A Novel Data-Dependent Learning Paradigm for Large Hypothesis Classes

• URL: http://arxiv.org/abs/2511.09996v1
• Date: Fri, 14 Nov 2025 01:24:51 GMT
• Title: A Novel Data-Dependent Learning Paradigm for Large Hypothesis Classes
• Authors: Alireza F. Pour, Shai Ben-David,
• Abstract summary: We address the general task of learning with a set of candidate models that is too large to have a uniform convergence of empirical estimates to true losses.<n>We propose a novel learning paradigm that relies on stronger incorporation of empirical data and less algorithmic decisions to be based on prior assumptions.
• Score: 4.299934797034146
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We address the general task of learning with a set of candidate models that is too large to have a uniform convergence of empirical estimates to true losses. While the common approach to such challenges is SRM (or regularization) based learning algorithms, we propose a novel learning paradigm that relies on stronger incorporation of empirical data and requires less algorithmic decisions to be based on prior assumptions. We analyze the generalization capabilities of our approach and demonstrate its merits in several common learning assumptions, including similarity of close points, clustering of the domain into highly label-homogeneous regions, Lipschitzness assumptions of the labeling rule, and contrastive learning assumptions. Our approach allows utilizing such assumptions without the need to know their true parameters a priori.

Related papers

• Preference Learning for AI Alignment: a Causal Perspective [55.2480439325792]
  We frame this problem in a causal paradigm, providing the rich toolbox of causality to identify persistent challenges.<n>Inheriting from the literature of causal inference, we identify key assumptions necessary for reliable generalisation.<n>We illustrate failure modes of naive reward models and demonstrate how causally-inspired approaches can improve model robustness.
  arXiv  Detail & Related papers  (2025-06-06T10:45:42Z)
• Probably Approximately Precision and Recall Learning [60.00180898830079]
  A key challenge in machine learning is the prevalence of one-sided feedback.<n>We introduce a Probably Approximately Correct (PAC) framework in which hypotheses are set functions that map each input to a set of labels.<n>We develop new algorithms that learn from positive data alone, achieving optimal sample complexity in the realizable case.
  arXiv  Detail & Related papers  (2024-11-20T04:21:07Z)
• Bounds on the Generalization Error in Active Learning [0.0]
  We establish empirical risk principles for active learning by deriving a family of upper bounds on the generalization error. We systematically link diverse active learning scenarios, characterized by their loss functions and hypothesis classes to their corresponding upper bounds. Our results show that regularization techniques used to constraint the complexity of various hypothesis classes are sufficient conditions to ensure the validity of the bounds.
  arXiv  Detail & Related papers  (2024-09-10T08:08:09Z)
• An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models [20.314426291330278]
  In traditional statistical learning, data points are usually assumed to be independently and identically distributed.<n>This paper presents a contrasting viewpoint, perceiving data points as interconnected.<n>We introduce a generalized temporal difference (TD) learning algorithm as a resolution.
  arXiv  Detail & Related papers  (2024-04-23T21:02:58Z)
• Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical [66.57396042747706]
  Complementary-label learning is a weakly supervised learning problem. We propose a consistent approach that does not rely on the uniform distribution assumption. We find that complementary-label learning can be expressed as a set of negative-unlabeled binary classification problems.
  arXiv  Detail & Related papers  (2023-11-27T02:59:17Z)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• Hypothesis Transfer Learning with Surrogate Classification Losses: Generalization Bounds through Algorithmic Stability [3.908842679355255]
  Hypothesis transfer learning (HTL) contrasts domain adaptation by allowing for a previous task leverage, named the source, into a new one, the target. This paper studies the learning theory of HTL through algorithmic stability, an attractive theoretical framework for machine learning algorithms analysis.
  arXiv  Detail & Related papers  (2023-05-31T09:38:21Z)
• Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning [79.83792914684985]
  We prove a new identifiability result that provides conditions under which maximally sparse base-predictors yield disentangled representations. Motivated by this theoretical result, we propose a practical approach to learn disentangled representations based on a sparsity-promoting bi-level optimization problem.
  arXiv  Detail & Related papers  (2022-11-26T21:02:09Z)
• Self-Certifying Classification by Linearized Deep Assignment [65.0100925582087]
  We propose a novel class of deep predictors for classifying metric data on graphs within PAC-Bayes risk certification paradigm. Building on the recent PAC-Bayes literature and data-dependent priors, this approach enables learning posterior distributions on the hypothesis space.
  arXiv  Detail & Related papers  (2022-01-26T19:59:14Z)
• Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound [15.557653926558638]
  We investigate a counterpart of majority votes over finite ensembles of classifiers, and study its generalization properties. We instantiate it with Dirichlet distributions: this allows for a closed-form and differentiable expression for the expected risk. The resulting majority vote learning algorithm achieves state-of-the-art accuracy and benefits from (non-vacuous) tight bounds.
  arXiv  Detail & Related papers  (2021-06-23T16:57:23Z)
• Measure Theoretic Approach to Nonuniform Learnability [16.467540842571328]
  characterization of nonuniform learnability has been redefined using the measure theoretic approach. introduction of a new algorithm, Generalize Measure Learnability framework, to implement this approach. Many situations were presented, Hypothesis Classes that are countable where we can apply the GML framework.
  arXiv  Detail & Related papers  (2020-11-01T01:03:26Z)

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.