mlsanityData to 7 Oct 2026

On Feynman--Kac training of partial Bayesian neural networks

arXiv 2310.19608 ↗First posted 30 Oct 2023cs.LG stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Recently, partial Bayesian neural networks (pBNNs), which only consider a subset of the parameters to be stochastic, were shown to perform competitively with full Bayesian neural networks. However, pBNNs are often multi-modal in the latent variable space and thus challenging to approximate with parametric models. To address this problem, we propose an efficient sampling-based training strategy, wherein the training of a pBNN is formulated as simulating a Feynman--Kac model. We then describe variations of sequential Monte Carlo samplers that allow us to simultaneously estimate the parameters and the latent posterior distribution of this model at a tractable computational cost. Using various synthetic and real-world datasets we show that our proposed training scheme outperforms the state of the art in terms of predictive performance.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 26 of its 68 references that are in the map. First posted on arXiv 30 Oct 2023.

Builds on

26 of 68 references.

References · 26

  1. 2017On Calibration of Modern Neural Networkscited by 4,860
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2016Variational Inference: A Review for Statisticianscited by 1,466
  4. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  5. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  6. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  7. 2014New insights and perspectives on the natural gradient methodcited by 435
  8. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 341
  9. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
  10. 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 227
  11. 2019Subspace Inference for Bayesian Deep Learningcited by 94
  12. 2017Variational Sequential Monte Carlocited by 93
14 more
  1. 2020Bayesian Deep Learning via Subnetwork Inferencecited by 85
  2. 2022Do Bayesian Neural Networks Need To Be Fully Stochastic?cited by 63
  3. 2021Differentiable Particle Filtering via Entropy-Regularized Optimal Transportcited by 59
  4. 2014On Particle Methods for Parameter Estimation in State-Space Modelscited by 47
  5. 2019Challenges in Markov chain Monte Carlo for Bayesian neural networkscited by 43
  6. 2019Benchmarking the Neural Linear Model for Regressioncited by 31
  7. 2022Automatic Differentiation of Programs with Discrete Randomnesscited by 28
  8. 2017Online Natural Gradient as a Kalman Filtercited by 25
  9. 2020AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMCcited by 13
  10. 2023Differentiating Metropolis-Hastings to Optimize Intractable Densitiescited by 5
  11. 2013On nonnegative unbiased estimatorscited by 4
  12. 2023A Tutorial on Parametric Variational Inferencecited by 4
  13. 2020A Global Stochastic Optimization Particle Filter Algorithmcited by 2
  14. 2022De-biasing particle filtering for a continuous time hidden Markov model with a Cox process observation modelcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025VIKING: Deep variational inference with stochastic projectionscited by 3
  2. 2025Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networkscited by 2
  3. 2025Diffusion differentiable resamplingcited by 2
  4. 2025Utilising Gradient-Based Proposals Within Sequential Monte Carlo Samplers for Training of Partial Bayesian Neural Networkscited by 0