Search for: All records

We develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training. By examining the underlying high-dimensional probabilistic models, we reveal that the training process explores an effectively low-dimensional manifold. Networks with a wide range of architectures, sizes, trained using different optimization methods, regularization techniques, data augmentation techniques, and weight initializations lie on the same manifold in the prediction space. We study the details of this manifold to find that networks with different architectures follow distinguishable trajectories, but other factors have a minimal influence; larger networks train along a similar manifold as that of smaller networks, just faster; and networks initialized at very different parts of the prediction space converge to the solution along a similar manifold. 

We develop information geometric techniques to understand the representations learned by deep networks when they are trained on different tasks using supervised, meta-, semi-supervised and con- trastive learning. We shed light on the following phenomena that relate to the structure of the space of tasks: (1) the manifold of probabilistic models trained on different tasks using different represen- tation learning methods is effectively low-dimen- sional; (2) supervised learning on one task results in a surprising amount of progress even on seem- ingly dissimilar tasks; progress on other tasks is larger if the training task has diverse classes; (3) the structure of the space of tasks indicated by our analysis is consistent with parts of the Word- net phylogenetic tree; (4) episodic meta-learning algorithms and supervised learning traverse differ- ent trajectories during training but they fit similar models eventually; (5) contrastive and semi-su- pervised learning methods traverse trajectories similar to those of supervised learning. We use classification tasks constructed from the CIFAR- 10 and Imagenet datasets to study these phenom- ena. Code is available at https://github.com/grasp- lyrl/picture of space of tasks.