no code implementations • 19 Aug 2020 • Xu Qian, Victor Li, Crews Darren
Recent paper proposes to use Hessian traces of weights and activations for mixed-precision quantization and achieves state-of-the-art results.
no code implementations • 24 Jan 2019 • Xu Qian, Zheng Qu, Peter Richtárik
We study the problem of minimizing the average of a very large number of smooth functions, which is of key importance in training supervised learning models.