Daily Dose of Data Science

Home
Premium
Archive
About

Memory Optimization

Condense Random Forest into a Decision Tree
Preserve generalization power while reducing run-time.
 • 
Avi Chawla
3
The Probe Method: An Intuitive Feature Selection Technique
Introduce a bad feature to remove other bad features.
 • 
Avi Chawla
7
Create Robust and Memory Efficient Class Objects
Fix the attributes an object can ever possess.
 • 
Avi Chawla
3
Gradient Accumulation in Neural Networks and How it Works
An underrated technique to train neural networks in memory constrained settings.
 • 
Avi Chawla
Implementing LoRA from Scratch for Fine-tuning LLMs
Understanding the challenges of traditional fine-tuning and addressing them with LoRA.
 • 
Avi Chawla
Mixed Precision Training
Train large deep learning models efficiently.
 • 
Avi Chawla
3
Cython: An Under-appreciated Technique to Speed-up Native Python Programs
...within minimal effort.
 • 
Avi Chawla
6
Reduce Memory Usage By 50-60% When Training a Neural Network
An underrated technique to train larger ML models.
 • 
Avi Chawla
2
GROUPING SETS — A HIGHLY Underrated Technique to Run Multiple Aggregations While Scanning the Table Only Once
A lesser-known and much efficient way to run multiple aggregations.
 • 
Avi Chawla
3
The Most Overlooked Source of Optimization in Data Pipelines
Sometimes, the pain point can be outside your code.
 • 
Avi Chawla
5
Boost Sklearn Model Training and Inference by Doing (Almost) Nothing
...along with a lesser-known advice on vectorized operations.
 • 
Avi Chawla
4
A Practical and Intuitive Guide to Building Multi-task Learning Models
Building MTL models in PyTorch.
 • 
Avi Chawla
1
© 2024 Avi Chawla
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture