LGD reaches Bayes optimality at optimal hyperparameters and admits an O(dh) pseudo-dimension bound for meta-learning hyperparameters on convex regression tasks.
Further and stronger analogy between sampling and optimization: Langevin monte carlo and gradient descent
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates
LGD reaches Bayes optimality at optimal hyperparameters and admits an O(dh) pseudo-dimension bound for meta-learning hyperparameters on convex regression tasks.