AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Learning Escorted Protocols For Multistate Free-Energy Estimation

Lars Holdijk, Nithishwer Mouroug Anand, Michael M. Bronstein, Max Welling

ICLR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Expressive invertible architectures

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use escorted protocol flow graph (EPFG) concatenation instead of pairwise summation (ablation)E-NEQ with underdamped Langevin · ADPMAE: 0.93 -> 0.88Improved
use escorted protocol flow graph (EPFG) concatenation instead of pairwise summation (ablation)E-NEQ with overdamped Langevin · ADPMAE: 0.96 -> 0.59Improved
use escorted protocol flow graph (EPFG) concatenation instead of pairwise summation (ablation)E-NEQ with HMC · ADPMAE: 0.99 -> 0.95Improved
learn escorting field and potential (E-NEQ UL) instead of TFEP vector field onlyTFEP · ADPMAE: 1.17 -> 0.93Improved
learn escorting field and potential (E-NEQ OL with EPFG) instead of TFEPTFEP · ADPMAE: 1.17 -> 0.59Improved
use E-NEQ instead of TFEP for free-energy correlation with USTFEP · ADPR2 / Pearson r: R2 0.90 -> 0.91, r 0.95 -> 0.96Improved
add the escort vector field to JE with learned potential (E-NEQ 100 steps vs JE 50,000 steps) (ablation)JE with learned potential · ADPMAE: 3.92 -> 0.93Improved
increase JE interpolation steps from 500 to 5,000JE with learned potential · ADPMAE: 6.16 -> 7.73Hurt
increase JE interpolation steps from 5,000 to 50,000JE with learned potential · ADPMAE: 7.73 -> 3.92Improved
use Langevin dynamics rather than HMC as stationary-preserving componentE-NEQ · ADPsuccessful trajectories from C5: 32477 -> 48328Improved
use overdamped Langevin instead of HMC for stationary-preserving dynamicsE-NEQ · ADPMAE with EPFG: 0.95 -> 0.59Improved
add Metropolis-Hastings correction against HMC divergenceE-NEQ HMC · ADPtrajectory stabilityNo clear effect

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