Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes
Junqi Tang, Mohammad Golbabaee, Francis Bach, Mike E. davies
–Neural Information Processing Systems
We propose a structure-adaptive variant of a state-of-the-art stochastic variance-reduced gradient algorithm Katyusha for regularized empirical risk minimization.
Neural Information Processing Systems
Nov-20-2025, 15:44:21 GMT
- Country:
- Europe
- France (0.04)
- United Kingdom > England
- North America > Canada
- Oceania > Australia
- New South Wales > Sydney (0.04)
- Europe
- Technology: