Eric Liu

Sorry I've been gone for so long! See: #448 for details. I'll add this to my upcoming to-do list. Yup, I agree, the I/O bounds/type/etc checking is pretty weak. You...

Sorry I've been gone for so long! See: #448 for details. @orasis, I'm not sure I'm understanding your question. What are you trying to do? Pick the best one of...

Oh, maybe this is what you're doing... at Yelp, one of the things we used MOE to do was optimize parameters of the advertising system to increase click-through-rate. So we'd...

Gotcha. So that's basically the same as the Yelp example I described. For each data point, you'd want to provide MOE with the mean & variance. For us, we were...

Sure, glad I could help. Keep in mind that you **should not** apply the logic: "I want MOE to explore more, let me change the mean so that more points...

Sorry I didn't respond sooner... just started a new job so I've been pretty busy. Plus I don't have a working linux installation at the moment to test on, lol....

1. `optimizer_success: True` is what you're looking for. That field is the name of a boolean. Both hyper_opt and next_points produce something along those lines. 2. Your kernel dies...? That...

- Ok. There should be a msg like that returned by the next_points call too. - Still weird. Idk why it would cause ipython to freeze. I don't use docker...

Also does this guy in `moe_examples` folder work for you? Basically does the same thing as your script, I think... https://github.com/Yelp/MOE/blob/master/moe_examples/combined_example.py may want to disable the noise in `function_to_minimize`. Looks...

I can understand having to abandon MOE... I'd be annoyed too if I were stuck for so long :( I was hoping to spend some time on this over the...