Gradient Boosting with Regression Trees Explained

Опубликовано: 22 Март 2026
на канале: DataMListic
31,342
491

In this video I explain what gradient boosting is and how it works, from both a theoretical and practical perspective. In general, gradient Boosting is a powerful machine learning technique for building predictive models that involves combining multiple weak models to create a stronger overall model. The idea behind gradient boosting is to iteratively improve the performance of a weak learner by training it on the errors made by the previous model in the sequence.

Related Videos
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
The Bias Variance Tradeoff:    • Bias-Variance Trade-off - Explained  
Multivariate Normal Distribution:    • Multivariate Normal (Gaussian) Distributio...  
Estimated Calibrated Error (ECE):    • Model Calibration - Estimated Calibration ...  

Resources
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Gradient Boosting Equation derivation (Math section): https://towardsdatascience.com/all-yo...

Contents
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
00:00 - Intro
00:15 - Gradient Boosting Theory
01:57 - Gradient Boosted Regression Trees - Step 0
02:14 - Gradient Boosted Regression Trees - Step 1
02:31 - Gradient Boosted Regression Trees - Step 2
02:48 - Gradient Boosted Regression Trees - Step 3
03:09 - Gradient Boosting Overview
03:59 - Outro

Follow Me
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
🐦 Twitter: @datamlistic   / datamlistic  
📸 Instagram: @datamlistic   / datamlistic  
📱 TikTok: @datamlistic   / datamlistic  

Channel Support
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
The best way to support the channel is to share the content. ;)

If you'd like to also support the channel financially, donating the price of a coffee is always warmly welcomed! (completely optional and voluntary)
► Patreon:   / datamlistic  
► Bitcoin (BTC): 3C6Pkzyb5CjAUYrJxmpCaaNPVRgRVxxyTq
► Ethereum (ETH): 0x9Ac4eB94386C3e02b96599C05B7a8C71773c9281
► Cardano (ADA): addr1v95rfxlslfzkvd8sr3exkh7st4qmgj4ywf5zcaxgqgdyunsj5juw5
► Tether (USDT): 0xeC261d9b2EE4B6997a6a424067af165BAA4afE1a

#gradientboosting #regressiontrees