AI Paper Atlas

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

Investigating the Histogram Loss in Regression

Ehsan Imani, Kai Luedemann, Sam Scholnick-Hughes, Esraa Elelimy, Martha White

JMLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 10 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
replace l2 loss with HL-GaussMLP regressor · CT PositionTest MAE: 0.176 -> 0.098Improved
use Gaussian target distribution instead of Dirac delta (HL-OneBin) (ablation)histogram loss · CT PositionTest MAE: 0.335 -> 0.098Improved
use Gaussian target instead of zero-bias projected target (ablation)histogram loss · CT PositionTest MAE: 0.103 -> 0.098Improved
replace l2 with softmax output and per-bin l2 lossMLP regressor · CT PositionTest MAE: 0.176 -> 0.105Improved
add target noise or gradient clipping to l2l2 regression · CT PositionTest MAE: 0.176 -> 0.152Improved
add uniform component to target distribution (HL-Uniform) (ablation)histogram loss · CT PositionTest MAEHurt
use histogram loss with fixed random representation (ablation)MLP last layer only · CT Position (random representation)Test MAE: 9.305 -> 2.727Improved
initialize l2 network with HL-Gauss representation (ablation)l2 regression · CT PositionTest MAE: 0.176 -> 0.185No clear effect
add distribution prediction as auxiliary task to l2 (Multi-Task) (ablation)l2 regression · CT PositionTest MAENo clear effect
add higher-moment prediction auxiliary tasks to l2 (ablation)l2 regression · CT PositionTest MAENo clear effect
anneal sigma from high to low during training (ablation)HL-Gauss · Song Year and Bike SharingTest MAEImproved
replace l2 with HL-Gauss for LSTM time-series predictionLSTM · ETTh1Test MSE: 0.775 -> 0.6575Improved

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