Finite size corrections for neural network Gaussian processes
원문 초록
There has been a recent surge of interest in modeling neural networks (NNs) as Gaussian processes. In the limit of a NN of infinite width the NN becomes equivalent to a Gaussian process. Here we demonstrate that for an ensemble of large, finite, fully connected networks with a single hidden layer the distribution of outputs at initialization is well described by a Gaussian perturbed by the fourth Hermite polynomial for weights drawn from a symmetric distribution. We show that the scale of the perturbation is inversely proportional to the number of units in the NN and that higher order terms decay more rapidly, thereby recovering the Edgeworth expansion. We conclude by observing that understanding how this perturbation changes under training would reveal the regimes in which the Gaussian process framework is valid to model NN behavior.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
STACI: Spatio-Temporal Aleatoric Conformal Inference
Statistical Machine Learning for Astronomy -- A Textbook
LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization
MathOptAI.jl: Embed trained machine learning predictors into JuMP models
The kernel of graph indices for vector search
Model-Based Real-Time Pose and Sag Estimation of Overhead Power Lines Using LiDAR for Drone Inspection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.