91–100 of 132 posts
Can anyone link to experiments in the space of evolving code by mutating it in a syntactically-correct way, running it, evaluating its results or killing it if it doesn't complete?
Earlier quoted context omitted.
This is absolutely not cheating; every hand designed algorithm can access and compare everything in the array! The real point of what they’re saying in your italicized quote is actually that giving the net full access hinders efficiency, so they actually restrict it. Almost like the opposite of cheating.
It is not a pointer to an array I'm concerned about but the "neighbour diff vector" or what you should call it that provided by the "environment". See A.1.2. Doing so many comparisons and storing them has a cost. Also the model can't decide if it is done so at each step the array has to be iterated to see if it is sorted by the "environment". Are they only counting function calls? I guess so. The paper is really hard…
Oh that, yes, it's true. They're listing "average episode lengths" in tables 1-3 and those are their main support for their claim of efficiency. By "episode length" they mean instruction or function calls made during training by the student agent which they compare to the instructions/function calls by the teacher agent. So, no asymptotic analysis, just a count of concrete operations performed to solve e.g. a sorting task.
It's really hard to write correct code. Sorting was broken in java and nobody noticed for a long time: http://envisage-project.eu/wp-content/uploads/2015/02/sortin... The same was true for java's binary search: https://ai.googleblog.com/2006/06/extra-extra-read-all-about... So I am not sure I will ever trust an ML algorithm trained on inputs/outputs only (which is what I think "neural program induction" means). The a…
I used to ask "implement binary search" as an interview question and gave up on using it because not a single candidate could do it correctly in 45 minutes. This was at a FAANG.
Earlier quoted context omitted.
> There's a place for fast sorting algorithms which are correct most of the time - basically anything non-critical, like sorting comments by upvotes. Nothing saddens me more than this trend of the modern web where everything works semi-probabilistically (even if it's likely for "good" technical reasons, such as, "we wrote our server backend in Ruby which is slow as molasses so now we need 230 CDN and 800 databases in…
I think the good technical reasons are quite often the CAP theorem.
Stackoverflow was just using 4 db servers in 2016 (https://nickcraver.com/blog/2016/02/17/stack-overflow-the-ar...)
It's really hard to write correct code. Sorting was broken in java and nobody noticed for a long time: http://envisage-project.eu/wp-content/uploads/2015/02/sortin... The same was true for java's binary search: https://ai.googleblog.com/2006/06/extra-extra-read-all-about... So I am not sure I will ever trust an ML algorithm trained on inputs/outputs only (which is what I think "neural program induction" means). The a…
> The same was true for java's binary search I used to ask "implement binary search" as an interview question and gave up on using it because not a single candidate could do it correctly in 45 minutes. This was at a FAANG.
If they didn't, than I believe you did a poor job of guiding them. I refuse to believe that this is some esoteric, tough question. If you can solve dynamic programming problems, you can easily solve this one.
Earlier quoted context omitted.
> The same was true for java's binary search I used to ask "implement binary search" as an interview question and gave up on using it because not a single candidate could do it correctly in 45 minutes. This was at a FAANG.
I don't believe you. Surely, after a few hints, the FAANG canidates must have been able to figure out the classic gotcha of this question (why does this sometimes overflow and how do you fix {high + low / 2}) If they didn't, than I believe you did a poor job of guiding them. I refuse to believe that this is some esoteric, tough question. If you can solve dynamic programming problems, you can easily solve this one.
Earlier quoted context omitted.
> There's a place for fast sorting algorithms which are correct most of the time - basically anything non-critical, like sorting comments by upvotes. Nothing saddens me more than this trend of the modern web where everything works semi-probabilistically (even if it's likely for "good" technical reasons, such as, "we wrote our server backend in Ruby which is slow as molasses so now we need 230 CDN and 800 databases in…
Today's perfections are yesterday's "good enoughs". Don't be sad for the trend. In 10 years, you will have new perfections to enjoy.
Short version: In summary, this paper makes strong claims of generalisation and efficiency but does not seem to provide sufficently strong evidence to back them up, e.g. it does not perform an asymptotic analysis to support the efficiency claim, it doesn't show actual program output to allow the evaluation of what is actually learned and the claim about strong generalisation is based on a very vaguely described exper…
Functions can be recursive. So the algorithm that the agent generates is able to use divide-and-conquer.
Earlier quoted context omitted.
I don't believe you. Surely, after a few hints, the FAANG canidates must have been able to figure out the classic gotcha of this question (why does this sometimes overflow and how do you fix {high + low / 2}) If they didn't, than I believe you did a poor job of guiding them. I refuse to believe that this is some esoteric, tough question. If you can solve dynamic programming problems, you can easily solve this one.
I interview tons of candidates at a FAANG company, and I can tell you for sure binary search is way too hard to get right on a whiteboard. Even in a proper coding environment I wouldn't ask it. There are lots of better questions with fewer sharp edges.