Pith. sign in

REVIEW 1 cited by

ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.02472 v2 pith:JTFWTPXK submitted 2023-03-04 cs.LG cs.AIcs.CLcs.CV

classification cs.LGcs.AIcs.CLcs.CV
keywords calibrationtrainingdifferenceinternalsquaredtrainablebeencomputational
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Studies have shown that modern neural networks tend to be poorly calibrated due to over-confident predictions. Traditionally, post-processing methods have been used to calibrate the model after training. In recent years, various trainable calibration measures have been proposed to incorporate them directly into the training process. However, these methods all incorporate internal hyperparameters, and the performance of these calibration objectives relies on tuning these hyperparameters, incurring more computational costs as the size of neural networks and datasets become larger. As such, we present Expected Squared Difference (ESD), a tuning-free (i.e., hyperparameter-free) trainable calibration objective loss, where we view the calibration error from the perspective of the squared difference between the two expectations. With extensive experiments on several architectures (CNNs, Transformers) and datasets, we demonstrate that (1) incorporating ESD into the training improves model calibration in various batch size settings without the need for internal hyperparameter tuning, (2) ESD yields the best-calibrated results compared with previous approaches, and (3) ESD drastically improves the computational costs required for calibration during training due to the absence of internal hyperparameter. The code is publicly accessible at https://github.com/hee-suk-yoon/ESD.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Training a policy to prefer responses by optimizing only its own low-confidence (high-surprisal) tokens improves alignment over uniform token optimization in SimPO and DPO.

Pith tools