Celestine Dünner

Celestine Mendler-Dünner

I am a Principal Investigator at the ELLIS Institute in Tübingen, co-affiliated with the Max Planck Institute for Intelligent Systems and the Tübingen AI Center. My research focuses on machine learning in social context and the role of prediction in digital economies. Before moving to Germany I spent two years as an SNSF postdoctoral fellow at UC Berkeley hosted by Moritz Hardt. I have obtained my PhD from ETH Zurich where I was affiliated with the Data Analytics Laboratory and supervised by Thomas Hofmann. During my PhD I was employed at IBM Research Zurich where I contributed to the design and implementation of the IBM Snap ML library.

LinkedIn Google Scholar Twitter


     I was appointed as an ELLIS Scholar
     I was named an Elisabeth-Schiemann-Fellow
    Serving as Program co-Chair for EAAMO'23
    Serving as an Area Chair for NeurIPS'22, ICML'23 and EWAF'23
    Organizing a NeurIPS'21 workshop on Learning and Decision-Making with Strategic Feedback.
     I was awarded the ETH Medal for my dissertation
     I won the Fritz Kutter Award for the high industrial impact of my research on system-aware algorithm design
     I was awarded the SNSF Early Postdoc.Mobility fellowship and will join UC Berkeley in Summer 2019
   I successfully defended my PhD. I am now a postdoctoral researcher at IBM Research, Zurich
    My contributions to Snap ML were recognized with the IBM Eminence and Excellence Award
    Snap ML released for public use: > pip install snapml
    Snap ML in the press: Forbes, The Register and EE Times writing about our research


Are you interested in working with me as a Postdoc? Please get in touch via email.
Prospective PhD students, please apply through one of the following programs:
(indicate that you are interested in working with me)

Selected Research Projects

  • Performative Prediction

    → See my talk in the MIT OPTML++ seminar for a technical overview.

    When informing consequential decisions, predictions have the potential to change the way the broader system behaves by triggering actions and reactions of individuals. Thereby they alter the data distribution the predictive model has been trained on -- a dynamic effect that traditional machine learning fails to account for. To formalize and address this phenomenon, we introduce the framework of performative prediction to supervised learning [ICML'20]. We analyze the dynamics of retraining strategies in this setup and address challenges faced in stochastic optimization when the deployment of a model triggers performative effects in the data distribution it is being trained on [NeurIPS'20]. When performative effects are strong we would wish to model and understand these effects in order to incorporate them into the very design of learning systems. Towards this ambitious goal we explore connections to microfoundations from macroeconomics theory and investigate how assumptions on individual behavior can be used to model and analyze performative effects in the context of strategic classification [ICML'21]. We study performative prediction through the lense of causal inference [NeurIPS'22], and we build on connection to online learning to design targeted experimentation and exploration strategies to collect data and find good models ex-post [ICML'22]. More broadly, performative prediction brings together ideas from machine learning, optimization, causality, and control theory to offer a formal framework to talk about the impact of algoirthms on society.

  • Power in Prediction and Digital Economies

    → See my talk at Oxford Social foundations for Statistics and ML for an overview.

    The extent to which predictions are performative is closely related to the economic concept of power -- the more powerful the firm making the prediction, the stronger the performative effects they induce. As such, power plays a suddle role in learning. In particular, it offers a lever to achieve low risk for the firm making the predictions by exerting influence on the population. We introduce the notion of performative power [NeurIPS'22a] to formally study power in prediction. We relate performative power to the economic study of competition in digital economies, analyze its role in optimization and propose an observational causal design to estimate performative power from properties of predictive Systems [NeurIPS'22b,CDS@NeurIPS'22]. Shifting perspective, we investigate algorithmic collective action as a means to counter power imbalances in digital economies. Most digital firms rely to some extent on data provided by individuals. This offers a lever to the population for gaining some control over the system by strategically reporting data [ICML'23]. We study different learning settings and quantify the critical mass of individuals that need to be mobilized to achieve concrete goals. The critical mass is closely related to the cost of mobilizing a collective. Going further, I am interested in studying the effectiveness of concrete strategies and challenges of coordination, as well as connection to labor markets and collective action theory in political economy.

  • System-Aware Algorithm Design

    When training machine learning models in production, speed and efficiency are critical factors. Fast training times allow short development cycles, offer fast time-to-insight, and after all, save valuable resources. Our approach to achieving fast training is to enable the efficient use of modern hardware through novel algorithm design. In particular, we develop principled tools and methods for training machine learning models focusing on: compute parallelism [NeurIPS'19][ICML'20], hierarchical memory structures [HiPC'19][NeurIPS'17], accelerator units [FGCS'17] and interconnect bandwidth in distributed systems [ICML'18]. We demonstrated [NeurIPS'18] that such an approach can lead to several orders of magnitude reduction in training time compared to standard system-agnostic methods. The innovations of this research form the backbone of the IBM Snap ML library and help diverse companies improve speed, efficiency and scalability of their machine learning workloads.


*alphabetical order
Questioning the Survey Responses of Large Language Models
R. Dominguez-Olmedo, M.Hardt and C.Mendler-Dünner
Arxiv, 2023.
Algorithmic Collective Action in Machine Learning
M.Hardt*, E.Mazumdar*, C.Mendler-Dünner* and T.Zrnic*
International Conference on Machine Learning (ICML), 2023.
Anticipating Performativity by Predicting from Predictions
C.Mendler-Dünner, F. Ding and Y. Wang
Advances in Neural Information Processing Systems (NeurIPS), 2022.
Performative Power
M.Hardt*, M.Jagadeesan* and C.Mendler-Dünner*
Advances in Neural Information Processing Systems (NeurIPS), 2022.
Regret Minimization with Performative Feedback
M.Jagadeesan, T.Zrnic and C.Mendler-Dünner
International Conference on Machine Learning (ICML), 2022.
Symposium on Foundations of Responsible Computing (FORC), 2022.
Test-time Collective Prediction
C.Mendler-Dünner, W.Guo, S.Bates and M.I.Jordan
Advances in Neural Information Processing Systems (NeurIPS), 2021.
Alternative Microfoundations for Strategic Classification
M.Jagadeesan, C.Mendler-Dünner and M.Hardt
International Conference on Machine Learning (ICML), 2021.
Differentially Private Stochastic Coordinate Descent
G.Damaskinos, C.Mendler-Dünner, R.Guerraoui, N.Papandreou and T.Parnell
AAAI Conference on Artificial Intelligence (AAAI), 2021.
Stochastic Optimization for Performative Prediction
C.Mendler-Dünner*, J.C.Perdomo*, T.Zrnic* and M.Hardt
Advances in Neural Information Processing Systems (NeurIPS), 2020.
Performative Prediction
J.C.Perdomo*, T.Zrnic*, C.Mendler-Dünner and M.Hardt
International Conference on Machine Learning (ICML), 2020.
Randomized Block-Diagonal Preconditioning for Parallel Learning
C.Mendler-Dünner and A.Lucchi
International Conference on Machine Learning (ICML), 2020.
SySCD: A System-Aware Parallel Coordinate Descent Algorithm
N.Ioannou*, C.Mendler-Dünner* and T.Parnell
Advances in Neural Information Processing Systems (NeurIPS -- Spotlight), 2019.
On Linear Learning with Manycore Processors
E.Wszola, C.Mendler-Dünner, M.Jaggi and M.Püschel
IEEE International Conference on High Performance Computing (HiPC -- best paper finalist), 2019.
System-Aware Algorithms for Machine Learning
ETH Research Collection (PhD Thesis -- ETH medal), 2019.
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), 2018.
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), 2018.
Addressing Interpretability and Cold-Start in Matrix Factorization for Recommender Systems
C.Dünner*, M. Vlachos*, R.Heckel, V.Vassiliaadis, T.Parnell and K.Atasu
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2018.
Tera-Scale Coordinate Descent on GPUs
T.Parnell, C.Dünner, K.Atasu, M.Sifalakis and H.Pozidis
Journal of Future Generation Computer Systems (FGCS), 2018.
Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems
C.Dünner, T.Parnell and M.Jaggi
Advances in Neural Information Processing Systems (NIPS), 2017.
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), 2017.
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), 2017.
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), 2017.
Primal-Dual Rates and Certificates
C.Dünner, S.Forte, M.Takac and M.Jaggi
International Conference on Machine Learning (ICML), 2016.

Peer-reviewed Workshop Contributions

Causal Inference out of Control: Estimating the Steerability of Consumption
G.Cheng, M.Hardt and C.Mendler-Dünner
A Causal View on Dynamical Systems Workshop (CDS@NeurIPS -- Oral presentation), 2022.
Revisiting Design Choices in Proximal Policy Optimization
C.C.-Y.Hsu, C.Mendler-Dünner and M.Hardt
Workshop on Real World Challenges in RL (RWRL@NeurIPS), 2020.
Differentially Private Stochastic Coordinate Descent
G.Damaskinos, C.Mendler-Dünner, R.Guerraoui, N.Papandreou and T.Parnell
Workshop on Privacy Preserving ML (PPML@NeurIPS), 2020.
Breadth-first, Depth-next Training of Random Forests
A.Anghel*, N.Ioannou*, T.Parnell, N.Papandreou, C.Mendler-Dünner and H.Pozidis
Workshop on Systems for ML (MLSys@NeurIPS), 2019.
Snap ML
C.Mendler-Dünner and A.Anghel
Women in Machine Learning Workshop (WiML@NeurIPS), 2018.
Sampling Acquisition Functions for Batch Bayesian Optimization
A.De Palma, C.Mendler-Dünner, T.Parnell, A.Anghel and H.Pozidis
Workshop on Bayesian Nonparametrics (BNP@NeurIPS), 2018.
Parallel training of linear models without compromising convergence
N.Ioannou, C.Mendler-Dünner, K.Kourtis, T.Parnell
Workshop on Systems for ML (MLSys@NeurIPS), 2018.
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), 2017.