A Theory of Machine Learning

• URL: http://arxiv.org/abs/2407.05520v1
• Date: Sun, 7 Jul 2024 23:57:10 GMT
• Title: A Theory of Machine Learning
• Authors: Jinsook Kim, Jinho Kang,
• Abstract summary: We show that this theory challenges common assumptions in the statistical and the computational learning theories. We briefly discuss some case studies from natural language processing and macroeconomics from the perspective of the new theory.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We critically review three major theories of machine learning and provide a new theory according to which machines learn a function when the machines successfully compute it. We show that this theory challenges common assumptions in the statistical and the computational learning theories, for it implies that learning true probabilities is equivalent neither to obtaining a correct calculation of the true probabilities nor to obtaining an almost-sure convergence to them. We also briefly discuss some case studies from natural language processing and macroeconomics from the perspective of the new theory.

Related papers

• Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models [76.6028674686018]
  We introduce thought-tracing, an inference-time reasoning algorithm to trace the mental states of agents. Our algorithm is modeled after the Bayesian theory-of-mind framework. We evaluate thought-tracing on diverse theory-of-mind benchmarks, demonstrating significant performance improvements.
  arXiv  Detail & Related papers  (2025-02-17T15:08:50Z)
• Machine Learning and Theory Ladenness -- A Phenomenological Account [44.99833362998488]
  We argue that both positions are overly simplistic and do not advance our understanding of the interplay between ML methods and domain theories. Our analysis reveals that, while the construction of models can be relatively independent of domain theory, the practical implementation and interpretation of these models within a given specific domain still relies on fundamental theoretical assumptions and background knowledge.
  arXiv  Detail & Related papers  (2024-09-17T15:29:14Z)
• Review and Prospect of Algebraic Research in Equivalent Framework between Statistical Mechanics and Machine Learning Theory [0.0]
  This paper is devoted to the memory of Professor Huzihiro Araki who is a pioneer founder of algebraic research in both statistical mechanics and quantum field theory.
  arXiv  Detail & Related papers  (2024-05-31T11:04:13Z)
• Machine Learning of the Prime Distribution [49.84018914962972]
  We provide a theoretical argument explaining the experimental observations of Yang-Hui He about the learnability of primes. We also posit that the ErdHos-Kac law would very unlikely be discovered by current machine learning techniques.
  arXiv  Detail & Related papers  (2024-03-19T09:47:54Z)
• Three Conjectures on Unexpectedeness [0.5874142059884521]
  This paper lays the groundwork for three theoretical conjectures. First, unexpectedness can be seen as a generalization of Bayes' rule. Second, the frequentist core of unexpectedness can be connected to the function of tracking ergodic properties of the world.
  arXiv  Detail & Related papers  (2023-11-15T08:24:41Z)
• The role of prior information and computational power in Machine Learning [0.0]
  We discuss how prior information and computational power can be employed to solve a learning problem. We argue that employing high computational power has the advantage of a higher performance.
  arXiv  Detail & Related papers  (2022-10-31T20:39:53Z)
• Incompatibility of observables, channels and instruments in information theories [68.8204255655161]
  We study the notion of compatibility for tests of an operational probabilistic theory. We show that a theory admits of incompatible tests if and only if some information cannot be extracted without disturbance.
  arXiv  Detail & Related papers  (2022-04-17T08:44:29Z)
• Computation in a general physical setting [0.0]
  This paper reviews and extends some results on the computational ability of quantum theory. It provides a refined version of the conjecture that a quantum computer can simulate the computation in any theory. It ends by describing an important relation between this conjecture and delegated computation, similar to the relation between quantum non-locality and device-independent cryptography.
  arXiv  Detail & Related papers  (2021-08-25T20:00:20Z)
• Constrained Learning with Non-Convex Losses [119.8736858597118]
  Though learning has become a core technology of modern information processing, there is now ample evidence that it can lead to biased, unsafe, and prejudiced solutions.
  arXiv  Detail & Related papers  (2021-03-08T23:10:33Z)
• Quantum field-theoretic machine learning [0.0]
  We recast the $phi4$ scalar field theory as a machine learning algorithm within the mathematically rigorous framework of Markov random fields. Neural networks are additionally derived from the $phi4$ theory which can be viewed as generalizations of conventional neural networks.
  arXiv  Detail & Related papers  (2021-02-18T16:12:51Z)
• A Note on High-Probability versus In-Expectation Guarantees of Generalization Bounds in Machine Learning [95.48744259567837]
  Statistical machine learning theory often tries to give generalization guarantees of machine learning models. Statements made about the performance of machine learning models have to take the sampling process into account. We show how one may transform one statement to another.
  arXiv  Detail & Related papers  (2020-10-06T09:41:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.