Salvato in:
Dettagli Bibliografici
Autori principali: Dinh, Vu C., Ho, Lam Si Tung, Nguyen, Cuong V.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.22065
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909370572341248
author Dinh, Vu C.
Ho, Lam Si Tung
Nguyen, Cuong V.
author_facet Dinh, Vu C.
Ho, Lam Si Tung
Nguyen, Cuong V.
contents We analyze the error rates of the Hamiltonian Monte Carlo algorithm with leapfrog integrator for Bayesian neural network inference. We show that due to the non-differentiability of activation functions in the ReLU family, leapfrog HMC for networks with these activation functions has a large local error rate of $Ω(ε)$ rather than the classical error rate of $O(ε^3)$. This leads to a higher rejection rate of the proposals, making the method inefficient. We then verify our theoretical findings through empirical simulations as well as experiments on a real-world dataset that highlight the inefficiency of HMC inference on ReLU-based neural networks compared to analytical networks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22065
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient
Dinh, Vu C.
Ho, Lam Si Tung
Nguyen, Cuong V.
Machine Learning
We analyze the error rates of the Hamiltonian Monte Carlo algorithm with leapfrog integrator for Bayesian neural network inference. We show that due to the non-differentiability of activation functions in the ReLU family, leapfrog HMC for networks with these activation functions has a large local error rate of $Ω(ε)$ rather than the classical error rate of $O(ε^3)$. This leads to a higher rejection rate of the proposals, making the method inefficient. We then verify our theoretical findings through empirical simulations as well as experiments on a real-world dataset that highlight the inefficiency of HMC inference on ReLU-based neural networks compared to analytical networks.
title Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient
topic Machine Learning
url https://arxiv.org/abs/2410.22065