Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models

NeurIPSSpotlight2025

Authors
Ilias Diakonikolas, Giannis Iakovidis, Daniel Kane, Lisheng Ren
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

We study the complexity of learning real-valued Multi-Index Models (MIMs) under the Gaussian distribution…

Opening excerpt from the authors’ abstract. source

Read the paper

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive