Till Speicher
Till Speicher
PhD student, Planck Institute for Software Systems (MPI-SWS)
Verified email at - Homepage
Cited by
Cited by
A unified approach to quantifying algorithmic unfairness: Measuring individual &group unfairness via inequality indices
T Speicher, H Heidari, N Grgic-Hlaca, KP Gummadi, A Singla, A Weller, ...
Proceedings of the 24th ACM SIGKDD international conference on knowledge …, 2018
Potential for discrimination in online targeted advertising
T Speicher, M Ali, G Venkatadri, FN Ribeiro, G Arvanitakis, F Benevenuto, ...
Conference on fairness, accountability and transparency, 5-19, 2018
A generalized language model as the combination of skipped n-grams and modified Kneser-Ney smoothing
R Pickhardt, T Gottron, M Körner, PG Wagner, T Speicher, S Staab
arXiv preprint arXiv:1404.3377, 2014
Measuring Representational Robustness of Neural Networks Through Shared Invariances
V Nanda, T Speicher, C Kolling, JP Dickerson, K Gummadi, A Weller
International Conference on Machine Learning, 16368-16382, 2022
Reliable learning by subsuming a trusted model: Safe exploration of the space of complex models
T Speicher, MB Zafar, KP Gummadi, A Singla, A Weller
Proc. Int. Conf. Mach. Learn. Workshop (ICML), 1-5, 2017
Diffused Redundancy in Pre-trained Representations
V Nanda, T Speicher, JP Dickerson, S Feizi, KP Gummadi, A Weller
arXiv preprint arXiv:2306.00183, 2023
Pointwise Representational Similarity
C Kolling, T Speicher, V Nanda, M Toneva, KP Gummadi
arXiv preprint arXiv:2305.19294, 2023
Learned Neural Network Representations are Spread Diffusely with Redundancy
V Nanda, T Speicher, JP Dickerson, S Feizi, K Gummadi, A Weller
Invariance Makes a Difference: Disentangling the Role of Invariance and Equivariance in Representations
T Speicher, V Nanda, KP Gummadi
Unifying Model Explainability and Robustness via Machine-Checkable Concepts
V Nanda, T Speicher, JP Dickerson, KP Gummadi, MB Zafar
arXiv preprint arXiv:2007.00251, 2020
The system can't perform the operation now. Try again later.
Articles 1–10