# Revisiting Gradient Descent: A Dual-Weight Method for Improved Learning

arXiv: https://arxiv.org/abs/2503.11965 · HTML: https://mlsanity.com/paper/2503.11965/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 15 Mar 2025.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)

## Abstract (arXiv)

We introduce a novel framework for learning in neural networks by decomposing each neuron's weight vector into two distinct parts, W1 and W2, thereby modeling contrastive information directly at the neuron level. Traditional gradient descent stores both positive (target) and negative (non-target) feature information in a single weight vector, often obscuring fine-grained distinctions. Our approach, by contrast, maintains separate updates for target and non-target features, ultimately forming a single effective weight W = W1 - W2 that is more robust to noise and class imbalance. Experimental results on both regression (California Housing, Wine Quality) and classification (MNIST, Fashion-MNIST, CIFAR-10) tasks suggest that this decomposition enhances generalization and resists overfitting, especially when training data are sparse or noisy. Crucially, the inference complexity remains the same as in the standard WX + bias setup, offering a practical solution for improved learning without additional inference-time overhead.