AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

Breaking the $\sqrt{d}$ Communication Barrier in Federated Sampling with Adaptive Hamiltonian Monte Carlo

Jiajun Liang, Linxuan Wang, Guang Lin, Qifan Song

NeurIPS 2026 · Federated learning and privacy › Communication-efficient FL · approach: Federated optimization algorithms · 0 citations (OpenAlex)

Read the paper

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Adaptive Federated Hamiltonian Monte Carlo (AFHMC) for Bayesian federated learning, aiming to beat the O(√d/ε) communication cost of prior federated HMC sampling.

Problem

Communication cost of sampling from posteriors in Bayesian federated learning; prior federated HMC achieves O(√d/ε) communication under log-convex distributions.

Approach

Adaptive federated HMC with a refined analysis that reveals further benefits of HMC in the FL regime, aiming to break the √d communication barrier.

Key results

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add global drift control variate and surrogate leapfrog to federated HMCAFHMC vs FA-HMC · Bayesian logistic regression d=1000, eta=5e-4marginal error: 5.3e-2 -> 2.3e-2Improved
add drift control variate (AFHMC) under matched leapfrog budgetfederated HMC · Heterogeneous Gaussian d=500squared W2 distance: 3.81e4 (FA-HMC) vs below 0.1 threshold reached by AFHMC at round 430Improved
give FA-HMC twice the rounds and its own tuned stepsize schedules (ablation)FA-HMC · Heterogeneous Gaussian d=500squared W2 distance: 1.19e4 and 1.98e4 after 860 roundsNo clear effect
lower client heterogeneity (clients sampled from same distribution) (ablation)AFHMC · Gaussian, d from 50 to 500communication rounds: 212 -> 248 vs 162 -> 430 on heterogeneous targetImproved
use AFHMC instead of FA-HMC on heterogeneous FMNISTBayesian logistic regression · FMNIST (Dirichlet 0.1)test accuracy: 0.841 -> 0.842 (same exchanges); 0.836 at same roundsImproved

Limitations

Experimental setup

Metrics: communication cost

Baselines: federated Langevin dynamics methods prior federated HMC (O(√d/ε))

Builds on: federated Hamiltonian Monte Carlo

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy