[p1esk]

But that's my point: their results are not that important to me.

As an example, recently I saw a paper on NN weight quantization, which had a very interesting idea, but the results were not impressive. I don't remember if they had any code published or not, but it didn't matter - I wanted to see what kind of results I'd get if I implemented it. Turned out it works really well, much better than what they reported in the paper.

[nonbel]

Here is an idea: inverse dropout.

How would you implement that?

[p1esk]

Link to paper?

[nonbel]

http://jmlr.org/papers/v15/srivastava14a.html

[p1esk]

You linked to the original dropout paper. What’s “inverse dropout”?

[nonbel]

It is just the description of an idea I came up with without any implementation.

I was leaving it purposefully vague, just do the "inverse" of what it says in that paper.

[lorenzhs]

That's not a description of an idea, just like a paper doesn't only consist of the title. This kind of argument is insincere and not helpful at all.