper

A 2D classification problem with red and green dots and decision areas

Reliable Learning by Subsuming a Trusted Model: Safe Exploration of the Space of Complex Models

Till Speicher, Muhammad Bilal Zafar, Krishna P. Gummadi, Adish Singla, Adrian Weller

Reliable Machine Learning in the Wild - ICML 2017 Workshop

Paper

A cascade of recursive n-gram probability distributions

A Generalized Language Model as the Combination of Skipped n-grams and Modified Kneser-Ney Smoothing

Rene Pickhardt, Thomas Gottron, Martin Körner, Paul Georg Wagner, Till Speicher, Steffen Staab

ACL 2014

Paper