Efficient Preconditioned Optimization Methods with Frequent Directions

Name: Efficient Preconditioned Optimization Methods with Frequent Directions
Uploaded: 2026-10-18T17:50:26.483609+00:00
Duration: 270 s
Description: The authors propose efficient preconditioned optimization methods like FTSL and S-ASGO that accelerate adaptive optimization using frequent directions (FD). They integrate FD with primal-dual frameworks and exploit matrix structures to achieve tighter regret bounds and reduced computational complexity for optimizing both vector and matrix variables.

The authors propose efficient preconditioned optimization methods like FTSL and S-ASGO that accelerate adaptive optimization using frequent directions (FD). They integrate FD with primal-dual frameworks and exploit matrix structures to achieve tighter regret bounds and reduced computational complexity for optimizing both vector and matrix variables.

Open the full episode