AI Paper Atlas

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

Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems

Tongtong Fang, Nan Lu, Gang Niu, Masashi Sugiyama

NeurIPS 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 2 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 GIW instead of DIW under support shiftimportance weighting · MNIST (iii)accuracy: 80.53 -> 95.16Improved
use GIW instead of DIW under support shiftimportance weighting · Color-MNIST (iii)accuracy: 39.50 -> 93.87Improved
use GIW instead of DIW under support shiftimportance weighting · CIFAR-20 (iii)accuracy: 55.78 -> 59.73Improved
use CCSA domain adaptation instead of GIWGIW · CIFAR-20 (iii)accuracy: 59.73 -> 60.87Mixed
add label noise 0.4 and compare DANNDANN · MNIST LN 0.4accuracy: 87.24 -> 65.56Hurt
class-prior shift rho=100 for CCSACCSA · MNIST CS 100accuracy: 94.37 -> 72.67Hurt
flip OOT validation data into IT (rate 0.7) (ablation)GIW · MNIST LN 0.2accuracy: 94.60 -> 86.76Hurt
flip IT validation data into OOT (rate 0.7) (ablation)GIW · MNIST LN 0.2accuracy: 94.60 -> 93.55Hurt
flip IT validation data into OOT (rate 0.7) (ablation)GIW · MNIST LN 0.4accuracy: 93.74 -> 90.53Hurt
vary training size n_tr from 10000 to 20000 (ablation)GIW · MNIST LN 0.2accuracyNo clear effect
increase validation data n_v from 10 to 20 (ablation)GIW · MNIST LN 0.2accuracyImproved
use loss-value representation (GIW-L) instead of hidden-layer output (ablation)GIW · MNIST LN 0.2accuracyImproved

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