VENIAT Tom

PhD graduated
Team : MLIA
Departure date : 07/01/2017
https://lip6.fr/Tom.Veniat

Supervision : Ludovic DENOYER

Co-supervision : RANZATO Marc'Aurelio

Neural Architecture Search under Budget Constraints

The recent increase in computing power and amount of data available has catalyzed the rise in popularity of deep learning algorithms. However, these two factors combined with the memory and energy footprint of these algorithms, their latency as well as the expertise required to build them are all obstacles preventing their use in a larger number of applications. In this thesis, we propose several methods to build the architecture of deep learning models in a more efficient and automated way.
First, we focus on learning efficient architectures for image processing. We propose a new method in which the user can guide the learning procedure by specifying a cost function and a maximum budget to be respected during inference. This budget can take various forms, "less than 200ms per image on this mobile device" for example. Our method then automatically learns a model and its architecture by jointly optimizing the predictive performance and the cost function specified by the user. Next, we consider the problem of sequence classification, where a model can be made even more efficient by dynamically adapting its size to the complexity of the signal to be processed. We show that both approaches result in significant budget savings over a range of cost functions and classes of model. Finally, we address the efficiency problem through the lens of transfer learning. A learning procedure can be made even more efficient if, instead of starting tabula rasa, it builds on the knowledge gained from previous experiments. We present a new evaluation protocol that allows a fine-grained analysis of the different types of transfer and show that our neural architecture search approach is able to beat existing methods on most of these dimensions.

Defence : 07/01/2021 - 16h - Campus Jussieu, salle Jacques Pitrat (25-26/105) - https://youtu.be/GJwfOHu6k4A

Jury members :

M. Francois Fleuret, Université de Genève - MLG [Rapporteur]
M. Jakob Verbeek, Facebook - FAIR [Rapporteur]
M. Patrick Gallinari, Sorbonne Université - MLIA
Mme. Raia Hasdell, DeepMind
M. Vincenzo Lomonaco, Université de Pise - PAILab
M. Ludovic Denoyer, Facebook - FAIR
M. Marc'Aurelio Ranzato, Facebook - FAIR

2018-2021 Publications