Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspective 文章

ArXiv CS.CV2026-07-31PAPERen作者: Rishabh Iyer, Truong Pham, Anay Majee

详细信息

来源站点
ArXiv CS.CV
作者
Rishabh Iyer, Truong Pham, Anay Majee
文章类型
PAPER
语言
en
发布日期
2026-07-31

摘要

arXiv:2607.27660v1 Announce Type: cross Abstract: Submodular Information Measures (SIMs) have recently emerged as a powerful framework for representation learning and multimodal learning. In particular, the SCORE framework~\cite{majee2024score} demonstrated that SIMs can serve as effective objectives for supervised contrastive learning. Despite their empirical success, however, the geometric and statistical properties induced by different submodular information measures remain poorly understood. In this work, we develop a unified theoretical framework connecting SIMs to classical concepts in representation learning and statistical pattern recognition. We show that Total Information (TI) objectives characterize intra-class structure: Graph Cut TI recovers within-class variance, LogDet TI recovers generalized variance and covariance volume, and Facility Location TI induces imbalance-aware separation that emphasizes rare and confusable classes.

相关事件

暂无数据

相关公司查看全部 (3)

A
ANDINONPROFIT
A
AT TCOMPANY

相关人物

暂无数据