7 citations · 17 across the 9 of their papers we have counts for
10 papers
Lightweight Probabilistic Downscaling from a Deterministic Base Model
Joseph McLean, Tiffany Vlaar, Sigrid Passano Hellan +1
Climate data downscaling is the task of increasing the spatial resolution of climate data, typically by generating fine-resolution regional climate data from coarse global model ou…
Camera trap classification with deep learning under ground truth uncertainty
Leonard Hockerts, Peter S. Stewart, Sarthak Arora +1
Supervised deep learning methods enable the rapid processing of ecological image data, but depend on a costly annotation process. Consequently, training labels are commonly derived…
Could Model Partitioning Make Federated Learning More Sustainable?
Tobias Frohlich, Tiffany Vlaar, Lauritz Thamsen
As federated learning (FL) extends from distributed machine learning between low-power devices to cross-silo scenarios involving edge servers and data centres, its carbon footprint…
Normalization Layers Are All That Sharpness-Aware Minimization Needs
Maximilian Mueller, Tiffany Vlaar, David Rolnick +1
Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in various settings. In this work we show tha…
Better Training using Weight-Constrained Stochastic Dynamics
Benedict Leimkuhler, Tiffany Vlaar, Timothée Pouchon +1
We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing…
What can linear interpolation of neural network loss landscapes tell us?
Tiffany Vlaar, Jonathan Frankle
Studying neural network loss landscapes provides insights into the nature of the underlying optimization problems. Unfortunately, loss landscapes are notoriously difficult to visua…
Multirate Training of Neural Networks
Tiffany Vlaar, Benedict Leimkuhler
We propose multirate training of neural networks: partitioning neural network parameters into "fast" and "slow" parts which are trained on different time scales, where slow parts a…
Constraint-Based Regularization of Neural Networks
Benedict Leimkuhler, Timothée Pouchon, Tiffany Vlaar +1
We propose a method for efficiently incorporating constraints into a stochastic gradient Langevin framework for the training of deep neural networks. Constraints allow direct contr…
Partitioned integrators for thermodynamic parameterization of neural networks
Benedict Leimkuhler, Charles Matthews, Tiffany Vlaar
Traditionally, neural networks are parameterized using optimization procedures such as stochastic gradient descent, RMSProp and ADAM. These procedures tend to drive the parameters…
Shape dependence of two-cylinder Renyi entropies for free bosons on a lattice
Leilee Chojnacki, Caleb Q. Cook, Denis Dalidovich +4
Universal scaling terms occurring in Renyi entanglement entropies have the potential to bring new understanding to quantum critical points in free and interacting systems. Quantita…