Frontend
On numerical issues of divergences between nearly equal distributions
arXiv stat.ML0 views
arXiv:2611.18511v1 Announce Type: cross Abstract: Barron et al. (2026) recently identified numerical issues in the softmax and soft cross-entropy loss. We show that similar issues are present in standard divergence operations between categorical distributions. This includes the forward and reverse Kullback-Leibler (KL) divergence and generalized Jensen-Shannon divergence (JSD), as well as Monte Carlo KL estimates and entropy. When the distributions are nearly equal, rounding and cancellation issues affect the forward and gradient computations. These issues can affect settings using divergences in optimization objectives, such as knowledge distillation, reinforcement learning, and proximal methods. We propose numerically stable reformulations and provide example implementations for each setting, validated by property-based tests.
Source:https://arxiv.org/abs/2611.18511PreviousDynamic bigraphical Mat\'ern--Whittle processes: learning dependence graphs among spatial-temporal fieldsNextWhy Finite Intelligence Works in an Infinite World: A Mathematical Theory
Related posts
VOKE: Visual Object Kinematics Estimator for Dexterous In-Hand Manipulation
0arXiv cs.RO
From Meeting Transcript to Task Queue: Put a Verification Gate in the Data Contract
0dev.to AI
Réserver la place d’une image avant son chargement
0dev.to CSS
7 Arabic Website Localization Mistakes Developers Should Avoid
0dev.to CSS
100 tools in the browser, 9 on a 4 GB server: how we decide where a web tool runs
0dev.to WebDev
Building a face analysis tool that never uploads the photo
0dev.to WebDev