Chi Wang
Chi Wang
I'm glad this question is asked. I implemented this some time ago. I spent some effort in the design to enable blackbox constraint in our new BlendSearch method. Some idea...
> > One empirical study is in https://arxiv.org/pdf/2208.02922.pdf, in which @YIWEI-CHEN also demonstrates that when combined with early stopping, the performance can be further improved. > > Is this implemented...
By default, "r2" is used as the optimization metric for regression tasks. Looking at your plots, the model doesn't overfit the r2 or KGE metric. The model overfits RMSE. If...
I just ran a standalone test using your code and it doesn't fail: ```python # %% import flaml base = 10 rand_float = flaml.tune.loguniform(1, 20, base=base) samples = rand_float.sample(size=10000) #...
I ran the test. The failed tests are FAILED test/test_log_uniform.py::test_flaml_uniform_int - assert 0.33734160716544936 > 0.5 FAILED test/test_log_uniform.py::test_flaml_log_uniform_int - assert 0.0 > 0.5 The failure is not about log. It's about...
> Double checked. The float log uniform was an errant report on my part - I was applying a ceil mistakenly in the stack before doing the test. Removed that...
This appears an issue in ray. Could you try pip install "ray[tune]
@AbhinavGaur147 @xiaoyaoyang what's the version of ray in your env?
> > This appears an issue in ray. Could you try pip install "ray[tune]
This example is most close to what you need: https://github.com/microsoft/FLAML/blob/main/test/tune_example.py Please let me know if your problem can be solved by modifying that script.