Energy
Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices
Training deep neural networks on large datasets can often be accelerated by using multiple compute nodes.
FUSE: Fast Unified Simulation and Estimation for PDEs
Parametric PDEs consider different system conditions as well as an underlying solution operator characterized by a set of finite-dimensional parameters.
Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks
Designing efficient exploration is central to Reinforcement Learning due to the fundamental problem posed by the exploration-exploitation dilemma.
A Prototype-Oriented Framework for Unsupervised Domain Adaptation: Appendix
Since it is difficult to directly optimize the marginal likelihood due to the sum inside the log function, we resort to the Expectation-Maximization (EM) algorithm, where we iterate between the expectation and maximization steps. In practice, we draw a mini-batch of size M to estimate this quantity. In other words, we assign each data point to its closest centroid. We report the average accuracy from three independent runs. We do not perform any additional hyper-parameter searches.
