# MBGDT:Robust Mini-Batch Gradient Descent

arXiv: https://arxiv.org/abs/2206.07139 · HTML: https://mlsanity.com/paper/2206.07139/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 6 references that are in the map.
- First posted on arXiv 14 Jun 2022.

## Builds on (most cited first, 5 of 5)

- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Learning Models with Uniform Performance via Distributionally Robust Optimization](https://mlsanity.com/paper/1810.08750/) (2018)
- [Sever: A Robust Meta-Algorithm for Stochastic Optimization](https://mlsanity.com/paper/1803.02815/) (2018)
- [On Robustness to Adversarial Examples and Polynomial Optimization](https://mlsanity.com/paper/1911.04681/) (2019)
- [Robust Learning of Fixed-Structure Bayesian Networks](https://mlsanity.com/paper/1606.07384/) (2016)

## Abstract (arXiv)

In high dimensions, most machine learning method perform fragile even there are a little outliers. To address this, we hope to introduce a new method with the base learner, such as Bayesian regression or stochastic gradient descent to solve the problem of the vulnerability in the model. Because the mini-batch gradient descent allows for a more robust convergence than the batch gradient descent, we work a method with the mini-batch gradient descent, called Mini-Batch Gradient Descent with Trimming (MBGDT). Our method show state-of-art performance and have greater robustness than several baselines when we apply our method in designed dataset.