### ICML 2013 Reading List

The ICML is now already over for two weeks, but I still wanted to write about my reading list, as there have been some quite interesting papers (the proceedings are here). Also, I haven't blogged in ages, for which I really have no excuse ;)

There are three topics that I am particularly interested in, which got a lot of attention at this years ICML: Neural networks, feature expansion and kernel approximation, and Structured prediction.

But first:

###

This is the newest in a series of papers by James Bergstra on hyperparamter optimization. I quite enjoy his work and his hyperopt software is in active use in my lab. In particular in computer vision applications, there is so much engineering, that it is very hard to separate research contributions from engineering contributions. This paper shows 1) how important engineering is and 2) how far automatization of the engineering part can really go.

They gained a lot of attention in the more machine-learny circles in the last couple of years. Still I was a bit surprised how many - in particular very empirical papers - made it to ICML.

There are three topics that I am particularly interested in, which got a lot of attention at this years ICML: Neural networks, feature expansion and kernel approximation, and Structured prediction.

But first:

###
**Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures**

This is the newest in a series of papers by James Bergstra on hyperparamter optimization. I quite enjoy his work and his hyperopt software is in active use in my lab. In particular in computer vision applications, there is so much engineering, that it is very hard to separate research contributions from engineering contributions. This paper shows 1) how important engineering is and 2) how far automatization of the engineering part can really go.

## Neural Networks

Now, let's come to the somewhat most unlikely candidate, neural networks.They gained a lot of attention in the more machine-learny circles in the last couple of years. Still I was a bit surprised how many - in particular very empirical papers - made it to ICML.

Thanks, Andy for mentioning my paper :)

ReplyDeleteIt seems like I'll have to go over the list of paper at ICML 2013 again. Although I was there myself, just the amount of talks and posters was a bit too overwhelming.

It is really overwhelming. I wish I was there.

DeleteI went over the proceedings three times and still found new interesting stuff I over read in the first two reads.

The last word of Cho's paper title are missing, though

ReplyDeleteI've referenced the Gitten's et al. paper multiple times in my dissertation. Great work.

ReplyDeleteThis comment has been removed by the author.

ReplyDelete