Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian

by   Samet Oymak, et al.

Modern neural network architectures often generalize well despite containing many more parameters than the size of the training dataset. This paper explores the generalization capabilities of neural networks trained via gradient descent. We develop a data-dependent optimization and generalization theory which leverages the low-rank structure of the Jacobian matrix associated with the network. Our results help demystify why training and generalization is easier on clean and structured datasets and harder on noisy and unstructured datasets as well as how the network size affects the evolution of the train and test errors during training. Specifically, we use a control knob to split the Jacobian spectum into "information" and "nuisance" spaces associated with the large and small singular values. We show that over the information space learning is fast and one can quickly train a model with zero training loss that can also generalize well. Over the nuisance space training is slower and early stopping can help with generalization at the expense of some bias. We also show that the overall generalization capability of the network is controlled by how well the label vector is aligned with the information space. A key feature of our results is that even constant width neural nets can provably generalize for sufficiently nice datasets. We conduct various numerical experiments on deep networks that corroborate our theoretical findings and demonstrate that: (i) the Jacobian of typical neural networks exhibit low-rank structure with a few large singular values and many small ones leading to a low-dimensional information space, (ii) over the information space learning is fast and most of the label vector falls on this space, and (iii) label noise falls on the nuisance space and impedes optimization/generalization.


Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks

The skip-connections used in residual networks have become a standard ar...

The Low-Rank Simplicity Bias in Deep Networks

Modern deep neural networks are highly over-parameterized compared to th...

Coresets for Robust Training of Neural Networks against Noisy Labels

Modern neural networks have the capacity to overfit noisy labels frequen...

Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks

Modern neural networks are typically trained in an over-parameterized re...

When Does Preconditioning Help or Hurt Generalization?

While second order optimizers such as natural gradient descent (NGD) oft...

Simultaneous Training of Partially Masked Neural Networks

For deploying deep learning models to lower end devices, it is necessary...

Please sign up or login with your details

Forgot password? Click here to reset