AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Statistical Learning under Heterogenous Distribution Shift

Max Simchowitz, Anurag Ajay, Pulkit Agrawal, Akshay Krishnamurthy

ICML 2023 · Label-efficient and robust learning › Test-time adaptation · approach: Characterizing out-of-distribution failures

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 additive predictor f(x)+g(y) fit by ERM (structure separating simple feature x from complex feature y)ERM under heterogeneous covariate shift · Synthetic additive regressionMSE under distribution shiftImproved
Shift in simpler feature (background) instead of complex feature (birdtype)Standard-trained classifier on Waterbird · Waterbirdbirdtype prediction accuracyNo clear effect
Shift in simpler attribute (bald) instead of complex attribute (big_lips)Logical operator classifiers on CelebA · CelebA OR/XORsuccess rate under shiftImproved
Shift in simpler factor (object mass) instead of complex factor (dampness)Imitation policy on Pusher Control · Pusher Controlsuccess rate under shiftImproved
Replace naive covariate-shift bound with additive decomposition bound (nu_1 Rtrain[f] + nu_2 Rtrain(f,g))ERM theory · Theoretical boundexcess test risk boundImproved
Holder-style Dudley inequality for Hadamard products used to bound cross-critical radius (vs multiplying Dudley functionals)Cross-critical radius bound · Theorybound on cross-critical radiusImproved
Replace orthogonal ML double-training with single-step ERM without auxiliary supervisionEstimation of f_star · Theory vs orthogonal MLrate for f recoveryMixed

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