Nicholas Knight
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1
Research Timeline
2026
Riemannian Gradient Descent for Low-Rank Architectures
The paper investigates applying Riemannian optimization techniques to low-rank matrix parameters for deep learning, but finds that the proposed methods do not conclusively outperform the AdamW baseline.
Highlighted terms show continued research focus across papers