1 citations · 3 across the 4 of their papers we have counts for
3 papers · 1 filter
Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
Mohamed Elsayed, Homayoon Farrahi, Felix Dangel +1
Second-order information is valuable for many applications but challenging to compute. Several works focus on computing or approximating Hessian diagonals, but even this simplifica…
Weight Clipping for Deep Continual and Reinforcement Learning
Mohamed Elsayed, Qingfeng Lan, Clare Lyle +1
Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting.…
Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning
Mohamed Elsayed, A. Rupam Mahmood
Modern representation learning methods often struggle to adapt quickly under non-stationarity because they suffer from catastrophic forgetting and decaying plasticity. Such problem…