Robuta

https://openreview.net/forum?id=SJlHwkBYDH Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks | OpenReview We proposed a Nesterov Iterative Fast Gradient Sign Method (NI-FGSM) and a Scale-Invariant attack Method (SIM) that can boost the transferability of... nesterov accelerated gradient and scale adversarial attacks invariance openreview https://openreview.net/forum?id=-OfK_B9Q5hI Improving Neural Ordinary Differential Equations with Nesterov's Accelerated Gradient Method |... We propose the Nesterov neural ordinary differential equations (NesterovNODEs) whose layers solve the second-order ordinary differential equations limit of... differential equations improving neural ordinary https://openreview.net/forum?id=o66yu12PXa Accelerated Policy Gradient: On the Nesterov Momentum for Reinforcement Learning | OpenReview Policy gradient methods have recently been shown to enjoy global convergence at a $\Theta(1/t)$ rate in the non-regularized tabular softmax setting.... policy gradient on the reinforcement learning accelerated