Perception Learning: A Formal Separation of Sensory Representation Learning from Decision Learning
Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Author: Sanyal, Suman
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7102390189
Cites:
Cited by:
Related to: