47 citations · 272 across the 43 of their papers we have counts for
5 papers · 1 filter
Quarks to Cosmos: Particles and Plasma in Cosmological evolution
Johann Rafelski, Jeremiah Birrell, Christopher Grayson +2
We describe in the context of the particle physics (PP) standard model (SM) `PP-SM' the understanding of the primordial properties and composition of the Universe in the temperatur…
Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
Jeremiah Birrell, Reza Ebrahimi, Rouzbeh Behnia +1
Differentially private stochastic gradient descent (DP-SGD) has been instrumental in privately training deep learning models by providing a framework to control and track the priva…
Fermi-Dirac Integrals in Degenerate Regimes: A Novel Asymptotic Expansion
Jeremiah Birrell, Martin Formanek, Andrew Steinmetz +2
We characterize in a novel manner the physical properties of the low temperature Fermi gas in the degenerate domain as a function of temperature and chemical potential. For the fir…
Statistical Error Bounds for GANs with Nonlinear Objective Functionals
Jeremiah Birrell
Generative adversarial networks (GANs) are unsupervised learning methods for training a generator distribution to produce samples that approximate those drawn from a target distrib…
Nonlinear denoising score matching for enhanced learning of structured distributions
Jeremiah Birrell, Markos A. Katsoulakis, Luc Rey-Bellet +2
We present a novel method for training score-based generative models which uses nonlinear noising dynamics to improve learning of structured distributions. Generalizing to a nonlin…