A projected gradient descent algorithm for noisy inductive matrix completion achieves linear convergence and stable recovery at sample complexity governed by side-information dimension, extending to inexact side-information with optimal error degradation.
Handbook of Reinforcement Learning and Control , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A sharp threshold at zero reach-weighted contingent action capacity governs whether self-play RL collapses to a deterministic exploitation attractor under asymmetric perturbations.
citing papers explorer
-
Sample-efficient inductive matrix completion with noise and inexact side-information
A projected gradient descent algorithm for noisy inductive matrix completion achieves linear convergence and stable recovery at sample complexity governed by side-information dimension, extending to inexact side-information with optimal error degradation.
-
A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning
A sharp threshold at zero reach-weighted contingent action capacity governs whether self-play RL collapses to a deterministic exploitation attractor under asymmetric perturbations.