AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

ExPT: Synthetic Pretraining for Few-Shot Experimental Design

Tung Nguyen, Sudhanshu Agrawal, Aditya Grover

NeurIPS 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-tuning strategies for few-shot

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
replace inverse modeling with forward modeling (TNP-ED + gradient ascent) (ablation)ExPT · Design-Bench poorest, D'Kittymean score: 0.871 -> 0.405Hurt
replace inverse modeling with forward modeling (TNP-ED + gradient ascent) (ablation)ExPT · Design-Bench random, Antmean score: 0.639 -> 0.451Hurt
make GP length scale too small (U[0.1, 1.0]) (ablation)ExPT · Design-Bench random, Antmean score: 0.639 -> 0.518Hurt
make GP length scale too large (U[100, 200]) (ablation)ExPT · Design-Bench random, Antmean score: 0.639 -> 0.528Hurt
make GP function scale too large (U[100, 200]) (ablation)ExPT · Design-Bench random, Antmean score: 0.639 -> 0.534Hurt
make GP function scale too small (U[0.01, 0.1]) (ablation)ExPT · Design-Bench D'Kitty mean scoremean score: 0.865 -> 0.896 (random); 0.871 -> 0.755 (poorest)Mixed
pretrain on GP-Cosine instead of GP-RBF data (ablation)ExPT · Design-Bench random, mean over 4 tasksmean score: 0.614 -> 0.525Hurt
pretrain on trained-MLP generated functions instead of GP-RBF (ablation)ExPT · Design-Bench random, mean over 4 tasksmean score: 0.614 -> 0.625No clear effect
replace VAE decoder with diffusion decoder (ablation)ExPT · Design-Bench random, mean over 4 tasksmean score: 0.614 -> 0.575Hurt
replace VAE decoder with diffusion decoder (ablation)ExPT · Design-Bench poorest, mean over 4 tasksmean score: 0.639 -> 0.514Hurt
use sequential sampling with feedback instead of simultaneous sampling (ablation)ExPT · Design-Bench poorest, Antmean score: 0.646 -> 0.767Improved
sort context and target points during pretraining (ablation)ExPT · Design-Bench random, D'Kittymean score: 0.865 -> 0.794Hurt

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