cs.AINov 12, 2026

When Does Less Information Pay? An Exact Finite Atlas of Representation, Payoff, and Cost

Authors: Aleksandr M. Shtraukh-Adamsky, Vladimir M. Adamsky, Irina G. Voloshina, Artemiy D. Spitsyn

Organizations: Independent researchers, Moscow, Russia

Abstract

A representation that retains one bit about a four-state world can solve a task perfectly, while another that retains 1.5 bits on average reaches only 75% accuracy. The difference lies in which distinctions each representation preserves. We examine this relationship in a uniform four-state world by enumerating all admissible representations and binary action rules. Constructions are compared both by replacing one component while holding the others fixed and by choosing the best action rule separately for each module. We consider three tasks, their mixtures, and four separate hypothetical cost tariffs. In some comparisons, the representation retaining less world information has the higher payoff; in others, the more informative representation does. There are also pairs with different information amounts but equal payoff--that is, equal task accuracy. If a representation preserves all existing distinctions and adds new ones, its best zero-cost payoff cannot decrease. Lower-information advantages therefore depend on which distinctions are retained. Equal counts of opposing advantages under representation replacement follow from coding symmetry. In broader comparisons, the shares depend on how repeated realizations are counted. A different task set or resource price can change which member of a fixed pair performs better. These results are exact, complete censuses of the specified finite sets of constructions and comparisons. The atlas provides a reproducible worked model for examining how action constraints, counting rules, and cost assumptions affect comparisons. It illustrates established distinctions between information quantity and decision value rather than proposing a new general law of their relation. I(W;R)I(W;R) measures retained world information, and payoff measures task accuracy.

Figures & tables

Explore similar work

CardsList
  1. Bayes-Sufficient Representations in Supervised Learning

    Jun 2, 2026Vasileios SevetlidisRepresentation LearningOutput Elicitation

  2. What Should an Information Bottleneck Encoder Learn? Separating Representation Learning from Rate Control

    Oct 26, 2026Hassan Tavakoli, Bella BoseInformation BottleneckRepresentation Learning