AI & ML
Why Finite Intelligence Works in an Infinite World: A Mathematical Theory
arXiv stat.ML0 views
arXiv:2611.18538v1 Announce Type: cross Abstract: An information system often has to learn before it knows what it will be asked. A finite representation can succeed without recording an infinite environment in full when those asks share collective structure, rather than demand unrelated facts scattered arbitrarily across it. We formalize this phenomenon through future-task information, the minimum retained information needed to preserve decision value relative to the available evidence. A joint decision-regret state records posterior comparisons among actions for every permitted task. Under compactness assumptions, every retained representation admits a calibrated replacement based on this state, preserving all task regrets without increasing information; the resulting information-regret curve equals an operational coding rate. Two exact boundaries govern finite preservation: weak-star closure for a fixed action count, and the singular mass of the source-evidence law when all finite action menus are admitted. Collective structure determines information requirements beyond individual-question difficulty. Families with identical source laws, pairwise task metrics, and individual-task rates can have different high-resolution exponents. Covariance-identical coordinate and parity families have different exact rate-distortion curves, with optimal parity retention characterized by a sharp Fourier-entropy inequality. For balanced nested task families, refinement sizes and weighted reach determine the rate within an additive constant, attained by prefix coding under explicit decay conditions. Nonlinear learning and computational separations distinguish preservation from efficient discovery and use. The proposed mathematical theory identifies which shared decision requirements allow finite information to remain useful for infinitely many possible purposes.
Source:https://arxiv.org/abs/2611.18538PreviousOn numerical issues of divergences between nearly equal distributionsNextRecovering the Euclidean Geometry of High-Dimensional Data Under Heterogeneous Noise
Related posts
Your enterprise AI access can be sold for pennies – beware ‘LLM Mixers’
0ZDNet
Quantum neural networks with high-dimensional quantum neurons
0Phys.org Tech
Less data, faster discovery: Researchers rethink AI's role in developing new materials
0Phys.org Tech
What makes 'super shoes' so fast?
0Phys.org Tech

Amazon’s Starlink rival sees major setback after 40 satellites destroyed in rocket failure
0Tom's Hardware

Unlock Tom's Hardware Premium's SuperComputer 2026 coverage for free — sign up for an account to read detailed reports from the show
0Tom's Hardware