Portrait of Thomas George is unavailable

Thomas George

Alumni

Publications

Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty
Thomas George
Guillaume Lajoie
Aristide Baratin
Among attempts at giving a theoretical account of the success of deep neural networks, a recent line of work has identified a so-called `laz… (see more)y' training regime in which the network can be well approximated by its linearization around initialization. Here we investigate the comparative effect of the lazy (linear) and feature learning (non-linear) regimes on subgroups of examples based on their difficulty. Specifically, we show that easier examples are given more weight in feature learning mode, resulting in faster training compared to more difficult ones. In other words, the non-linear dynamics tends to sequentialize the learning of examples of increasing difficulty. We illustrate this phenomenon across different ways to quantify example difficulty, including c-score, label noise, and in the presence of easy-to-learn spurious correlations. Our results reveal a new understanding of how deep networks prioritize resources across example difficulty.
2022-01-01
Trans. Mach. Learn. Res. (published)
doi.org
openreview.net
Continual Learning in Deep Networks: an Analysis of the Last Layer
Timothee LESORT
Thomas George
Irina Rish
We study how different output layers in a deep neural network learn and forget in continual learning settings. The following three factors… (see more) can affect catastrophic forgetting in the output layer: (1) weights modifications, (2) interference, and (3) projection drift. In this paper, our goal is to provide more insights into how changing the output layers may address (1) and (2). Some potential solutions to those issues are proposed and evaluated here in several continual learning scenarios. We show that the best-performing type of the output layer depends on the data distribution drifts and/or the amount of data available. In particular, in some cases where a standard linear layer would fail, it turns out that changing parameterization is sufficient in order to achieve a significantly better performance, whithout introducing a continual-learning algorithm and instead using the standard SGD to train a model. Our analysis and results shed light on the dynamics of the output layer in continual learning scenarios, and suggest a way of selecting the best type of output layer for a given scenario.
2021-06-03
ArXiv (preprint)
openreview.net
openreview.net
Implicit Regularization in Deep Learning: A View from Function Space
Aristide Baratin
Thomas George
César Laurent
(Rex) Devon Hjelm
Guillaume Lajoie
Pascal Vincent
Simon Lacoste-Julien
2020-08-03
ArXiv (preprint)
arxiv.org
arxiv.org
Implicit Regularization in Deep Learning: A View from Function Space
Aristide Baratin
Thomas George
César Laurent
(Rex) Devon Hjelm
Guillaume Lajoie
Pascal Vincent
Simon Lacoste-Julien
We approach the problem of implicit regularization in deep learning from a geometrical viewpoint. We highlight a possible regularization eff… (see more)ect induced by a dynamical alignment of the neural tangent features introduced by Jacot et al, along a small number of task-relevant directions. By extrapolating a new analysis of Rademacher complexity bounds in linear models, we propose and study a new heuristic complexity measure for neural networks which captures this phenomenon, in terms of sequences of tangent kernel classes along in the learning trajectories.
2020-08-03
ArXiv (preprint)
arxiv.org
arxiv.org