AI Paper Atlas

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

Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation

Justin Fu, Sergey Levine

ICLR 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Gradient estimation for discrete variables · 7 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
use NEMO's quantized NML training instead of optimizing a pretrained forward model without NML (ablation)NEMO · Superconductor, MoleculeActivity, and GFPground truth scoreImproved
replace the discretized logistic architecture with a categorical feedforward network (ablation)NEMO · Superconductor50th-percentile ground truth scoreHurt
replace the discretized logistic architecture with a categorical feedforward network (ablation)NEMO · MoleculeActivityground truth scoreHurt
increase model optimization steps while using a small model learning rate (ablation)NEMO · Superconductorground truth scoreImproved
increase model optimization steps while using a high model learning rate (ablation)NEMO · Superconductorground truth scoreHurt
increase model optimization steps while using a small model learning rate (ablation)NEMO · MoleculeActivityground truth scoreImproved
increase model optimization steps while using a high model learning rate (ablation)NEMO · MoleculeActivityground truth scoreNo clear effect
use NEMO instead of the strongest baselineoffline MBO · 100th-percentile scores across six Design-bench tasksground truth scoreMixed
use NEMO instead of the strongest baselineoffline MBO · 50th-percentile scores across six Design-bench tasksground truth scoreMixed

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