SGD is well-known for large-scale optimization. In my mind, there are two (and only two) fundamental improvements since the original introduction of SGD: (1) variance reduction, and (2) acceleration. In this guest post at Princeton’s OptiML group, I’d love to conduct a survey regarding (1), and I’d like to especially thank those ICML’16 participants who pushed me to write this post🙂

### Blogroll

### Archives

- July 2016 (2)
- June 2016 (3)
- May 2016 (1)
- June 2012 (3)
- May 2012 (1)
- May 2011 (1)
- March 2011 (1)
- January 2011 (5)
- December 2010 (2)
- November 2010 (2)

### Categories

- Readings (13)
- Research (20)
- Algorithm (8)
- Cryptogaphy (2)
- Game Theory (1)
- Learning Theory (6)
- Optimization (6)

- Story (2)