AI Paper Atlas

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

From Individual Calibration to Reliable Classifiers: ALD Parameterization with mPAIC Guarantees

Deming Sheng, Ricardo Henao

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Confidence calibration objectives

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
replace Softmax with the asymmetric Laplace distribution (ALD) classifier (ablation)distribution-based classifier · 9 datasets (Figure 2a)overall average rank: 4.21 -> 3.00Improved
replace Softmax with ALD classifier (ablation)distribution-based classifier · 9 datasets, ECE rank (Figure 2b)ECE average rank: 4.58 -> 3.07Improved
add ICALD individualized calibration objective (pre-calibration) to the ALD classifierHALD · 9 datasets, 45 settingsoverall average rank: 6.10 -> 4.65Improved
add ICALD calibration as post-calibration adapter instead of temperature scalingHALD · 9 datasets, 45 settingsoverall average rank: HALD+TS 7.23 -> HPost-ICALD 5.03Improved
add ICALD pre-calibration to ALD vs MMD distribution matchingHALD · 9 datasets, KCE rankKCE average rank: HALD+MMD 3.49 vs HPre-ICALD 4.24Hurt
add post-hoc temperature scaling to SoftmaxHSoftmax · 9 datasets, 45 settingsoverall average rank: 7.11 -> 7.74Hurt
add post-hoc histogram binning to SoftmaxHSoftmax · 9 datasets, 45 settingsoverall average rank: 7.11 -> 8.72Hurt
add MMD pre-calibration to SoftmaxHSoftmax · 9 datasets, 45 settingsoverall average rank: 7.11 -> 6.23Improved
allow calibration gradients to update the backbone (Full Grad) instead of detaching them (ablation)HALD · Fisher Ratio on BREAST-CANCER, SST-2Fisher RatioHurt
add gradient detachment (DDSO) to calibration stream (ablation)HICALD · Fisher Ratio across datasetsFisher RatioImproved
add gradient detachment (DDSO) to calibration stream (ablation)HICALD · training costrelative train+inference time: 1x -> 0.554xImproved
use ALD instead of Softmaxclassifier head · training time relative to Softmaxrelative wall-clock time: 1.020xNo 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