将感知与决策学习解耦，让模型自动优化感官表征质量。
Perception Learning: A Formal Separation of Sensory Representation Learning from Decision Learning
- 用无标签信号直接优化感知模块的稳定性与信息量
- 证明感知更新方向与任务梯度正交，避免干扰决策
- 提供可验证感知质量的通用评估指标，适合基础表征研究
我们提出感知学习（Perception Learning, PeL），一种将感知表征学习 $f_ϕ:/mathcal{X} o/mathcal{Z}$ 与下游决策学习 $g_θ:/mathcal{Z} o/mathcal{Y}$ 解耦的范式。PeL 使用与任务无关的信号优化感知接口，直接针对稳定性、信息量不退化、几何可控性等无标签感知属性，通过表示不变的客观度量进行评估。我们形式化了感知与决策的分离，定义了独立于目标或重参数化的感知属性，并证明：保持足够不变量的PeL更新方向与贝叶斯任务风险梯度正交。此外，我们提出一套任务无关的评估指标，用于认证感知质量。
原文摘要 · Abstract (English)
We introduce Perception Learning (PeL), a paradigm that optimizes an agent's sensory interface $f_ϕ:\mathcal{X}\to\mathcal{Z}$ using task-agnostic signals, decoupled from downstream decision learning $g_θ:\mathcal{Z}\to\mathcal{Y}$. PeL directly targets label-free perceptual properties, such as stability to nuisances, informativeness without collapse, and controlled geometry, assessed via objective representation-invariant metrics. We formalize the separation of perception and decision, define perceptual properties independent of objectives or reparameterizations, and prove that PeL updates preserving sufficient invariants are orthogonal to Bayes task-risk gradients. Additionally, we provide a suite of task-agnostic evaluation metrics to certify perceptual quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。