PulseAugur
EN
LIVE 22:01:50

New research paper introduces 'loss shift' concept in transfer learning

A new research paper introduces the concept of "loss shift" as a distinct challenge in transfer learning, separate from distribution shift. The paper formalizes this by using Bayes quotients to order losses by refinement, identifying when a representation suitable for a coarser loss is insufficient for a strictly finer target loss. Experiments across various settings demonstrate that classification-equivalent representations can yield different optimal performance under a fixed data distribution when loss functions vary. AI

RANK_REASON The cluster contains a new academic paper on a machine learning topic. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Vasileios Sevetlidis ·

    Loss-Shift Transfer via Bayes Quotients

    Transfer learning is usually studied as a consequence of distribution shift. This paper identifies an orthogonal failure mode in which the data distribution is fixed and the loss changes. This setting is called \emph{loss shift}. A loss determines which information in \(X\) is Ba…