Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.06549 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913798867124224 |
|---|---|
| author | Chen, Haotian Kuzina, Anna Esmaeili, Babak Tomczak, Jakub M |
| author_facet | Chen, Haotian Kuzina, Anna Esmaeili, Babak Tomczak, Jakub M |
| contents | Current state-of-the-art optimizers are adaptive gradient-based optimization methods such as Adam. Recently, there has been an increasing interest in formulating gradient-based optimizers in a probabilistic framework for better modeling the uncertainty of the gradients. Here, we propose to combine both approaches, resulting in the Variational Stochastic Gradient Descent (VSGD) optimizer. We model gradient updates as a probabilistic model and utilize stochastic variational inference (SVI) to derive an efficient and effective update rule. Further, we show how our VSGD method relates to other adaptive gradient-based optimizers like Adam. Lastly, we carry out experiments on two image classification datasets and four deep neural network architectures, where we show that VSGD outperforms Adam and SGD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06549 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Variational Stochastic Gradient Descent for Deep Neural Networks Chen, Haotian Kuzina, Anna Esmaeili, Babak Tomczak, Jakub M Machine Learning Current state-of-the-art optimizers are adaptive gradient-based optimization methods such as Adam. Recently, there has been an increasing interest in formulating gradient-based optimizers in a probabilistic framework for better modeling the uncertainty of the gradients. Here, we propose to combine both approaches, resulting in the Variational Stochastic Gradient Descent (VSGD) optimizer. We model gradient updates as a probabilistic model and utilize stochastic variational inference (SVI) to derive an efficient and effective update rule. Further, we show how our VSGD method relates to other adaptive gradient-based optimizers like Adam. Lastly, we carry out experiments on two image classification datasets and four deep neural network architectures, where we show that VSGD outperforms Adam and SGD. |
| title | Variational Stochastic Gradient Descent for Deep Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.06549 |