AI Paper Atlas

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

End-to-End Deep Learning for Predicting Metric Space-Valued Outputs

Yidong Zhou, Su I Iao, Hans-Georg Müller

JMLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 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 E2M instead of deep Frechet regressionE2M · Simulation, distribution outputs (n=500)MSPE: 0.869 -> 0.562Improved
use E2M instead of deep Frechet regressionE2M · Simulation, network outputs (n=2000)MSPE: 3.018 -> 1.729Improved
use E2M instead of RFWLFRE2M · Simulation, SPD outputs power metric (n=2000)MSPE: 0.637 -> 0.187Improved
increase sample size from 500 to 2000E2M · Simulation, distribution outputsMSPE: 0.562 -> 0.218Improved
use anchor-based strategy with n=10,000E2M · Simulation, distribution outputsMSPE: 0.218 -> 0.088Improved
use E2M instead of GFR with anchors at n=10,000E2M · Simulation, network outputs (n=10000)MSPE: 9.416 -> 1.072Improved
use E2M instead of DFRE2M · Human mortalityMSPE: 26.75 -> 22.64Improved
use E2M instead of DFRE2M · Taxi networkMSPE: 7.93 -> 6.83Improved
use E2M instead of GFR when the true relationship is linearE2M · Simulation, linear distribution outputs (n=2000)MSPE: 0.188 -> 0.015Hurt
use E2M instead of IFR at small sample sizeE2M · Simulation, distribution outputs (n=50)MSPE: 1.151 -> 1.103Hurt
add mild negative entropy regularization lambda=-0.01 instead of 0 (ablation)E2M · Simulation, distribution outputs (n=2000)MSPE: 0.444 -> 0.291Improved
use strong positive entropy regularization lambda=0.1 instead of 0 (ablation)E2M · Simulation, distribution outputs (n=2000)MSPE: 0.444 -> 1.033Hurt

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