1 code implementation • 3 Aug 2022 • Hailiang Liu, Xuping Tian
In this paper, we propose SGEM, Stochastic Gradient with Energy and Momentum, to solve a large class of general non-convex stochastic optimization problems, based on the AEGD method that originated in the work [AEGD: Adaptive Gradient Descent with Energy.
1 code implementation • 23 Mar 2022 • Hailiang Liu, Xuping Tian
We introduce a novel algorithm for gradient-based optimization of stochastic objective functions.
no code implementations • ICLR 2022 • Tianxiang Gao, Hailiang Liu, Jia Liu, Hridesh Rajan, Hongyang Gao
Implicit deep learning has received increasing attention recently due to the fact that it generalizes the recursive prediction rules of many commonly used neural network architectures.
no code implementations • 29 Sep 2021 • Hailiang Liu, Xuping Tian
In this paper, we propose SGDEM, Stochastic Gradient Descent with Energy and Momentum to solve a large class of general nonconvex stochastic optimization problems, based on the AEGD method that originated in the work [AEGD: Adaptive Gradient Descent with Energy.
1 code implementation • 10 Oct 2020 • Hailiang Liu, Xuping Tian
We propose AEGD, a new algorithm for first-order gradient-based optimization of non-convex objective functions, based on a dynamically updated energy variable.