paper-with-me

홈 › Papers

Stochastic Variational Propagation: Local, Scalable and Efficient Alternative to Backpropagation

2025-05-08 · Bojian Yin, Federico Corradi

Backpropagation (BP) is the cornerstone of deep learning, but its reliance on global gradient synchronization limits scalability and imposes significant memory overhead. We propose Stochastic Variational Propagation (SVP), a scalable alternative that reframes training as hierarchical variational inference. SVP treats layer activations as latent variables and optimizes local Evidence Lower Bounds (ELBOs), enabling independent, local updates while preserving global coherence. However, directly applying KL divergence in layer-wise ELBOs risks inter-layer's representation collapse due to excessive compression. To prevent this, SVP projects activations into low-dimensional spaces via fixed random matrices, ensuring information preservation and representational diversity. Combined with a feature alignment loss for inter-layer consistency, SVP achieves competitive accuracy with BP across diverse architectures (MLPs, CNNs, Transformers) and datasets (MNIST to ImageNet), reduces memory usage by up to 4x, and significantly improves scalability. More broadly, SVP introduces a probabilistic perspective to deep representation learning, opening pathways toward more modular and interpretable neural network design.

📄 PDF Abstract BibTeX arXiv:2505.05181

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityRepresentation LearningVariational Inference

Similar Papers 제목 키워드 기반

Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server

2015-12-31 · Leonard Hasenclever, Stefan Webb, Thibaut Lienart, Sebastian Vollmer 외

This paper makes two contributions to Bayesian machine learning algorithms. Firstly, we propose stochastic natural gradient expectation propagation (SNEP), a novel alternative to expectation propagation (EP), a popular v…

Variational Inference

Scalable Gaussian Process Classification via Expectation Propagation

2015-07-16 · Daniel Hernández-Lobato, José Miguel Hernández-Lobato

Variational methods have been recently considered for scaling the training process of Gaussian process classifiers to large datasets. As an alternative, we describe here how to train these classifiers efficiently using e…

ClassificationGeneral Classification

Fast Second-Order Stochastic Backpropagation for Variational Inference

2015-09-09 · Kai Fan, Ziteng Wang, Jeff Beck, James Kwok 외

We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well. This is acc…

regressionVariational Inference

Fast Second Order Stochastic Backpropagation for Variational Inference

2015-12-01 · NeurIPS 2015 12 · Kai Fan, Ziteng Wang, Jeff Beck, James Kwok 외

We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well. This is ac…

regressionVariational Inference

Scalable Stochastic Parametric Verification with Stochastic Variational Smoothed Model Checking

2022-05-11 · Luca Bortolussi, Francesca Cairoli, Ginevra Carbone, Paolo Pulcini

Parametric verification of linear temporal properties for stochastic models can be expressed as computing the satisfaction probability of a certain property as a function of the parameters of the model. Smoothed model ch…

Bayesian InferenceComputational EfficiencyGaussian ProcessesGPU+1