105 citations · 195 across the 2 of their papers we have counts for
3 papers
Black-Box Optimization with Local Generative Surrogates
Sergey Shirobokov, Vladislav Belavin, Michael Kagan +2
We propose a novel method for gradient-based optimization of black-box simulators using differentiable local surrogate models. In fields such as physics and engineering, many proce…
Continual Learning via Neural Pruning
Siavash Golkar, Michael Kagan, Kyunghyun Cho
We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method,…
Multivariate discrimination and the Higgs + W/Z search
Kevin Black, Jason Gallicchio, John Huth +3
A systematic method for optimizing multivariate discriminants is developed and applied to the important example of a light Higgs boson search at the Tevatron and the LHC. The Signi…