Establishes non-asymptotic Gaussian approximation bounds for federated LSA with explicit communication-heterogeneity trade-offs and introduces an online multiplier bootstrap for last-iterate inference with validity guarantees.
Advances in Neural Information Processing Systems , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ML 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proposes Factor-Augmented SGD that runs on streaming high-dimensional data and supplies the first convergence analysis explicitly accounting for latent-factor estimation error.
citing papers explorer
-
Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation
Establishes non-asymptotic Gaussian approximation bounds for federated LSA with explicit communication-heterogeneity trade-offs and introduces an online multiplier bootstrap for last-iterate inference with validity guarantees.
-
Factor Augmented High-Dimensional SGD
Proposes Factor-Augmented SGD that runs on streaming high-dimensional data and supplies the first convergence analysis explicitly accounting for latent-factor estimation error.