Hi Adarsh,
Thank you for sharing the proposal. It looks nice but I did not go all
over it.
We already had a student last year who worked on XGBoost but he did not
have a chance to complete all of the implementations. I think the
correct thing to do is to investigate the parts that he did not complete
and start from there. This will give a higher chance of completing the
project rather than finishing 80 to 90 percent of it, and never merging
the code.
A nice proposal would be to identify the parts that are missing and not
completed and build a proposal on top of that. Eventually, if you
estimate that you will have enough time left, you can add examples
related to the algorithm as well.
Best regards,
Omar
On 2023-03-31 22:33, Adarsh Santoria wrote:
Dear mlpack community,
I'm writing to follow up on my GSoC project proposal for improving
ensemble trees with XGBoost implementation. I submitted my proposal a
few days ago and wanted to check if you'd had a chance to review it
yet.
My proposal aims to enhance the performance of ensemble trees in
mlpack by implementing XGBoost, a machine-learning algorithm that uses
decision trees as base learners. You can access the detailed project
plan and timeline through this link:
https://docs.google.com/document/d/1mQx5e7thE42zIlEPO2U5aUkk4sZfvDZxBWtTYgytrNY/edit?usp=sharing.
I would appreciate any feedback you may have on my proposal. Thank you
for considering my application for the GSoC project.
Best regards,
Adarsh Santoria
Github link: https://github.com/AdarshSantoria
On Mon, Mar 20, 2023 at 12:53 AM Adarsh Santoria
<[email protected]> wrote:
Dear mlpack community,
My name is Adarsh Santoria, and I am a sophomore at IIT Mandi,
India. I am writing to submit my proposal for the GSoC project on
improving ensemble trees with XGBoost implementation. You can access
the document through this link:
https://docs.google.com/document/d/1mQx5e7thE42zIlEPO2U5aUkk4sZfvDZxBWtTYgytrNY/edit?usp=sharing,
which outlines my project plan and timeline in detail. XGBoost is a
machine learning algorithm that uses decision trees as base
learners, known for its high accuracy, interpretability,
scalability, feature importance, and robustness to noisy or
incomplete data. Implementing XGBoost in mlpack is a necessary step
towards enhancing the performance of ensemble trees, making it an
important contribution to the mlpack community.
In summary, my proposal includes the following:
● Implementing Random Forest Regressor method and adding tests
● Parallelizing decision tree, random forest and xgboost with
OpenMP
● Adding bindings for the decision tree, random forest and xgboost
● Adding the XGBoost Classifier and Regressor along with some
split methods and loss functions.
● Adding tutorials and sample code snippets
I believe that with my skills and experience, I can make significant
contributions to mlpack and enhance the performance of ensemble
trees with XGBoost implementation.
Thank you for considering my proposal for the GSoC project.
Best regards,
Adarsh Santoria
Github link: https://github.com/AdarshSantoria
_______________________________________________
mlpack mailing list -- [email protected]
To unsubscribe send an email to [email protected]
%(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
_______________________________________________
mlpack mailing list -- [email protected]
To unsubscribe send an email to [email protected]
%(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
