A bilevel optimization framework smooths isotonic regression outputs into continuous piece-wise linear monotonic functions to recover marginal properties in both convex and non-convex cases.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
LLM inference should be reframed and evaluated as energy-to-token production with a Token Production Function that accounts for power, cooling, and efficiency ceilings.
citing papers explorer
-
Piece-wise linear isotonic regression
A bilevel optimization framework smooths isotonic regression outputs into continuous piece-wise linear monotonic functions to recover marginal properties in both convex and non-convex cases.
-
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
LLM inference should be reframed and evaluated as energy-to-token production with a Token Production Function that accounts for power, cooling, and efficiency ceilings.