REVIEW 2 cited by
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
Despite the practical success of deep neural networks, a comprehensive theoretical framework that can predict practically relevant scores, such as the test accuracy, from knowledge of the training data is currently lacking. Huge simplifications arise in the infinite-width limit, where the number of units $N_\ell$ in each hidden layer ($\ell=1,\dots, L$, being $L$ the depth of the network) far exceeds the number $P$ of training examples. This idealisation, however, blatantly departs from the reality of deep learning practice. Here, we use the toolset of statistical mechanics to overcome these limitations and derive an approximate partition function for fully-connected deep neural architectures, which encodes information about the trained models. The computation holds in the ''thermodynamic limit'' where both $N_\ell$ and $P$ are large and their ratio $\alpha_\ell = P/N_\ell$ is finite. This advance allows us to obtain (i) a closed formula for the generalisation error associated to a regression task in a one-hidden layer network with finite $\alpha_1$; (ii) an approximate expression of the partition function for deep architectures (via an ''effective action'' that depends on a finite number of ''order parameters''); (iii) a link between deep neural networks in the proportional asymptotic limit and Student's $t$ processes.
Forward citations
Cited by 2 Pith papers
-
Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation
A replica/HCIZ theory predicts the Bayes-optimal generalization error of proportional-width MLPs near interpolation and discovers layer-wise specialization transitions that make deeper targets harder to learn.
-
Variational Bounds for Perceptron Learning from Structured Data
A variational potential gives both a lower and an upper bound on the quenched pressure of a perceptron, with matching supported numerically for logistic-type losses.
Discussion (0). Continue with ORCID to comment.