paper
Second-Order Path Kernel Interpolation Formulas in Machine Learning
paperactiveprovisional
second-order-path-kernel-interpolation-formulas-in-machine-learning-193a2843·1 events·first seen 9d agoAliases: Second-Order Path Kernel Interpolation Formulas in Machine Learning
Co-occurring entities
More like this (12)
Laplace KernelNeural Tangent KernelGaussian kernel smoothingAlgorithmic and Minimax Complexities in Kernel BanditsPC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-TrainingExact Posterior Score Estimation for Solving Linear Inverse ProblemsHow abundant are good interpolators?Neural Ordinary Differential EquationsA Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian NoiseSuperposition Model (neural networks)When to Align, When to Predict: A Phase Diagram for Multimodal LearningOperator Learning
Recent events (1)
Second-order path kernel interpolation formulas extend Domingos' gradient-descent characterization
This paper extends Pedro Domingos' 2020 first-order path-kernel interpolation formula for gradient-descent-trained models to second-order forms. The authors derive curvature-weighted correction terms for standard SGD, an additional sampling-induced component coupling prediction curvature with mini-batch gradient noise covariance, and an extension to SGD with momentum. A concentration estimate for the terminal prediction is also established, quantifying fluctuation around the expected second-order representation.