paper-with-me

홈 › Papers

Theory of Machine Learning with Limited Data

2022-06-15 · Marina Sapir

Application of machine learning may be understood as deriving new knowledge for practical use through explaining accumulated observations, training set. Peirce used the term abduction for this kind of inference. Here I formalize the concept of abduction for real valued hypotheses, and show that 14 of the most popular textbook ML learners (every learner I tested), covering classification, regression and clustering, implement this concept of abduction inference. The approach is proposed as an alternative to statistical learning theory, which requires an impractical assumption of indefinitely increasing training set for its justification.

📄 PDF Abstract BibTeX arXiv:2206.07586

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningClusteringDecision MakingLearning Theoryregression

Methods 이 논문이 사용한 방법론

k-NN $k$-Nearest Neighbors is a clustering-based algorithm for classification and regression. It is a a type of instance-based learning as it does not attempt to construct a…

Similar Papers 제목 키워드 기반

Theory In, Theory Out: The uses of social theory in machine learning for social science

2020-01-09 · Jason Radford, Kenneth Joseph

Research at the intersection of machine learning and the social sciences has provided critical new insights into social behavior. At the same time, a variety of critiques have been raised ranging from technical issues wi…

BIG-bench Machine LearningFairnessNavigate

Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis

2024-05-15 · Daniel Csillag, Claudio José Struchiner, Guilherme Tegoni Goedert

Many algorithms have been recently proposed for causal machine learning. Yet, there is little to no theory on their quality, especially considering finite samples. In this work, we propose a theory based on generalizatio…

Generalization BoundsregressionSensitivity

Deriving Neural Scaling Laws from the statistics of natural language

2026-02-07 · Francesco Cagnetta, Allan Raventós, Surya Ganguli, Matthieu Wyart arxiv

Despite the fact that experimental neural scaling laws have substantially guided empirical progress in large-scale machine learning, no existing theory can quantitatively predict the exponents of these important laws for…

Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models

2020-07-14 · Kim A. Nicoli, Christopher J. Anders, Lena Funcke, Tobias Hartung 외

In this work, we demonstrate that applying deep generative machine learning models for lattice field theory is a promising route for solving problems where Markov Chain Monte Carlo (MCMC) methods are problematic. More sp…

BIG-bench Machine Learning

Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method

2020-12-11 · Yuntian Chen, Dou Huang, Dongxiao Zhang, Junsheng Zeng 외

Machine learning models have been successfully used in many scientific and engineering fields. However, it remains difficult for a model to simultaneously utilize domain knowledge and experimental observation data. The a…

BIG-bench Machine LearningMathematical Proofs