Search Results for author:
Found 3 papers, 2 papers with code
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
We identify a key axis of matrix parameterizations termed sequence alignment, which increases the flexibility and performance of matrix mixers, providing insights into the strong performance of Transformers and recent SSMs such as Mamba.
Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
Vision tasks are characterized by the properties of locality and translation invariance.
Sharpened Lazy Incremental Quasi-Newton Method
Specifically, they exhibit a superlinear rate with $O(d^2)$ cost in contrast to the linear rate of first-order methods with $O(d)$ cost and the quadratic rate of second-order methods with $O(d^3)$ cost.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
