AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Contrastive Neural Ratio Estimation

Benjamin Kurt Miller, Christoph Weniger, Patrick Forré

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 1 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 NRE-C instead of NRE-B (multiclass with bias term)NRE · SBI benchmark, 10^3 simulationsC2ST: 0.867 -> 0.853Improved
Use NRE-C instead of NRE-BNRE · SBI benchmark, 10^4 simulationsC2ST: 0.811 -> 0.762Improved
Use NRE-C instead of NRE-BNRE · SBI benchmark, 10^5 simulationsC2ST: 0.762 -> 0.680Improved
NRE-C versus amortized NPENRE-C · SBI benchmark, 10^5 simulationsC2ST: 0.654 -> 0.680No clear effect
NRE-C versus NLENRE-C · SBI benchmark, 10^4 simulationsC2ST: 0.753 -> 0.762No clear effect
NRE-C versus sequential SNRENRE-C · SBI benchmark, 10^5 simulationsC2ST: 0.610 -> 0.680Hurt
Increase number of contrastive parameters K with unlimited data (ablation)NRE-B and NRE-C · Draw (theta, x) every mini-batch, 3 SBI tasksC2STImproved
Vary gamma with unlimited data (ablation)NRE-C · Draw (theta, x) every mini-batchC2STNo clear effect
Use Large NN (128 units, 3 residual blocks) instead of Small NN (50 units, 2 blocks) (ablation)NRE-C · SBI tasks, esp. SLCPC2STImproved
Draw contrastive parameters from the prior each mini-batch (ablation)NRE-B and NRE-C · 3 SBI tasksC2ST sensitivity to KImproved
Lower gamma with Large NN (ablation)NRE-C · Draw theta / fixed data regimesC2STNo clear effect
Increase K with fixed gamma (ablation)NRE-C · SLCP, mutual information bound-I_w^(0) boundMixed

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