Three Mechanisms of Feature Learning in the Exact Solution of a Latent Variable Model
We identify and exactly solve the learning dynamics of a one-hidden-layer linear model at any finite width whose limits exhibit both the kernel phase and the feature learning phase. We analyze the phase diagram of this model in different limits of common hyperparameters including width, layer-wise learning rates, scale of output, and scale of initialization. Our solution identifies three novel prototype mechanisms of feature learning: (1) learning by alignment, (2) learning by disalignment, and (3) learning by rescaling. In sharp contrast, none of these mechanisms is present in the kernel regime of the model. We empirically demonstrate that these discoveries also appear in deep nonlinear networks in real tasks.
PDF AbstractTasks
Datasets
Add Datasets
introduced or used in this paper
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
No methods listed for this paper. Add
relevant methods here
