no code implementations • 24 Aug 2023 • Helen Zhou, Sercan O. Arik, Jingtao Wang
We explore a wide range of plausible cost trade-off scenarios, and empirically demonstrate that end-to-end optimization often outperforms optimization of standard business-agnostic forecasting metrics (by up to 45. 7% for a simple scaling model, and up to 54. 0% for an LSTM encoder-decoder model).
no code implementations • ICCV 2023 • Jingtao Wang, Zengjie Song, Yuxi Wang, Jun Xiao, Yuran Yang, Shuqi Mei, Zhaoxiang Zhang
Surrogate gradient (SG) is one of the most effective approaches for training spiking neural networks (SNNs).
no code implementations • 16 Jun 2019 • Qingpeng Cai, Will Hang, Azalia Mirhoseini, George Tucker, Jingtao Wang, Wei Wei
In this paper, we introduce a novel framework to generate better initial solutions for heuristic algorithms using reinforcement learning (RL), named RLHO.