0

A Differential Theory of Quality-Resource Trade-offs for AI Model Selection: The Multiresource Frontier and Its Minimax Price

Comparing AI models across resource budgets yields quality-resource frontiers relating error to latency, parameter count, training compute, and energy. Offset power laws summarize such frontiers, but their fitted parameters reveal neither the price-independent geometry nor the…

Preview
Year
2026
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2611.23324ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Comparing AI models across resource budgets yields quality-resource frontiers relating error to latency, parameter count, training compute, and energy. Offset power laws summarize such frontiers, but their fitted parameters reveal neither the price-independent geometry nor the manner in which trade-offs extend across several resource channels. This paper addresses both gaps by developing a differential theory in which this structure is made explicit. Each frontier admits a price-independent plane-curve representation relating the effective number of active resource channels, N_{eff} = s^2/κ (squared slope over curvature), to the remaining log-error depth, ΔS = \ln(\varepsilon/\varepsilon_{\infty}). This representation separates intrinsic shape from the scale and origin of the resource axis. Complete monotonicity and divisibility yield differential inequalities and frontier bounds. When each of N resources contributes one active channel, the theory gives the parameter-free operating rule N_{eff} = 1 in delivered units and derives minimax resource prices λ^{\star}_i = α_i/(N+1) with an exact worst-case regret of \ln(N+1) nats. The results make it possible to interpret measured frontiers and compare resource costs without hand-chosen exchange rates. The theory is evaluated on 117 published frontiers and implemented in the open-source package nn-rank, which derives prices from measured quality and cost, ranks candidates, and reports supported choices and minimax regret: https://github.com/ABrain-One/nn-rank