A Near-optimal SQ Lower Bound for Smoothed Agnostic Learning of Boolean Halfspaces
cs.LG
Submitted: 2026-05-04
Updated: 2026-11-11
Terminology
Sources
- Statistical Query Lower Bounds for Smoothed Agnostic Learning
- Constructive Approximation under Carleman's Condition, with Applications to Smoothed Analysis
- Statistical Queries and Statistical Algorithms: Foundations and Applications
- Superconvergence points of Hermite spectral interpolation
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis