Extends high-dimensional KRR to product kernels, proving convergence rates that recover minimax optimality for source condition s ≤ 1, saturation for s > 1, and multiple-descent phenomena with respect to sample size n.
Advances in Neural Information Processing Systems , volume=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
LOFT unifies orthogonal PEFT by treating adaptation as low-rank subspace rotation and adds task-aware support selection that improves efficiency under fixed budgets.
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
Zeroth-order SGD learning dynamics are governed by a random low-dimensional projection of the empirical NTK whose approximation error scales with model output dimension, not parameter count.
A gradient-similarity complexity measure that generalizes polynomial degree, kernel length scale, neighbor count, tree splits, and forest size while offering insights into double descent.
citing papers explorer
-
Large Dimensional Kernel Ridge Regression: Extending to Product Kernels
Extends high-dimensional KRR to product kernels, proving convergence rates that recover minimax optimality for source condition s ≤ 1, saturation for s > 1, and multiple-descent phenomena with respect to sample size n.
-
LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection
LOFT unifies orthogonal PEFT by treating adaptation as low-rank subspace rotation and adds task-aware support selection that improves efficiency under fixed budgets.
-
Adaptive Kernel Ridge Regression with Linear Structure: Sharp Oracle Inequalities and Minimax Optimality
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
-
Learning Dynamics of Zeroth-Order Optimization: A Kernel Perspective
Zeroth-order SGD learning dynamics are governed by a random low-dimensional projection of the empirical NTK whose approximation error scales with model output dimension, not parameter count.
-
A Rigorous, Tractable Measure of Model Complexity
A gradient-similarity complexity measure that generalizes polynomial degree, kernel length scale, neighbor count, tree splits, and forest size while offering insights into double descent.