7 citations · 13 across the 4 of their papers we have counts for
5 papers
Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation
Ahmed Salah, David Yevick
Grokking refers to delayed generalization in which the increase in test accuracy of a neural network occurs appreciably after the improvement in training accuracy This paper introd…
The Accuracy of Restricted Boltzmann Machine Models of Ising Systems
David Yevick, Roger Melko
Restricted Boltzmann machine (RBM) provide a general framework for modeling physical systems, but their behavior is dependent on hyperparameters such as the learning rate, the numb…
Electric Field Propagation Through Singular Value Decomposition
David Yevick
We demonstrate that the singular value decomposition algorithm in conjunction with the fast Fourier transform or finite difference procedures provides a straightforward and accurat…
Renormalized Multicanonical Sampling
David Yevick
For a homogeneous system divisible into identical, weakly interacting subsystems, the muticanonical procedure can be accelerated if it is first applied to determine of the density…
Accelerated rare event sampling
David Yevick
A sampling procedure for the transition matrix Monte Carlo method is introduced that generates the density of states function over a wide parameter range with minimal coding effort…