105 citations · 343 across the 11 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2020
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…
cs.LG2019★ 90 cited
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,…