Robust Learning of Multi-Index Models under Logconcave Distributions via Weak Partial Learners
cs.LG
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: Full version of the paper appearing in FOCS 2026. The abstract was shortened due to requirements from arXiv
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Learning Functions of Halfspaces
- Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals
- Thin-shell bounds via parallel coupling
- The Kannan-Lov'asz-Simonovits Conjecture
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