English

A Trainable Optimizer

Machine Learning 2026-01-30 v2

Abstract

The concept of learning to optimize involves utilizing a trainable optimization strategy rather than relying on manually defined full gradient estimations such as ADAM. We present a framework that jointly trains the full gradient estimator and the trainable weights of the model. Specifically, we prove that pseudo-linear TO (Trainable Optimizer), a linear approximation of the full gradient, matches SGD's convergence rate while effectively reducing variance. Pseudo-linear TO incurs negligible computational overhead, requiring only minimal additional tensor multiplications. To further improve computational efficiency, we introduce two simplified variants of Pseudo-linear TO. Experiments demonstrate that TO methods converge faster than benchmark algorithms (e.g., ADAM) in both strongly convex and non-convex settings, and fine tuning of an LLM.

Keywords

Cite

@article{arxiv.2508.01764,
  title  = {A Trainable Optimizer},
  author = {Ruiqi Wang and Diego Klabjan},
  journal= {arXiv preprint arXiv:2508.01764},
  year   = {2026}
}