arXiv Machine Learning
Aug 4
Information-Theoretic Foundations for Machine Learning
arXiv:2407. 12288v5 Announce Type: replace-cross Abstract: The progress of machine learning over the past decade is undeniable.
The Method of Gaps: Exact Expressions for the Generalization Error of Supervised Learning Algorithms
arXiv:2411. 12030v3 Announce Type: replace Abstract: In this paper, the method of gaps, a technique for deriving closed-form expressions in terms of information measures for the generalization error of supervised learning algorithms, is introduced.
Related stories
arXiv Machine Learning
Jun 15
A General Framework for Decision Trees via Bregman Divergences
arXiv:2606. 13984v1 Announce Type: cross Abstract: Decision trees are one of the fundamental tools in statistical learning due to their interpretability, flexibility, and their ability to adapt to nonlinear structures.
arXiv AI
Jul 15
Solution of the Hempel's statistical ambiguity problem and Causal AI
arXiv:2607. 12826v1 Announce Type: new Abstract: This paper addresses Carl Hempel's longstanding problem of statistical ambiguity in inductive-statistical inference, in which contradictory predictions are derived from statistical laws.
Hugging Face Trending Papers
Jul 14
Solution of the Hempel's statistical ambiguity problem and Causal AI
This paper addresses Carl Hempel's longstanding problem of statistical ambiguity in inductive-statistical inference, in which contradictory predictions are derived from statistical laws. To avoid such predictions, Carl Hempel proposed the Requirement of Maximal Specificity (RMS) for the statistical laws used in the inference.
arXiv AI
Aug 3
A Generalized-Bayes Perspective on Counterfactual Explanations: Posterior-Based Decision-Making and Evaluation
arXiv:2607. 29077v1 Announce Type: new Abstract: Counterfactual explanations (CEs) enhance the interpretability of machine learning models by identifying the smallest change to an input required to obtain a desired output.
arXiv Machine Learning
Aug 7
A Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies
arXiv:2608. 05995v1 Announce Type: new Abstract: Reliable uncertainty estimates are critical in safety-sensitive applications, where understanding the sources of predictive uncertainty is essential.
arXiv Machine Learning
Jul 7
Distribution-free Deviation Bounds and The Role of Domain Knowledge in Learning via Model Selection with Cross-validation Risk Estimation
arXiv:2303. 08777v3 Announce Type: replace-cross Abstract: Cross-validation is one of the most widely used tools for risk estimation and model selection in statistics and machine learning, yet its theoretical properties when embedded in a learning procedure remain insufficiently understood.
arXiv AI
Aug 12
On Solomonoff Induction in Large Language Models and the Limits of Self-Improving: The Singularity Is Not Near Without Symbolic Model Synthesis
arXiv:2601. 05280v3 Announce Type: replace-cross Abstract: On the one hand, the question of whether large language models (LLMs) are Solomonoff induction estimators has become an explicit question at the intersection of Algorithmic Information Theory (AIT) and Machine Learning (ML) of great interest.
arXiv Machine Learning
Jun 2
A Theoretical Framework for Statistical Evaluability of Generative Models
arXiv:2604. 05324v2 Announce Type: replace Abstract: Statistical evaluation aims to estimate the generalization performance of a model using held-out i.
arXiv AI
Jun 19
Information Lattice Learning as Probabilistic Graphical Model Structure Learning
arXiv:2606. 19366v1 Announce Type: cross Abstract: Information lattice learning (ILL) learns interpretable rules of a signal by alternately projecting the signal onto a partition lattice that encodes a hierarchy of abstractions and lifting selected rules back to the signal domain.
arXiv Machine Learning
Jun 25
Certification of Machine Learning Models via Directional Sharpness
arXiv:2606. 25004v1 Announce Type: new Abstract: In machine learning, model certification has been identified as an important method for gaining assurance about a model's trustworthiness and quality.
arXiv AI
Jun 19
Computational Identifiability
arXiv:2606. 19361v1 Announce Type: cross Abstract: Identification conditions describe the computability of a target query or parameter of interest as a function of the type and amount of information available.