English
Related papers

Related papers: The Computational Boundary of Inference: Capabilit…

200 papers

The illusion phenomenon of large language models (LLMs) is the core obstacle to their reliable deployment. This article formalizes the large language model as a probabilistic Turing machine by constructing a "computational necessity…

Artificial Intelligence · Computer Science 2025-12-09 Wang Xi , Quan Shi , Zenghui Ding , Jianqing Gao , Xianjun Yang

AI systems improve by drawing on more compute, data, energy, and better training methods. This paper asks a precise, testable version of the "runaway growth" question: under what measurable conditions could capability escalate without bound…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Akbar Anbar Jafari , Cagri Ozcinar , Gholamreza Anbarjafari

The unwavering success of deep learning in the past decade led to the increasing prevalence of deep learning methods in various application fields. However, the downsides of deep learning, most prominently its lack of trustworthiness, may…

Machine Learning · Computer Science 2024-08-13 Holger Boche , Vit Fojtik , Adalbert Fono , Gitta Kutyniok

The study of the fundamental limits of information systems is a central theme in information theory. Both the traditional analytical approach and the recently proposed computational approach have significant limitations, where the former is…

Information Theory · Computer Science 2022-05-04 Wenjing Chen , Chao Tian

This paper offers a new perspective on the limits of machine learning: the ceiling on progress is set not by model size or algorithm choice but by the information structure of the task itself. Code generation has progressed more reliably…

Machine Learning · Computer Science 2026-04-14 Zhimin Zhao

In this paper we present theory and algorithms enabling classes of Artificial Intelligence (AI) systems to continuously and incrementally improve with a-priori quantifiable guarantees - or more specifically remove classification errors -…

Machine Learning · Computer Science 2022-05-18 Ivan Y. Tyukin , Alexander N. Gorban , Alistair A. McEwan , Sepehr Meshkinfamfard , Lixin Tang

Sequential hypothesis testing asks for decision rules that update as data arrive. A natural goal is \emph{eventual correctness}: the rule may change its mind early on, but it should make only finitely many wrong decisions almost surely.…

Information Theory · Computer Science 2026-05-05 Amir Leshem

We argue that progress toward AGI is theory limited rather than data or scale limited. Building on the critical rationalism of Popper and Deutsch, we challenge the Platonic Representation Hypothesis. Observationally equivalent worlds can…

Artificial Intelligence · Computer Science 2025-10-20 Marcus A. Thomas

Many constructions in computability theory rely on "time tricks". In the higher setting, relativising to some oracles shows the necessity of these. We construct an oracle~$A$ and a set~$X$, higher Turing reducible to~$X$, but for which…

Logic · Mathematics 2019-12-03 Laurent Bienvenu , Noam Greenberg , Benoit Monin

Models of computation operating over the real numbers and computing a larger class of functions compared to the class of general recursive functions invariably introduce a non-finite element of infinite information encoded in an arbitrary…

Computational Complexity · Computer Science 2010-12-20 Hector Zenil

This paper asks whether a bounded neural architecture can exhibit a meaningful division of labor between intuition and deliberation on a classic 64-item syllogistic reasoning benchmark. More broadly, the benchmark is relevant to ongoing…

Artificial Intelligence · Computer Science 2026-03-25 Laurence Anthony

Classical scaling laws model AI performance as monotonically improving with model size. We challenge this assumption by deriving the Institutional Scaling Law, showing that institutional fitness -- jointly measuring capability, trust,…

Artificial Intelligence · Computer Science 2026-03-17 Mark Baciak , Thomas A. Cellucci

We develop synthetic notions of oracle computability and Turing reducibility in the Calculus of Inductive Constructions (CIC), the constructive type theory underlying the Coq proof assistant. As usual in synthetic approaches, we employ a…

Logic in Computer Science · Computer Science 2023-07-31 Yannick Forster , Dominik Kirst , Niklas Mück

This paper studies the problem of learning computable functions in the limit by extending Gold's inductive inference framework to incorporate \textit{computational observations} and \textit{restricted input sources}. Complimentary to the…

Machine Learning · Computer Science 2025-07-11 Hristo Papazov , Nicolas Flammarion

A mathematical concept is identified and analyzed that is implicit in the 2012 paper Turing Incomputable Computation, presented at the Alan Turing Centenary Conference (Turing-100, Manchester). The concept, called dynamic level sets, is…

Computational Complexity · Computer Science 2026-03-03 Michael Stephen Fiske

The possibility of a rapid, "software-only" intelligence explosion brought on by AI's recursive self-improvement (RSI) is a subject of intense debate within the AI community. This paper presents an economic model and an empirical estimation…

General Economics · Economics 2025-08-19 Parker Whitfill , Cheryl Wu

Different types of reasoning impose different structural demands on representational systems, yet no systematic account of these demands exists across psychology, AI, and philosophy of mind. I propose a framework identifying four structural…

Artificial Intelligence · Computer Science 2026-04-03 Yiling Wu

It has been quite a long time since AI researchers in the field of computer science stop talking about simulating human intelligence or trying to explain how brain works. Recently, represented by deep learning techniques, the field of…

Artificial Intelligence · Computer Science 2015-09-30 Hao Wu

A century ago, discoveries of a serious kind of logical error made separately by several leading mathematicians led to acceptance of a sharply enhanced standard for rigor within what ultimately became the foundation for Computer Science. By…

Other Computer Science · Computer Science 2019-06-03 Arthur Charlesworth

This paper argues that continued AI scaling requires repeated efficiency doublings. Classical AI scaling laws remain useful because they make progress predictable despite diminishing returns, but the compute variable in those laws is best…

Machine Learning · Computer Science 2026-04-10 Chien-Ping Lu
‹ Prev 1 2 3 10 Next ›