AI Paper Atlas

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

Which Invariance Should We Transfer? A Causal Minimax Learning Approach

Mingzhou Liu, Xiangyu Zheng, Xinwei Sun, Fang Fang, Yizhou Wang

ICML 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 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
Select a stable subset by minimizing estimated worst-case riskCausal minimax learning approach · ADNImax. MSE: 0.890 vs 1.069Improved
Select a stable subset by minimizing estimated worst-case riskCausal minimax learning approach · Syn2max. MSE: 1.079 vs 1.079No clear effect
Select a stable subset by minimizing estimated worst-case riskCausal minimax learning approach · ADNIstd. MSE: 0.299 -> 0.038Improved
Search equivalence classes rather than all stable subsetsCausal minimax learning approach · ADNIsearching cost: $2^{25}$ -> $25307$; about 6.4y -> 42hImproved
Use validation loss rather than estimated worst-case risk to rank stable subsetsSurgery estimator · ADNImax. MSE: 0.890 vs 1.069Hurt

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