Celestine Dünner

Celestine Mendler-Dünner

I am a postdoctoral researcher at UC Berkeley interested in algorithmic aspects of machine learning and artificial intelligence. I am holding an SNF Early Postdoc.Mobility fellowship and I am hosted by Prof. Moritz Hardt. Prior to that I worked as a postdoctoral researcher at IBM Research Zürich. I have obtained my PhD from ETH Zürich where I was affiliated with the Data Analytics Laboratory and supervised by Prof. Thomas Hofmann.

LinkedIn Google Scholar

checkout Snap ML our new library for fast training of GLMs at large scale


Sampling Acquisition Functions for Batch Bayesian Optimization
A. De Palma, C.Mendler-Dünner, T.Parnell, A. Anghel, H. Pozidis
ArXiv preprint
SySCD: A System-Aware Parallel Coordinate Descent Algorithm
C.Mendler-Dünner*, N.Ioannou*, T.Parnell
to appear in Advances in Neural Information Processing Systems (NeurIPS - Spotlight)
On Linear Learning with Manycore Processors
E.Wszola, C.Mendler-Dünner, M.Jaggi, M.Püschel
to appear at IEEE International Conference on High Performance Computing (HiPC)
System-Aware Algorithms for Machine Learning
ETH Research Collection (PhD Thesis)
Snap ML: A Hierarchical Framework for Machine Learning
C.Dünner*, T.Parnell*, D.Sarigiannis, N.Ioannou, A.Anghel, G.Ravi, M.Kandasamy and H.Pozidis
Advances in Neural Information Processing Systems (NeurIPS)
A Distributed Second-Order Algorithm You Can Trust
C.Dünner, M. Gargiani, A. Lucchi, A. Bian, T. Hofmann and M. Jaggi
International Conference on Machine Learning (ICML)
Addressing Interpretability and Cold-Start in Matrix Factorization for Recommender Systems
M. Vlachos*, C.Dünner*, R.Heckel, V.Vassiliaadis, T.Parnell and K.Atasu
IEEE Transactions on Knowledge and Data Engineering (TKDE)
Tera-Scale Coordinate Descent on GPUs
T.Parnell, C.Dünner, K.Atasu, M.Sifalakis and H.Pozidis
Journal of Future Generation Computer Systems (FGCS)
Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems
C.Dünner, T.Parnell, M.Jaggi
Advances in Neural Information Processing Systems (NIPS)
Understanding and Optimizing the Performance of Distributed Machine Learning Applications on Apache Spark
C.Dünner, T.Parnell, K.Atasu, M.Sifalakis and H.Pozidis
IEEE International Conference on Big Data (IEEE Big Data)
High-Performance Recommender System Training Using Co-Clustering on CPU/GPU Clusters
K.Atasu, T.Parnell, C.Dünner, M.Vlachos and H.Pozidis
International Conference on Parallel Processing (ICPP)
Large-Scale Stochastic Learning using GPUs
T.Parnell, C.Dünner, K.Atasu, M.Sifalakis and H.Pozidis
IEEE International Workshop on Parallel and Distributed Computing for Large Scale Machine Learning and Big Data Analytics (ParLearning)
Scalable and Interpretable Product Recommendations via Overlapping Co-Clustering
R.Heckel, M.Vlachos, T.Parnell and C.Dünner
IEEE International Conference on Data Engineering (ICDE)
Primal-Dual Rates and Certificates
C.Dünner, S.Forte, M.Takac and M.Jaggi
International Conference on Machine Learning (ICML)
*equal contribution

Invited Talks

Zürich Women in Machine Learning and Data Science Meetup -- schedule
AMLD workshop -- Advances in ML: Theory meets practice -- slides schedule
EcoCloud Annual Event in Lausanne -- slides
Zurich ML meetup -- abstract