World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
46
Citations
17386
World Ranking
6661
National Ranking
2943

Overview

Zaid Harchaoui is affiliated with the University of Washington in the United States. Their research primarily spans the field of Computer Science, with 83 publications contributing to this area. Within this broad domain, their work focuses on several specialized subfields including Artificial Intelligence, Statistics and Probability, Computer Vision and Pattern Recognition, Control and Systems Engineering, and Computational Mechanics.

The scientist's research topics encompass a variety of technical and methodological areas. These topics include Stochastic Gradient Optimization Techniques, Statistical Methods and Inference, Sparse and Compressive Sensing Techniques, Topic Modeling, Natural Language Processing Techniques, Neural Networks and Applications, and Privacy-Preserving Technologies in Data.

Zaid Harchaoui has published extensively in numerous venues, with frequent contributions to arXiv (Cornell University), where they have 41 publications. Other venues include bioRxiv (Cold Spring Harbor Laboratory) with 5 publications, Foundations and Trends® in Machine Learning, IEEE Transactions on Signal Processing, and Nature Ecology & Evolution.

Their list of recent papers highlights a range of topics and collaborations:

  • Advances and Open Problems in Federated Learning, 2020, Foundations and Trends® in Machine Learning
  • MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers, 2021, arXiv (Cornell University)
  • Robust Aggregation for Federated Learning, 2022, IEEE Transactions on Signal Processing
  • Faith and Fate: Limits of Transformers on Compositionality, 2023, arXiv (Cornell University)
  • MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers, 2021, arXiv (Cornell University)

Zaid Harchaoui collaborates frequently with several researchers, including Krishna Pillutla, Vincent Roulet, Lang Liu, Yejin Choi, and Ronak Mehta. These collaborations have contributed to a diversity of research outputs across their fields of study.

Best Publications

  • Advances and Open Problems in Federated Learning

    Peter Kairouz;H. Brendan McMahan;Brendan Avent;Aurélien Bellet

  • DeepFlow: Large Displacement Optical Flow with Deep Matching

    Philippe Weinzaepfel;Jerome Revaud;Zaid Harchaoui;Cordelia Schmid

  • Advances and open problems in federated learning

    Peter Kairouz;H. Brendan McMahan;Brendan Avent;Aurélien Bellet

  • EpicFlow: Edge-preserving interpolation of correspondences for optical flow

    Jerome Revaud;Philippe Weinzaepfel;Zaid Harchaoui;Cordelia Schmid

  • Label-Embedding for Image Classification

    Zeynep Akata;Florent Perronnin;Zaid Harchaoui;Cordelia Schmid

  • Label-Embedding for Attribute-Based Classification

    Zeynep Akata;Florent Perronnin;Zaid Harchaoui;Cordelia Schmid

  • Category-Specific Video Summarization

    Danila Potapov;Matthijs Douze;Zaid Harchaoui;Cordelia Schmid

  • A universal catalyst for first-order optimization

    Hongzhou Lin;Julien Mairal;Zaid Harchaoui

  • Convolutional Kernel Networks

    Julien Mairal;Piotr Koniusz;Zaid Harchaoui;Cordelia Schmid

  • Multiple Change-Point Estimation With a Total Variation Penalty

    Zaid Harchaoui;Céline Lévy-Leduc

  • Learning to Track for Spatio-Temporal Action Localization

    Philippe Weinzaepfel;Zaid Harchaoui;Cordelia Schmid

  • Image Classification with Segmentation Graph Kernels

    Z. Harchaoui;F. Bach

  • DeepMatching: Hierarchical Deformable Dense Matching

    Jerome Revaud;Philippe Weinzaepfel;Zaid Harchaoui;Cordelia Schmid

  • Temporal Localization of Actions with Actoms

    A. Gaidon;Z. Harchaoui;C. Schmid

  • On learning to localize objects with minimal supervision

    Hyun Oh Song;Ross Girshick;Stefanie Jegelka;Julien Mairal

  • A Fast, Consistent Kernel Two-Sample Test

    Arthur Gretton;Kenji Fukumizu;Zaïd Harchaoui;Bharath K. Sriperumbudur

  • Actom sequence models for efficient action detection

    Adrien Gaidon;Zaid Harchaoui;Cordelia Schmid

  • Local Convolutional Features with Unsupervised Training for Image Retrieval

    Mattis Paulin;Matthijs Douze;Zaid Harchaoui;Julien Mairal

  • Conditional gradient algorithms for norm-regularized smooth convex optimization

    Zaid Harchaoui;Anatoli Juditsky;Arkadi Nemirovski

  • Good Practice in Large-Scale Learning for Image Classification

    Zeynep Akata;Florent Perronnin;Zaid Harchaoui;Cordelia Schmid

  • Robust Aggregation for Federated Learning

    Krishna Pillutla;Sham M. Kakade;Zaid Harchaoui

Frequent Co-Authors

Cordelia Schmid
Cordelia Schmid French Institute for Research in Computer Science and Automation - INRIA
Julien Mairal
Julien Mairal French Institute for Research in Computer Science and Automation - INRIA
Matthijs Douze
Matthijs Douze Facebook (United States)
Sham M. Kakade
Sham M. Kakade Harvard University
Francis Bach
Francis Bach École Normale Supérieure
Arkadi Nemirovski
Arkadi Nemirovski Georgia Institute of Technology
Adrien Gaidon
Adrien Gaidon Stanford University
Zeynep Akata
Zeynep Akata University of Tübingen
Siddhartha S. Srinivasa
Siddhartha S. Srinivasa University of Washington

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online degrees expands your options for a career in computer science and related fields. If you are seeking a fast-track entry into the tech sector, you may want to consider what is the easiest associate's degree to get. Associate degrees can provide a solid foundation in computing and allow for quicker transitions into the workforce or further study.

For those interested in advancing their expertise, degrees such as an ed d in education can open doors to leadership roles, curriculum development, or academic positions, bridging the gap between technology and education.

Selecting the right institution is crucial. Choosing the most respected online university can enhance your credentials and ensure recognition by employers nationwide.

If your passion is technology and creativity, you may want to consider a specialized pathway with a game development degree. This field blends programming, art, and design, leading to exciting opportunities in the gaming industry.

Best Scientists Citing Zaid Harchaoui

Trending Scientists