中文
相关论文

相关论文: Bad Universal Priors and Notions of Optimality

200 篇论文

It has been demonstrated earlier that universal computation is 'almost surely' chaotic. Machine learning is a form of computational fixed point iteration, iterating over the computable function space. We showcase some properties of this…

机器学习 · 计算机科学 2014-07-29 Nabarun Mondal , Partha P. Ghosh

Enormous attention and resources are being devoted to the quest for artificial general intelligence and, even more ambitiously, artificial superintelligence. We wonder about the implications for methodological research that aims to help…

计量经济学 · 经济学 2026-05-19 Jeff Dominitz , Charles F. Manski

We introduce the notion of universal memcomputing machines (UMMs): a class of brain-inspired general-purpose computing machines based on systems with memory, whereby processing and storing of information occur on the same physical location.…

神经与进化计算 · 计算机科学 2015-12-17 Fabio L. Traversa , Massimiliano Di Ventra

Since its inception, artificial intelligence has relied upon a theoretical foundation centered around perfect rationality as the desired property of intelligent systems. We argue, as others have done, that this foundation is inadequate…

人工智能 · 计算机科学 2014-11-17 S. J. Russell , D. Subramanian

Generative artificial intelligence (AI) holds enormous potential to revolutionize decision-making processes, from everyday to high-stake scenarios. By leveraging generative AI, humans can benefit from data-driven insights and predictions,…

综合经济学 · 经济学 2024-02-19 Valerio Capraro , Roberto Di Paolo , Veronica Pizziol

Reinforcement learners are agents that learn to pick actions that lead to high reward. Ideally, the value of a reinforcement learner's policy approaches optimality--where the optimal informed policy is the one which maximizes reward.…

机器学习 · 计算机科学 2021-05-27 Michael K. Cohen , Elliot Catt , Marcus Hutter

Developments in the field of Artificial Intelligence (AI), and particularly large language models (LLMs), have created a 'perfect storm' for observing 'sparks' of Artificial General Intelligence (AGI) that are spurious. Like simpler models,…

人工智能 · 计算机科学 2024-06-03 Patrick Altmeyer , Andrew M. Demetriou , Antony Bartlett , Cynthia C. S. Liem

The goal of explainable Artificial Intelligence (XAI) is to generate human-interpretable explanations, but there are no computationally precise theories of how humans interpret AI generated explanations. The lack of theory means that…

人工智能 · 计算机科学 2022-06-10 Scott Cheng-Hsin Yang , Tomas Folke , Patrick Shafto

According to our current conception of physics, any valid physical theory is supposed to describe the objective evolution of a unique external world. However, this condition is challenged by quantum theory, which suggests that physical…

量子物理 · 物理学 2020-07-21 Markus P. Mueller

This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. Our approach is based on a direct approximation of AIXI, a Bayesian optimality notion for general reinforcement learning agents.…

人工智能 · 计算机科学 2010-12-30 Joel Veness , Kee Siong Ng , Marcus Hutter , William Uther , David Silver

In this work, we formally prove that, under certain conditions, if a neural network is invariant to a finite group then its weights recover the Fourier transform on that group. This provides a mathematical explanation for the emergence of…

机器学习 · 计算机科学 2024-06-17 Giovanni Luca Marchetti , Christopher Hillar , Danica Kragic , Sophia Sanborn

There have been two major lines of research aimed at capturing resource-bounded players in game theory. The first, initiated by Rubinstein, charges an agent for doing costly computation; the second, initiated by Neyman, does not charge for…

计算机科学与博弈论 · 计算机科学 2013-08-20 Joseph Y. Halpern , Rafael Pass , Lior Seeman

Machine learning systems increasingly make life-changing decisions about individuals, such as loan approvals, hiring, and cheating detection, raising a pressing question: how can individuals respond to negative decisions made by these…

机器学习 · 统计学 2026-05-18 Timo Freiesleben , Kristof Meding , Gunnar König

Reasoning under uncertainty is a fundamental challenge in Artificial Intelligence. As with most of these challenges, there is a harsh dilemma between the expressive power of the language used, and the tractability of the computational…

人工智能 · 计算机科学 2025-05-08 Luise Ge , Brendan Juba , Kris Nilsson

People solve different problems and know that some of them are simple, some are complex and some insoluble. The main goal of this work is to develop a mathematical theory of algorithmic complexity for problems. This theory is aimed at…

计算复杂性 · 计算机科学 2008-07-08 Mark Burgin

If we could define the set of all bad outcomes, we could hard-code an agent which avoids them; however, in sufficiently complex environments, this is infeasible. We do not know of any general-purpose approaches in the literature to avoiding…

人工智能 · 计算机科学 2020-06-17 Michael K. Cohen , Marcus Hutter

The halting problem is undecidable --- but can it be solved for "most" inputs? This natural question was considered in a number of papers, in different settings. We revisit their results and show that most of them can be easily proven in a…

逻辑 · 数学 2017-01-11 Laurent Bienvenu , Damien Desfontaines , Alexander Shen

An action of a group on a vector space partitions the latter into a set of orbits. We consider three natural and useful algorithmic "isomorphism" or "classification" problems, namely, orbit equality, orbit closure intersection, and orbit…

数据结构与算法 · 计算机科学 2021-10-22 Peter Bürgisser , M. Levent Doğan , Visu Makam , Michael Walter , Avi Wigderson

This paper establishes a theoretical foundation for understanding the fundamental limits of AI explainability through algorithmic information theory. We formalize explainability as the approximation of complex models by simpler ones,…

人工智能 · 计算机科学 2025-11-04 Shrisha Rao

Existing observational approaches for learning human preferences, such as inverse reinforcement learning, usually make strong assumptions about the observability of the human's environment. However, in reality, people make many important…

机器学习 · 统计学 2021-10-29 Cassidy Laidlaw , Stuart Russell