| 2025 | AISTATS | Spectral Differential Network Analysis for High-Dimensional Time Series. | Michael Hellstern, Byol Kim, Zad Harchaoui, Ali Shojaie |
| 2025 | ICML | A Generalization Theory for Zero-Shot Prediction. | Ronak Mehta, Zad Harchaoui |
| 2024 | EMNLP | StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements. | Jillian Fisher, Skyler Hallinan, Ximing Lu, Mitchell L. Gordon, Zad Harchaoui, Yejin Choi |
| 2024 | ICASSP | The Rao, Wald, And Likelihood-Ratio Tests under Generalized Self-Concordance. | Lang Liu, Zad Harchaoui |
| 2024 | ICLR | Distributionally Robust Optimization with Bias and Variance Reduction. | Ronak Mehta, Vincent Roulet, Krishna Pillutla, Zad Harchaoui |
| 2024 | NAACL | JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models. | Jillian Fisher, Ximing Lu, Jaehun Jung, Liwei Jiang, Zad Harchaoui, Yejin Choi |
| 2023 | AISTATS | Influence Diagnostics under Self-concordance. | Jillian Fisher, Lang Liu, Krishna Pillutla, Yejin Choi, Zad Harchaoui |
| 2023 | AISTATS | Stochastic Optimization for Spectral Risk Measures. | Ronak Mehta, Vincent Roulet, Krishna Pillutla, Lang Liu, Zad Harchaoui |
| 2022 | AISTATS | Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates. | Nicholas J. Irons, Meyer Scetbon, Soumik Pal, Zad Harchaoui |
| 2022 | AISTATS | Entropy Regularized Optimal Transport Independence Criterion. | Lang Liu, Soumik Pal, Zad Harchaoui |
| 2022 | COLT | Orthogonal Statistical Learning with Self-Concordant Loss. | Lang Liu, Carlos Cinelli, Zad Harchaoui |
| 2022 | ICASSP | Differentiable Programming A La Moreau. | Vincent Roulet, Zad Harchaoui |
| 2021 | AISTATS | A Spectral Analysis of Dot-product Kernels. | Meyer Scetbon, Zad Harchaoui |
| 2021 | CISS | A Superquantile Approach to Federated Learning with Heterogeneous Devices. | Yassine Laguel, Krishna Pillutla, Jrme Malick, Zad Harchaoui |
| 2021 | CISS | On the Smoothing of Deep Networks. | Vincent Roulet, Zad Harchaoui |
| 2021 | ICASSP | Score-Based Change Detection For Gradient-Based Learning Machines. | Lang Liu, Joseph Salmon, Zad Harchaoui |
| 2020 | ICML | Harmonic Decompositions of Convolutional Networks. | Meyer Scetbon, Zad Harchaoui |
| 2019 | CVPR | Object Discovery in Videos as Foreground Motion Clustering. | Christopher Xie, Yu Xiang, Zad Harchaoui, Dieter Fox |
| 2019 | ICML | A Statistical Investigation of Long Memory in Language and Music. | Alexander Greaves-Tunnell, Zad Harchaoui |
| 2019 | ICML | Iterative Linearized Control: Stable Algorithms and Complexity Guarantees. | Vincent Roulet, Dmitriy Drusvyatskiy, Siddhartha S. Srinivasa, Zad Harchaoui |
| 2019 | ICRA | A Simple Adaptive Tracker with Reminiscences. | Christopher Xie, Emily B. Fox, Zad Harchaoui |
| 2018 | AISTATS | Catalyst for Gradient-based Nonconvex Optimization. | Courtney Paquette, Hongzhou Lin, Dmitriy Drusvyatskiy, Julien Mairal, Zad Harchaoui |
| 2018 | ICASSP | Invariances and Data Augmentation for Supervised Music Transcription. | John Thickstun, Zad Harchaoui, Dean P. Foster, Sham M. Kakade |
| 2018 | ICML | Efficient First-Order Algorithms for Adaptive Signal Denoising. | Dmitrii Ostrovskii, Zad Harchaoui |
| 2018 | IJCAI | Rademacher Complexity Bounds for a Penalized Multi-class Semi-supervised Algorithm (Extended Abstract). | Yury Maximov, Massih-Reza Amini, Zad Harchaoui |
| 2017 | ICASSP | The group k-support norm for learning with structured sparsity. | Nikhil Rao, Miroslav Dudk, Zad Harchaoui |
| 2017 | ICLR | Learning Features of Music From Scratch. | John Thickstun, Zad Harchaoui, Sham M. Kakade |
| 2015 | COLT | Adaptive Recovery of Signals by Convex Optimization. | Zad Harchaoui, Anatoli B. Juditsky, Arkadi Nemirovski, Dmitry Ostrovsky |
| 2015 | CVPR | EpicFlow: Edge-preserving interpolation of correspondences for optical flow. | Jrme Revaud, Philippe Weinzaepfel, Zad Harchaoui, Cordelia Schmid |
| 2015 | CVPR | Learning to detect Motion Boundaries. | Philippe Weinzaepfel, Jrme Revaud, Zad Harchaoui, Cordelia Schmid |
| 2015 | ICCV | Local Convolutional Features with Unsupervised Training for Image Retrieval. | Mattis Paulin, Matthijs Douze, Zad Harchaoui, Julien Mairal, Florent Perronnin, Cordelia Schmid |
| 2015 | ICCV | Learning to Track for Spatio-Temporal Action Localization. | Philippe Weinzaepfel, Zad Harchaoui, Cordelia Schmid |
| 2014 | CVPR | Fast and Robust Archetypal Analysis for Representation Learning. | Yuansi Chen, Julien Mairal, Zad Harchaoui |
| 2014 | CVPR | Transformation Pursuit for Image Classification. | Mattis Paulin, Jrme Revaud, Zad Harchaoui, Florent Perronnin, Cordelia Schmid |
| 2014 | ECCV | Category-Specific Video Summarization. | Danila Potapov, Matthijs Douze, Zad Harchaoui, Cordelia Schmid |
| 2014 | ICML | On learning to localize objects with minimal supervision. | Hyun Oh Song, Ross B. Girshick, Stefanie Jegelka, Julien Mairal, Zad Harchaoui, Trevor Darrell |
| 2013 | CVPR | Label-Embedding for Attribute-Based Classification. | Zeynep Akata, Florent Perronnin, Zad Harchaoui, Cordelia Schmid |
| 2013 | ICCV | DeepFlow: Large Displacement Optical Flow with Deep Matching. | Philippe Weinzaepfel, Jrme Revaud, Zad Harchaoui, Cordelia Schmid |
| 2012 | BMVC | Recognizing activities with cluster-trees of tracklets. | Adrien Gaidon, Zad Harchaoui, Cordelia Schmid |
| 2012 | CVPR | Large-scale image classification with trace-norm regularization. | Zad Harchaoui, Matthijs Douze, Mattis Paulin, Miroslav Dudk, Jrme Malick |
| 2012 | CVPR | Towards good practice in large-scale learning for image classification. | Florent Perronnin, Zeynep Akata, Zad Harchaoui, Cordelia Schmid |
| 2011 | BMVC | A time series kernel for action recognition. | Adrien Gaidon, Zad Harchaoui, Cordelia Schmid |
| 2011 | CVPR | Actom sequence models for efficient action detection. | Adrien Gaidon, Zad Harchaoui, Cordelia Schmid |
| 2009 | ICASSP | A regularized kernel-based approach to unsupervised audio segmentation. | Zad Harchaoui, Flicien Vallet, Alexandre Lung-Yut-Fong, Olivier Capp |
| 2007 | CVPR | Image Classification with Segmentation Graph Kernels. | Zad Harchaoui, Francis R. Bach |