AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetry

Xunye Tian, Zhijian Zhou, Liuhua Peng, Feng Liu

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 0 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
add uncertainty-guided selection/weighting of RDRs (ablation)LOTTERY · BLOB (N=4000, M=20)test power: 0.411 -> 0.524Improved
add uncertainty-guided selection/weighting of RDRs (ablation)LOTTERY · CIFAR10-RES18 (N=100, M=4)test power: 0.916 -> 0.966Improved
add uncertainty-guided selection with large query size (ablation)LOTTERY · BLOB (N=4000, M=300)test power: 0.995 -> 1.000No clear effect
aggregate multiple RDR families instead of a single RDR (ablation)LOTTERY · Synthetic alternatives (N=4000, M=50)test power: 0.320 -> 0.442 (mean shift, vs Mahalanobis)Improved
learn representations from reference only instead of splitting query dataLOTTERY vs split-based tests · CIFAR10-RES18 (N=100, M=2)test power: 0.810 vs 0.105 (RL-TST)Improved
increase reference size N with few queriesLOTTERY · BLOB (M=50)test power: 0.082 -> 0.725Improved
very small reference set (N=100)LOTTERY · BLOB (M=50, N=100)test power: 0.082 vs 0.122 (MMD-FUSE)Hurt
increase reference size for baselinesMMD-FUSE · BLOB (M=50)test power: 0.122 -> 0.145No clear effect
weight RDRs by sensitivity divided by uncertainty rather than inverse uncertainty aloneLOTTERY · design argumenttest powerNo clear effect

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