# Meta-Regularization: An Approach to Adaptive Choice of the Learning Rate in Gradient Descent

arXiv: https://arxiv.org/abs/2104.05447 · HTML: https://mlsanity.com/paper/2104.05447/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 12 Apr 2021.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [Convex Optimization: Algorithms and Complexity](https://mlsanity.com/paper/1405.4980/) (2014)
- [Online Learning Rate Adaptation with Hypergradient Descent](https://mlsanity.com/paper/1703.04782/) (2017)
- [Variants of RMSProp and Adagrad with Logarithmic Regret Bounds](https://mlsanity.com/paper/1706.05507/) (2017)
- [Barzilai-Borwein Step Size for Stochastic Gradient Descent](https://mlsanity.com/paper/1605.04131/) (2016)
- [WNGrad: Learn the Learning Rate in Gradient Descent](https://mlsanity.com/paper/1803.02865/) (2018)
- [A Unified Approach to Adaptive Regularization in Online and Stochastic Optimization](https://mlsanity.com/paper/1706.06569/) (2017)

## Abstract (arXiv)

We propose textitMeta-Regularization, a novel approach for the adaptive choice of the learning rate in first-order gradient descent methods. Our approach modifies the objective function by adding a regularization term on the learning rate, and casts the joint updating process of parameters and learning rates into a maxmin problem. Given any regularization term, our approach facilitates the generation of practical algorithms. When textitMeta-Regularization takes the varphi-divergence as a regularizer, the resulting algorithms exhibit comparable theoretical convergence performance with other first-order gradient-based algorithms. Furthermore, we theoretically prove that some well-designed regularizers can improve the convergence performance under the strong-convexity condition of the objective function. Numerical experiments on benchmark problems demonstrate the effectiveness of algorithms derived from some common varphi-divergence in full batch as well as online learning settings.