English
Related papers

Related papers: The Computational Boundary of Inference: Capabilit…

200 papers

Large language models now write software, draft legal documents, and produce clinical notes, yet fundamental limits, from Turing and Arrow to the No Free Lunch theorems, shape what computation can do. This thesis turns such impossibility…

Artificial Intelligence · Computer Science 2026-05-25 Dongxin Guo

We initiate a formal study of reproducibility in optimization. We define a quantitative measure of reproducibility of optimization procedures in the face of noisy or error-prone operations such as inexact or stochastic gradient computations…

Optimization and Control · Mathematics 2022-12-06 Kwangjun Ahn , Prateek Jain , Ziwei Ji , Satyen Kale , Praneeth Netrapalli , Gil I. Shamir

We investigate the connection between interference and computational power within the operationally defined framework of generalised probabilistic theories. To compare the computational abilities of different theories within this framework…

Quantum Physics · Physics 2018-07-30 Howard Barnum , Ciarán M. Lee , John H. Selby

We give a number of formal proofs of theorems from the field of computable analysis. Many of our results specify executable algorithms that work on infinite inputs by means of operating on finite approximations and are proven correct in the…

Logic in Computer Science · Computer Science 2023-06-22 Florian Steinberg , Laurent Thery , Holger Thies

Computational modelling offers a powerful tool for formalising psychological theories, making them more transparent, testable, and applicable in digital contexts. Yet, the question often remains: how should one computationally model a…

Artificial Intelligence · Computer Science 2025-05-14 Erik M. Lintunen , Nadia M. Ady , Sebastian Deterding , Christian Guckelsberger

In reinforcement learning, the classic objectives of maximizing discounted and finite-horizon cumulative rewards are PAC-learnable: There are algorithms that learn a near-optimal policy with high probability using a finite amount of samples…

Machine Learning · Computer Science 2023-07-04 Cambridge Yang , Michael Littman , Michael Carbin

From the existence of an efficient quantum algorithm for factoring, it is likely that quantum computation is intrinsically more powerful than classical computation. At present, the best upper bound known for the power of quantum computation…

Quantum Physics · Physics 2015-09-14 Ciarán M. Lee , Jonathan Barrett

The common claim that generative AI simply amplifies the Dunning-Kruger effect is too coarse to capture the available evidence. The clearest findings instead suggest that large language model (LLM) use can improve observable output and…

Artificial Intelligence · Computer Science 2026-04-01 Christopher Koch

Intelligence-biological, artificial, or collective-requires structural coherence across recursive reasoning processes to scale effectively. As complex systems grow, coherence becomes fragile unless a higher-order structure ensures semantic…

Artificial Intelligence · Computer Science 2025-07-23 Andy E. Williams

We introduce an increasing-complexity, open-ended, and human-agnostic metric to evaluate foundational and frontier AI models in the context of Artificial General Intelligence (AGI) and Artificial Super Intelligence (ASI) claims. Unlike…

Artificial Intelligence · Computer Science 2026-02-13 Alberto Hernández-Espinosa , Luan Ozelim , Felipe S. Abrahão , Hector Zenil

Large Language Models (LLMs) often exhibit a gap between their internal knowledge and their explicit linguistic outputs. In this report, we empirically investigate whether Looped Transformers (LTs)--architectures that increase computational…

Computation and Language · Computer Science 2026-01-16 Guanxu Chen , Dongrui Liu , Jing Shao

Despite their impressive performance, contemporary neural networks often lack structural safeguards that promote stable learning and interpretable behavior. In this work, we introduce a reformulation of layer-level transformations that…

Machine Learning · Computer Science 2025-08-04 Saleh Nikooroo , Thomas Engel

As systems trend toward superintelligence, a natural modeling premise is that agents can self-improve along every facet of their own design. We formalize this with a five-axis decomposition and a decision layer, separating incentives from…

Artificial Intelligence · Computer Science 2026-02-03 Charles L. Wang , Keir Dorchen , Peter Jin

Scalable sequence models, such as Transformer variants and structured state-space models, often trade expressivity power for sequence-level parallelism, which enables efficient training. Here we examine the bounds on error and how error…

Machine Learning · Computer Science 2026-03-09 Gyuryang Heo , Timothy Ngotiaoco , Kazuki Irie , Samuel J. Gershman , Bernardo Sabatini

In recent years we observed rapid and significant advancements in artificial intelligence (A.I.). So much so that many wonder how close humanity is to developing an A.I. model that can achieve human level of intelligence, also known as…

Artificial Intelligence · Computer Science 2025-12-08 Georgios Mappouras , Charalambos Rossides

Large Language Models (LLMs) have benefited enormously from scaling, yet these gains are bounded by five fundamental limitations: (1) hallucination, (2) context compression, (3) reasoning degradation, (4) retrieval fragility, and (5)…

Recursive self-improving (RSI) systems have been dreamed of since the early days of computer science and artificial intelligence. However, many existing studies on RSI systems remain philosophical, and lacks clear formulation and results.…

Artificial Intelligence · Computer Science 2018-05-18 Wenyi Wang

Computation fundamentally separates time from space: nondeterministic search is exponential in time but polynomially simulable in space (Savitch's Theorem). We propose that the brain physically instantiates a biological variant of this…

Neurons and Cognition · Quantitative Biology 2025-12-02 Xin Li

Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verified outputs generated by the LLM itself. In contrast to the empirical success of self-improvement, the theoretical foundation of this…

Machine Learning · Computer Science 2026-03-23 Chenruo Liu , Yijun Dong , Yiqiu Shen , Qi Lei

Truly reliable AI requires more than simply scaling up knowledge; it demands the ability to know what it knows and when it does not. Yet recent research shows that even the best LLMs misjudge their own competence in more than one in five…

Computation and Language · Computer Science 2025-10-14 Sahil Kale , Devendra Singh Dhami