Timezone: »

 
Poster
Align, then memorise: the dynamics of learning with feedback alignment
Maria Refinetti · Stéphane d'Ascoli · Ruben Ohana · Sebastian Goldt

Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @
in Poster Session 3 »

Direct Feedback Alignment (DFA) is emerging as an efficient and biologically plausible alternative to backpropagation for training deep neural networks. Despite relying on random feedback weights for the backward pass, DFA successfully trains state-of-the-art models such as Transformers. On the other hand, it notoriously fails to train convolutional networks. An understanding of the inner workings of DFA to explain these diverging results remains elusive. Here, we propose a theory of feedback alignment algorithms. We first show that learning in shallow networks proceeds in two steps: an alignment phase, where the model adapts its weights to align the approximate gradient with the true gradient of the loss function, is followed by a memorisation phase, where the model focuses on fitting the data. This two-step process has a degeneracy breaking effect: out of all the low-loss solutions in the landscape, a net-work trained with DFA naturally converges to the solution which maximises gradient alignment. We also identify a key quantity underlying alignment in deep linear networks: the conditioning of the alignment matrices. The latter enables a detailed understanding of the impact of data structure on alignment, and suggests a simple explanation for the well-known failure of DFA to train convolutional neural networks. Numerical experiments on MNIST and CIFAR10 clearly demonstrate degeneracy breaking in deep non-linear networks and show that the align-then-memorize process occurs sequentially from the bottom layers of the network to the top.

Keywords: Models of Learning and Generalization

Author Information

Maria Refinetti (Laboratoire de Physique de l’Ecole Normale Supérieure Paris)
Stéphane d'Ascoli (ENS / FAIR, Paris)
Ruben Ohana (Ecole Normale Supérieure & LightOn)
Sebastian Goldt (International School of Advanced Studies (SISSA))

I'm an assistant professor working on theories of learning in neural networks.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors