Publications
2024
Proceedings of the International Conference on Machine Learning (ICML)
We present novel optimization techniques for training large-scale neural networks that significantly reduce computational overhead while maintaining model performance. Our approach introduces adaptive learning rate scheduling combined with gradient compression...
Journal of Mathematical Optimization
We present a rigorous mathematical analysis of gradient descent convergence rates under various smoothness conditions. Our main theorem establishes that for $L$-smooth functions, the convergence rate is $\mathcal{O}(1/k)$ where $k$...
Publication Metrics
- Total Publications: 2
- Publications with DOI: 2
- Publications with Code: 1
For a complete and up-to-date list, see my ORCID profile.
For citation metrics, see my Google Scholar profile.