Inquiry about Sample Efficient Neural architecture search by learning action space

[pipilurj]

Hello, as you have recommended, I studied your new paper and was amazed by the result, and the idea was quite enlightening, however, there are a few things that still confuses me:

1. Does Xbar in node.Xbar stand for the mean accuracy of architectures attached to that node
2. I am very curious about the way you encode the architectures, does it affect the performance a lot? Thank you very much and looking forward to your reply!

[linnanwang]

1. xbar can be mean acc or cumulative sum, this is an implementation preference.

2. a good research model shall be robust to any encoding mechanism. There is no tricks here, we use the the most brutal force encoding scheme. However, if you lose information, that's a different story.