Mates of Costate
There have been four thousand new frameworks for deep learning thrown on the market the past year, and I bet you were wondering what you needed to jump into this hot marketplace. Essentially, there are... Continue
Large Margin Micro Blogging
While intricate deep models are all the rage in machine learning, my last post tried to make the case that we still need to care about model regularization. As it has been since the dawn... Continue
Bottoming Out
In order to get a grasp on what makes optimization difficult in machine learning, it is important to specialize our focus. Nonconvex optimization is so general, and what makes deep learning hard may be completely... Continue
The Hardest Part
I’d like to thank Moritz, and Nisheeth, and Sanjeev for letting me guest post over at Off The Convex Path. I really enjoyed writing up my thoughts, so I’ve decided to dive in and try... Continue
Saddles again
Originally posted at offconvex.org Thanks to Rong for the very nice blog post describing critical points of nonconvex functions and how to avoid them. I’d like to follow up on his post to highlight a... Continue
Older