# LOSSGRAD: automatic learning rate in gradient descent

arXiv: https://arxiv.org/abs/1902.07656 · HTML: https://mlsanity.com/paper/1902.07656/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2019.

## Built on by (most cited first, 1 of 1)

- [Learning to Accelerate by the Methods of Step-size Planning](https://mlsanity.com/paper/2204.01705/) (2022)

## Abstract (arXiv)

In this paper, we propose a simple, fast and easy to implement algorithm LOSSGRAD (locally optimal step-size in gradient descent), which automatically modifies the step-size in gradient descent during neural networks training. Given a function f, a point x, and the gradient nablax f of f, we aim to find the step-size h which is (locally) optimal, i.e. satisfies:  h=arg,mint ≥ 0 f(x-t nablax f).  Making use of quadratic approximation, we show that the algorithm satisfies the above assumption. We experimentally show that our method is insensitive to the choice of initial learning rate while achieving results comparable to other methods.