Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes
–Neural Information Processing Systems
Reducing the variance of the gradient estimator is known to improve the convergence rate of stochastic gradient-based optimization and sampling algorithms.
Neural Information Processing Systems
Feb-9-2026, 22:31:26 GMT
- Country:
- Europe
- North America
- Canada > Quebec
- Montreal (0.14)
- United States
- California
- Los Angeles County > Long Beach (0.14)
- San Francisco County > San Francisco (0.14)
- Nevada (0.04)
- California
- Canada > Quebec
- Oceania > Australia
- New South Wales > Sydney (0.04)
- Genre:
- Research Report (0.46)
- Technology: