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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| sample in f32/f16 with a double-precision training copy | VMC with ResCNN · 2D TFIM, L=10, critical point | relative energy error: nearly identical across all data types | No clear effect |
| sample in bf16 instead of f16 (ablation) | VMC with ResCNN · 2D TFIM, L=10 | MC noise vs precision-error bound: MC noise does not exceed bound for bf16 | Hurt |
| increase number of samples and parameters | low-precision RBM sampling · H100 GPU sampling | speedup: up to 3.5x | Improved |
| use mixed-precision iterative solvers for preconditioning | VMC · stochastic reconfiguration | speed: benefits only for matrices larger than 2^15 x 2^15 | Mixed |
| increase noise sigma to order unity (ablation) | Noisy RBM sampling · TFIM RBM | MH acceptance rate: acceptance suppressed, ergodicity lost at large sigma | Hurt |
Closest papers by meaning
- PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization (NeurIPS 2025 · similarity 0.88)
- Quadratic Quantum Variational Monte Carlo (NeurIPS 2024 · similarity 0.88)
- One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective (NeurIPS 2026 · similarity 0.87)
- Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms (NeurIPS 2024 · similarity 0.85)
- Score-based Variational Inference via Quantum Maximally Mixed States (NeurIPS 2026 · similarity 0.85)
- TITAN: A Trajectory-Informed Technique for Adaptive Parameter Freezing in Large-Scale VQE (NeurIPS 2025 · similarity 0.85)
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.
