2e2c4bf7ceaa4712a72dd5ee136dc9a8-Supplemental.pdf
–Neural Information Processing Systems
Most notably, we obtain the first dimension-independent generalization bounds formulti-pass SGD inthenonsmooth case. Inaddition, our bounds allow us to derive a new algorithm for differentially private nonsmooth stochastic convex optimization withoptimal excess population risk.
Neural Information Processing Systems
Feb-7-2026, 23:24:19 GMT
- Country:
- Europe
- Sweden > Stockholm
- Stockholm (0.04)
- United Kingdom (0.04)
- Sweden > Stockholm
- North America
- Canada (0.04)
- United States
- Arizona > Maricopa County
- Phoenix (0.04)
- District of Columbia > Washington (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- Arizona > Maricopa County
- Oceania > Australia
- New South Wales > Sydney (0.04)
- Europe
- Technology: