Publications

Publications in reversed chronological order.

2025

  1. Fundamental Challenges in Evaluating Text2SQL Solutions and Detecting Their Limitations
    Cedric Renggli, Ihab F Ilyas, and Theodoros Rekatsinas
    arXiv preprint arXiv:2501.18197, 2025
    arXiv

2024

  1. Stochastic gradient descent without full data shuffle: with applications to in-database machine learning and deep learning systems
    Lijie Xu, Shuang Qiu, Binhang Yuan, and 8 more authors
    The VLDB Journal, 2024
    arXiv PDF

2023

  1. Automatic feasibility study via data quality analysis for ml: A case-study on label noise
    Cedric Renggli, Luka Rimanic, Luka Kolar, and 2 more authors
    2023 IEEE 39th International Conference on Data Engineering (ICDE), 2023
    arXiv PDF
  2. Co-design hardware and algorithm for vector search
    Wenqi Jiang, Shigang Li, Yu Zhu, and 8 more authors
    In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2023
    arXiv PDF
  3. DeepSE-WF: Unified Security Estimation for Website Fingerprinting Defenses
    Alexander Veicht, Cedric Renggli, and Diogo Barradas
    Proceedings on Privacy Enhancing Technologies, 2023
    arXiv PDF

2022

  1. Which Model to Transfer? Finding the Needle in the Growing Haystack
    Cedric Renggli, André Susano Pinto, Luka Rimanic, and 4 more authors
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
    arXiv PDF
  2. SHiFT: an efficient, flexible search engine for transfer learning
    Cedric Renggli, Xiaozhe Yao, Luka Kolar, and 3 more authors
    Proceedings of the VLDB Endowment, 2022
    arXiv PDF
  3. Learning to merge tokens in vision transformers
    Cedric Renggli, André Susano Pinto, Neil Houlsby, and 3 more authors
    arXiv preprint arXiv:2202.12015, 2022
    arXiv

2021

  1. A Data Quality-Driven View of MLOps
    Cedric Renggli, Luka Rimanic, Nezihe Merve Gürel, and 3 more authors
    IEEE Data Engineering Bulletin, 2021
    arXiv PDF
  2. Evaluating Bayes Error Estimators on Read-World Datasets with FeeBee
    Cedric Renggli, Luka Rimanic, Nora Hollenstein, and 1 more author
    In Advances in Neural Information Processing Systems (Datasets and Benchmarks), 2021
    arXiv PDF
  3. Scalable Transfer Learning with Expert Models
    Joan Puigcerver, Carlos Riquelme, Basil Mustafa, and 5 more authors
    In International Conference on Learning Representations, 2021
    arXiv

2020

  1. On Convergence of Nearest Neighbor Classifiers over Feature Transformations
    Luka Rimanic, Cedric Renggli, Bo Li, and 1 more author
    In Advances in Neural Information Processing Systems, 2020
    arXiv PDF
  2. Ease.ML/Snoopy in Action: Towards Automatic Feasibility Analysis for Machine Learning Application Development
    Cedric Renggli, Luka Rimanic, Luka Kolar, and 2 more authors
    In Proceedings of the VLDB Endowment, 2020
    PDF
  3. Building continuous integration services for machine learning
    Bojan Karlaš, Matteo Interlandi, Cedric Renggli, and 7 more authors
    In ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020
    PDF

2019

  1. Continuous Integration of Machine Learning Models with ease.ML/CI: Towards a Rigorous Yet Practical Treatment
    Cedric Renggli, Bojan Karlas, Bolin Ding, and 4 more authors
    In SysML Conference, 2019
    arXiv PDF
  2. Ease.ML/CI and Ease.ML/Meter in Action: Towards Data Management for Statistical Generalization
    Cedric Renggli, Frances Ann Hubis, Bojan Karlaš, and 3 more authors
    In Proceedings of the VLDB Endowment, 2019
    PDF
  3. SparCML: High-performance sparse communication for machine learning
    Cèdric Renggli, Saleh Ashkboos, Mehdi Aghagolzadeh, and 2 more authors
    In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2019
    arXiv PDF

2018

  1. The convergence of sparsified gradient methods
    Dan Alistarh, Torsten Hoefler, Mikael Johansson, and 3 more authors
    Advances in Neural Information Processing Systems, 2018
    arXiv PDF