Activity

The Machine Learning Group investigates the development of novel machine learning methods with a particular interest for their algorithmic cost and sample efficiency.

It was created in July 2020, and parts of its activities are conducted with research assistants from the former Machine Learning group at the Idiap Research Institute and the EPFL.

Recent publications

A. Vyas, A. Katharopoulos, and F. Fleuret. Fast Transformers with Clustered Attention. In Proceedings of the international conference on Neural Information Processing Systems (NeurIPS), 2020. (to appear). bib · pdf

V. Micheli, M. d'Hoffschmidt, and F. Fleuret. On the importance of pre-training data volume for compact language models. In Proceedings of the international Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7853–7858, 2020. bib · pdf

E. Courdier and F. Fleuret. Real-Time Segmentation Networks should be Latency Aware. In Proceedings of the Asian Conference on Computer Vision (ACCV), 2020. (to appear). bib · pdf

T. Prabhu, F. Mai, T. Vogels, M. Jaggi, and F. Fleuret. Optimizer Benchmarking Needs to Account for Hyperparameter Tuning. In Proceedings of the International Conference on Machine Learning (ICML), pages 8837–8846, 2020. bib · pdf

A. Katharopoulos, A. Vyas, N. Pappas, and F. Fleuret. Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention. In Proceedings of the International Conference on Machine Learning (ICML), pages 5294–5303, 2020. bib · pdf