-
There appears to be a regression in v0.2 for single-value sketches... quick testing shows the issue with any value, and any quantile:
```
let mut dd = DDSketch::new(Config::defaults());
…
-
It would be nice to support the [Benchopt](https://github.com/benchopt/benchopt) problem suite, which is also available in Python:
- [ ] Ordinary Least Squares
- [ ] Non-Negative Least Squares
- …
-
Hi Catboost team,
first off, thanks for truly amazing library.
My question has to do with custom losses, I went through the following documentation file:
[https://github.com/catboost/catboos…
-
The quantile regression should accept an optional `weight` parameter. Stata supports this: https://www.stata.com/manuals13/rqreg.pdf. I believe this changes the definition of a[ quantile from count to…
-
Quantile Regression calculates robust cov in fit
Based on a quick browsing of the code, I think the calculations could be moved to the results class as in RLM, even if the cov arguments are still in …
-
Hello,
If i have multiple quantile estimations for example the 90th quantile, 80th quantile, 70th quantile... learned through independent direct quantile regression models, how would i evaluate th…
-
Currently, Autogluon Tabular predicts values without giving an estimate of the uncertainty.
Are you going to integrate methods like [conformal prediction](https://arxiv.org/pdf/2005.07972.pdf) or ano…
-
Hi,
I was keen to use this package since when I've tried to do conformal prediction using quantile regression in the past I've encountered the common issue of quantile forecast results not increas…
-
I think a useful addition would be the Linear Quantile Mixed Model. As with quantile regression, it has become a fairly popular go to modelling approach especially in psychology / education. I think s…
-
aside: pygam has penalized Expectile regression according to the examples/documentation
Currently RLM and QuantileRegression only use a IRLS algorithm
For RLM we can add gradient fit with scipy …