# Read the Signs: Towards Invariance to Gradient Descent's Hyperparameter Initialization

arXiv: https://arxiv.org/abs/2301.10133 · HTML: https://mlsanity.com/paper/2301.10133/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 24 Jan 2023.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [Lookahead Optimizer: k steps forward, 1 step back](https://mlsanity.com/paper/1907.08610/) (2019)
- [AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients](https://mlsanity.com/paper/2010.07468/) (2020)
- [Deep Learning without Poor Local Minima](https://mlsanity.com/paper/1605.07110/) (2016)
- [Online Learning Rate Adaptation with Hypergradient Descent](https://mlsanity.com/paper/1703.04782/) (2017)
- [Small nonlinearities in activation functions create bad local minima in neural networks](https://mlsanity.com/paper/1802.03487/) (2018)
- [The Impact of the Mini-batch Size on the Variance of Gradients in Stochastic Gradient Descent](https://mlsanity.com/paper/2004.13146/) (2020)
- [The Number of Steps Needed for Nonconvex Optimization of a Deep Learning Optimizer is a Rational Function of Batch Size](https://mlsanity.com/paper/2108.11713/) (2021)

## Abstract (arXiv)

We propose ActiveLR, an optimization meta algorithm that localizes the learning rate, α, and adapts them at each epoch according to whether the gradient at each epoch changes sign or not. This sign-conscious algorithm is aware of whether from the previous step to the current one the update of each parameter has been too large or too small and adjusts the α accordingly. We implement the Active version (ours) of widely used and recently published gradient descent optimizers, namely SGD with momentum, AdamW, RAdam, and AdaBelief. Our experiments on ImageNet, CIFAR-10, WikiText-103, WikiText-2, and PASCAL VOC using different model architectures, such as ResNet and Transformers, show an increase in generalizability and training set fit, and decrease in training time for the Active variants of the tested optimizers. The results also show robustness of the Active variant of these optimizers to different values of the initial learning rate. Furthermore, the detrimental effects of using large mini-batch sizes are mitigated. ActiveLR, thus, alleviates the need for hyper-parameter search for two of the most commonly tuned hyper-parameters that require heavy time and computational costs to pick. We encourage AI researchers and practitioners to use the Active variant of their optimizer of choice for faster training, better generalizability, and reducing carbon footprint of training deep neural networks.