First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time
–Neural Information Processing Systems
To the best of our knowledge, this is the first theoretical result of first-order stochastic algorithms with an almost linear time in terms of problem's
Neural Information Processing Systems
Nov-20-2025, 15:02:38 GMT
- Country:
- Asia
- Afghanistan > Parwan Province
- Charikar (0.04)
- Middle East > Jordan (0.04)
- Afghanistan > Parwan Province
- North America
- Canada > Quebec
- Montreal (0.04)
- United States > Iowa
- Johnson County > Iowa City (0.14)
- Canada > Quebec
- Asia
- Genre:
- Research Report (0.46)
- Technology: