AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Physics-Driven ML-Based Modelling for Correcting Inverse Estimation

Ruiyuan Kang, Tingting Mu, Panos Liatsis, Dimitrios Kyritsis

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Machine learning for physical simulation

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
estimate error sum with a single-output MLP instead of per-element errors (ablation)GEESE · Problem 1, eps=0.05average query times: 20.20 -> 23.26Hurt
train the exploration generator instead of keeping random weights (ablation)GEESE · Problem 1, eps=0.05average query times: 32.64 -> 41.32Hurt
remove early stopping of base networks (ablation)GEESE · Problem 1, eps=0.05average query times: 20.20 -> 32.80Hurt
remove focus coefficient (ablation)GEESE · Problem 1, eps=0.05average query times: 20.20 -> 27.19Hurt
use GEESE instead of GA on Problem 3GEESE · Problem 3, eps=0.075failure times: 13 -> 0Improved
use GEESE instead of BOGP on Problem 2GEESE · Problem 2, eps=0.075failure times: 97 -> 0Improved
use GEESE instead of PSO on Problem 2GEESE · Problem 2, eps=0.075average query times: 64.00 -> 51.65Improved
use GEESE instead of CMAES on Problem 3GEESE · Problem 3, eps=0.075average query times: 227.42 -> 43.56Improved
use GEESE instead of BOGP on Problem 1GEESE · Problem 1, eps=0.075average query times: 3.29 -> 3.18No clear effect
use SVPEN (RL-based) instead of GEESESVPEN · all problems, eps=0.075failure times: 0 -> 100Hurt
lower the feasibility threshold from 0.1 to 0.05GEESE · Problem 3average query times: 35.58 -> 81.26Hurt
use GEESE instead of BOGP at eps=0.05 on Problem 1GEESE · Problem 1, eps=0.05average query times: 9.24 -> 20.20Hurt

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