Algorithms
Batch optimization for DNA synthesis
Directions in ML: Structured Models for Automated Machine Learning
Automated machine learning (AutoML) seeks algorithmic methods for finding the best machine learning pipeline and hyperparameters to fit a new dataset. The complexity of this problem is astounding: viewed as an optimization problem, it entails…
SCCL-Runtime
Synthesized Collective Communication Library (SCCL) is an algorithm synthesizer for GPU communication in machine learning workloads. SCCL-Runtime, which is what we are seeking the release approval for, takes a synthesized algorithm from SCCL and runs…
ChaCha for Online AutoML
In this work, we propose the ChaCha (Champion-Challengers) algorithm for making an online choice of hyperparameters in online learning settings. This work is published in ICML 2021. Python notebook demo: https://github.com/microsoft/FLAML/blob/main/notebook/autovw.ipynb
