AI Paper Atlas

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

Neural Quantum States in Mixed Precision

Massimo Solinas, Agnes Valenti, Nawaf Bou-Rabee, Roeland Wiersema

ICML 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Importance sampling and quadrature · 0 citations (OpenAlex)

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
sample in f32/f16 with a double-precision training copyVMC with ResCNN · 2D TFIM, L=10, critical pointrelative energy error: nearly identical across all data typesNo clear effect
sample in bf16 instead of f16 (ablation)VMC with ResCNN · 2D TFIM, L=10MC noise vs precision-error bound: MC noise does not exceed bound for bf16Hurt
increase number of samples and parameterslow-precision RBM sampling · H100 GPU samplingspeedup: up to 3.5xImproved
use mixed-precision iterative solvers for preconditioningVMC · stochastic reconfigurationspeed: benefits only for matrices larger than 2^15 x 2^15Mixed
increase noise sigma to order unity (ablation)Noisy RBM sampling · TFIM RBMMH acceptance rate: acceptance suppressed, ergodicity lost at large sigmaHurt

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