Summary of Variational Stochastic Gradient Descent For Deep Neural Networks, by Haotian Chen et al.
Variational Stochastic Gradient Descent for Deep Neural Networks
by Haotian Chen, Anna Kuzina, Babak Esmaeili, Jakub M Tomczak
First submitted to arxiv on: 9 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Variational Stochastic Gradient Descent (VSGD) optimizer combines probabilistic modeling with gradient-based optimization to better estimate gradients and model uncertainties. Building on adaptive gradient-based methods like Adam, VSGD utilizes stochastic variational inference (SVI) to derive an efficient update rule. This approach is evaluated on two image classification datasets and four deep neural network architectures, demonstrating improved performance compared to Adam and Stochastic Gradient Descent (SGD). |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to optimize deep neural networks using a combination of probabilistic modeling and gradient-based optimization. This method, called Variational Stochastic Gradient Descent (VSGD), is better at estimating gradients and modeling uncertainties than current methods like Adam. The authors test VSGD on two image classification datasets and four different types of neural networks, and show that it works better than Adam and another optimizer called Stochastic Gradient Descent. |
Keywords
* Artificial intelligence * Image classification * Inference * Neural network * Optimization * Stochastic gradient descent
