Approximate Computation via Le Cam Simulability

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Akdemir, Deniz
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908741483364352
author Akdemir, Deniz
author_facet Akdemir, Deniz
contents We propose a decision-theoretic framework for computational complexity, complementary to classical theory: moving from syntactic exactness (Turing / Shannon) to semantic simulability (Le Cam). While classical theory classifies problems by the cost of exact solution, modern computation often seeks only decision-valid approximations. We introduce a framework where "computation" is viewed as the efficient simulation of a target statistical experiment within a bounded risk distortion (Le Cam deficiency). We formally define computational deficiency ($δ_{\text{poly}}$) and use it to construct the complexity class LeCam-P (Decision-Robust Polynomial Time), characterizing problems that may be syntactically hard but semantically easy to approximate. We show that classical Karp reductions can be viewed as zero-deficiency simulations, and that approximate reductions correspond to bounded deficiency. Furthermore, we establish the No-Free-Transfer Inequality, showing that strictly invariant representations inevitably destroy decision-relevant information. This framework offers a statistical perspective on approximation theory, bridging the gap between algorithmic complexity and decision theory.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24860
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Approximate Computation via Le Cam Simulability
Akdemir, Deniz
Statistics Theory
Computational Complexity
Information Theory
We propose a decision-theoretic framework for computational complexity, complementary to classical theory: moving from syntactic exactness (Turing / Shannon) to semantic simulability (Le Cam). While classical theory classifies problems by the cost of exact solution, modern computation often seeks only decision-valid approximations. We introduce a framework where "computation" is viewed as the efficient simulation of a target statistical experiment within a bounded risk distortion (Le Cam deficiency). We formally define computational deficiency ($δ_{\text{poly}}$) and use it to construct the complexity class LeCam-P (Decision-Robust Polynomial Time), characterizing problems that may be syntactically hard but semantically easy to approximate. We show that classical Karp reductions can be viewed as zero-deficiency simulations, and that approximate reductions correspond to bounded deficiency. Furthermore, we establish the No-Free-Transfer Inequality, showing that strictly invariant representations inevitably destroy decision-relevant information. This framework offers a statistical perspective on approximation theory, bridging the gap between algorithmic complexity and decision theory.
title Approximate Computation via Le Cam Simulability
topic Statistics Theory
Computational Complexity
Information Theory
url https://arxiv.org/abs/2512.24860