تقرير
Gradient flow in parameter space is equivalent to linear interpolation in output space
| العنوان: | Gradient flow in parameter space is equivalent to linear interpolation in output space |
|---|---|
| المؤلفون: | Chen, Thomas, Ewald, Patrícia Muñoz |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science Mathematics Mathematical Physics Statistics |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Mathematical Physics, Mathematics - Optimization and Control, Statistics - Machine Learning, 62M45, 37C10 |
| الوصف: | We prove that the usual gradient flow in parameter space that underlies many training algorithms for neural networks in deep learning can be continuously deformed into an adapted gradient flow which yields (constrained) Euclidean gradient flow in output space. Moreover, if the Jacobian of the outputs with respect to the parameters is full rank (for fixed training data), then the time variable can be reparametrized so that the resulting flow is simply linear interpolation, and a global minimum can be achieved. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2408.01517 |
| رقم الأكسشن: | edsarx.2408.01517 |
| قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!