Yan Liu
Yan Liu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Maojun Zhang
School of Systems Engineering, National University of Defense Technology, Changsha 410073, China
1 shared publication- Maojun Zhang
National University of Defense Technology
1 shared publication - Na Zhao
Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore, Singapore
1 shared publication - Rouwan Wu
College of Systems and Engineering, National University of Defense Technology, Changsha, China
1 shared publication - Shen Yan
National University of Defense Technology
1 shared publication - Xiangrong Zeng
College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
1 shared publication
Latest Publications
- 2 October 2026
- Published by Springer Nature
- p. 656-674
AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision
- 2 October 2026
- Published by Springer Nature
- p. 656-674
AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision
- Open Access
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1)
AdaCN: An Adaptive Cubic Newton Method for Nonconvex Stochastic Optimization
In this work, we introduce AdaCN, a novel adaptive cubic Newton method for nonconvex stochastic optimization. AdaCN dynamically captures the curvature of the loss landscape by diagonally approximated Hessian plus the norm of difference between previous two estimates. It only requires at most first order gradients and updates with linear complexity for both time and memory. In order to reduce the variance introduced by the stochastic nature of the problem, AdaCN hires the first and second moment to implement and exponential moving average on iteratively updated stochastic gradients and approximated stochastic Hessians, respectively. We validate AdaCN in extensive experiments, showing that it outperforms other stochastic first order methods (including SGD, Adam, and AdaBound) and stochastic quasi‐Newton method (i.e., Apollo), in terms of both convergence speed and generalization performance.
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1)
Open AccessAdaCN: An Adaptive Cubic Newton Method for Nonconvex Stochastic Optimization
In this work, we introduce AdaCN, a novel adaptive cubic Newton method for nonconvex stochastic optimization. AdaCN dynamically captures the curvature of the loss landscape by diagonally approximated Hessian plus the norm of difference between previous two estimates. It only requires at most first order gradients and updates with linear complexity for both time and memory. In order to reduce the variance introduced by the stochastic nature of the problem, AdaCN hires the first and second moment to implement and exponential moving average on iteratively updated stochastic gradients and approximated stochastic Hessians, respectively. We validate AdaCN in extensive experiments, showing that it outperforms other stochastic first order methods (including SGD, Adam, and AdaBound) and stochastic quasi‐Newton method (i.e., Apollo), in terms of both convergence speed and generalization performance.