Sinon's Blog

The Optimizer Advantage?

This is not how I’d expect an optimizer system to work, at least based on how it’s advertised.

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence

We propose a new variant of the Adam optimizer called MicroAdam that specifically minimizes memory overheads, while maintaining theoretical convergence guarantees. We achieve this by compressing the gradient information before it is fed into the optimizer state, thereby reducing its memory footprint significantly. We control the resulting compression error via a novel instance of the classical \emph{error feedback} mechanism from distributed optimization in which *the error correction information is itself compressed* to allow for practical memory gains. We prove that the resulting approach maintains theoretical convergence guarantees competitive to those of AMSGrad, while providing good practical performance. Specifically, we show that MicroAdam can be implemented efficiently on GPUs: on both million-scale (BERT) and billion-scale (LLaMA) models, MicroAdam provides practical convergence competitive to that of the uncompressed Adam baseline, with lower memory usage and similar running time. Our code is available at https://github.com/IST-DASLab/MicroAdam.

PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates

PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization

Multi-Objective Neural Architecture Search by Learning Search Space Partitions

Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning

Neural Feature Learning in Function Space

Win: Weight-Decay-Integrated Nesterov Acceleration for Faster Network Training