Regret bounded by gradual variation for online convex optimization

By Tianbao Yang, Mehrdad Mahdavi, Rong Jin, Shenghuo Zhu. 2014

32 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ji Liu
2. Xiangru Lian
3. Rong Jin
4. Tianbao Yang
5. Yijun Huang
6. Yuncheng Li
7. Lijun Zhang
8. Jinfeng Yi

In Computer Networks and Communications

1. Xiangru Lian
2. Ji Liu
3. Rong Jin
4. Lijun Zhang
5. Yuncheng Li
6. Jinfeng Yi
7. Tianbao Yang
8. Yijun Huang

In Management Science and Operations Research

1. Ji Liu
2. Rong Jin
3. Lijun Zhang
4. Yuncheng Li
5. Jinfeng Yi
6. Xiangru Lian
7. Tianbao Yang
8. Yijun Huang

Citations in the corpus

• Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization (2015, methodology): “[Xiao, 2009]. The stochastic gradient is also closely related to online learning algorithms. Please refer to the online learning literatures, for example, [Crammer et al., 2006, Shalev-Shwartz, 2011, Yang et al., 2014]. Most studies for stochastic gradient focus on convex optimization. For nonconvex”
• Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient (2016, background): “…variation that measures point-wise difference between loss functions is the gradient variation introduced in (Chiang et al., 2012), which is defined as (5) The gradient variation has been explored for bounding the static regret (Chiang et al., 2012; Rakhlin & Sridharan, 2013; Yang et al., 2014).”