Amir Ziaimlbench — ML benchmarking utilsSimple utilities and visualizations to help with doing the right thing when you’re running ML experiments.Aug 19Aug 19
Amir ZiaiAn impact assessment framework for human-in-the-loop algo projectsThis post presents a framework for assessing the impact of human-in-the-loop project, in addition to adoption pitfalls and some…Feb 6Feb 6
Amir ZiaiLoad balancing for Data Parallel Actor-based systemsWe explore ways to dynamically load balance actors in a streaming framework.Jan 3Jan 3
Amir ZiaiRetrieval-Augmented Few-shot Image Classification (RAFIC)A method for augmenting support images for few-shot image classification with additional retrieved images, with yields sig improvement.Dec 30, 2023Dec 30, 2023
Amir ZiaiRanking metrics from first principles: Average PrecisionHaven’t read part 1 yet? Ranking metrics from first principles lays down some of the required foundations that you may find useful when…Sep 20, 2023Sep 20, 2023
Amir ZiaiA semi-random collection of advice that I’ve found very useful as an ML engineer1- Own things e2e 2- engg best practices 3- metrics! 4- problem formulation 5- bulletproof eval code 6- earn your complexitySep 12, 2023Sep 12, 2023
Amir ZiaiReservoir samplingSample a large data stream with optimal storage and minimal compute.May 16, 2023May 16, 2023
Amir ZiaiCount-min sketchNeed to count elements in an unbounded data stream using bounded memory? May want to consider count-min sketch.Apr 12, 2023Apr 12, 2023
Amir ZiaiRanking metrics from first principlesRanking metrics are not very well understood. Some of them are actually unintuitive, which makes them prone to misinterpretation.Mar 31, 2023Mar 31, 2023
Amir ZiaiConsistent hashing from first principles- Part 2(I’ve tried to minimize code clutter, so the code presented in the post is not self contained. If you want to run the code as you read, I…Sep 26, 2022Sep 26, 2022