Debiasing Conditional Stochastic Optimization Lie He
–Neural Information Processing Systems
The sample-averaged gradient of the CSO objective is biased due to its nested structure, and therefore requires a high sample complexity for convergence. We introduce a general stochastic extrapolation technique that effectively reduces the bias.
Neural Information Processing Systems
Feb-18-2026, 01:21:51 GMT
- Country:
- Europe
- North America
- Canada
- British Columbia > Vancouver (0.04)
- Quebec > Montreal (0.04)
- United States
- Arizona > Maricopa County
- Phoenix (0.04)
- Nevada (0.04)
- Arizona > Maricopa County
- Canada
- Oceania > Australia
- New South Wales > Sydney (0.04)
- Genre:
- Research Report > New Finding (0.67)
- Technology: