Scholarlink

We introduce Perception Learning (PeL), a paradigm that optimizes an agent’s sensory interface \(f_\phi :\mathcal {X}\rightarrow \mathcal {Z}\) using task-agnostic signals, decoupled from downstream decision learning \(g_\theta :\mathcal {Z}\rightarrow \mathcal {Y}\) . 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.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Perception Learning: A Formal Separation of Sensory Representation Learning from Decision Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Suman Sanyal

摘要

We introduce Perception Learning (PeL), a paradigm that optimizes an agent’s sensory interface \(f_\phi :\mathcal {X}\rightarrow \mathcal {Z}\) using task-agnostic signals, decoupled from downstream decision learning \(g_\theta :\mathcal {Z}\rightarrow \mathcal {Y}\) . 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.