What is Learnable in Valiant's Theory of the Learnable?

• URL: http://arxiv.org/abs/2605.13840v1
• Date: Wed, 13 May 2026 17:58:46 GMT
• Title: What is Learnable in Valiant's Theory of the Learnable?
• Abstract summary: Valiant's 1984 paper is widely credited with introducing the PAC learning model.<n>Unlike PAC learning, the learner receives only positives, may issue membership queries, and must output a hypothesis with no false positives.<n>We show that a class is learnable if and only if every realizable positive sample can be certified by a poly-size adaptive query-compression scheme.
• Score: 43.09148757729053
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Valiant's 1984 paper is widely credited with introducing the PAC learning model, but it, in fact, introduced a different model: unlike PAC learning, the learner receives only positives, may issue membership queries, and must output a hypothesis with no false positives. Prior work characterized variants, including the case without queries. We revisit Valiant's original model and ask: *Which classes are learnable in it?* For every finite domain, including Valiant's Boolean-hypercube setting, we show that a class is learnable if and only if every realizable positive sample can be certified by a poly-size adaptive query-compression scheme. This is a new variant of sample compression where the learner certifies samples via a short interaction with the membership oracle. Our characterization shows that learnability in Valiant's model is strictly sandwiched between learnability in the PAC model and the variant of Valiant's model without membership queries. This is one of the rare cases where introducing membership queries changes the set of learnable classes, and not just the sample or computational complexity. Next, we study the natural extension of the model to arbitrary domains. While we do not obtain an exact characterization, our techniques readily generalize and show that the same strict sandwiching persists. Finally, we show that $d$-dimensional halfspaces, which are not learnable without queries, are learnable with queries: we give a $\mathrm{poly}(d) \tilde{O}(1/ε)$ sample and $\mathrm{poly}(d) \mathrm{polylog}(1/ε)$ query algorithm, and prove that at least $Ω(d)$ samples or queries are necessary. To our knowledge, this is the first algorithm for halfspaces in Valiant's model. Together, these results uncover a surprisingly rich theory behind Valiant's original notion of learnability and introduce ideas that may be of independent interest in learning theory.

Related papers

• Optimal Rates for Learning with Monotone Adversaries [7.053805156684374]
  A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice.<n>Every example is correctly labeled, but the insertions depend on the clean sample, so the combined sample is not exchangeable.<n>Larsen, Pabbaraju, and Shetty, who introduced this model, show that empirical risk minimization attains expected error $O((d/n)log(n/d))$ for classes of VC dimension $d$.
  arXiv  Detail & Related papers  (2026-08-06T17:45:32Z)
• Online Set Learning from Precision and Recall Feedback [60.00180898830079]
  We consider the problem of learning an unknown subset $N_texttarget$ of a domain in an online setting.<n>This simple online set learning problem abstracts a variety of learning scenarios with precision- and recall-type feedback.<n>We show that a hypothesis class is learnable in this setting if and only if it has finite Vapnik-Chervonenkis dimension.
  arXiv  Detail & Related papers  (2026-05-10T14:28:05Z)
• Sample Complexity of Agnostic Multiclass Classification: Natarajan Dimension Strikes Back [84.81507553557556]
  We show that multiclass PAC sample complexity is governed by two distinct dimensions.<n>Unlike binary or online classification, multiclass learning inherently involves two structural parameters.<n>A key ingredient is a novel online procedure based on a self-adaptive multiplicative-weights algorithm performing a label-space reduction.
  arXiv  Detail & Related papers  (2025-11-16T15:47:47Z)
• Refereed Learning [4.024083217094761]
  We show refereed learning protocols that obtain a level of accuracy far exceeds what is obtainable at comparable cost without provers.<n>For all $varepsilon>0$ and ambient dimension $d$, our learner makes only one query to the ground truth function.<n>We develop a technique that allows the learner to sample, using the provers, from a distribution that is not efficiently samplable to begin with.
  arXiv  Detail & Related papers  (2025-10-06T23:07:31Z)
• Proper Learnability and the Role of Unlabeled Data [10.168670899305232]
  We show that there are problems whose proper learnability is logically undecidable, i.e., independent of the ZFC axioms.<n>We then show all impossibility results which obstruct any characterization of proper learnability in the realizable PAC model.
  arXiv  Detail & Related papers  (2025-02-14T18:41:53Z)
• Optimal Multi-Distribution Learning [88.3008613028333]
  Multi-distribution learning seeks to learn a shared model that minimizes the worst-case risk across $k$ distinct data distributions.<n>We propose a novel algorithm that yields an varepsilon-optimal randomized hypothesis with a sample complexity on the order of (d+k)/varepsilon2.
  arXiv  Detail & Related papers  (2023-12-08T16:06:29Z)
• When is Agnostic Reinforcement Learning Statistically Tractable? [76.1408672715773]
  A new complexity measure, called the emphspanning capacity, depends solely on the set $Pi$ and is independent of the MDP dynamics. We show there exists a policy class $Pi$ with a bounded spanning capacity that requires a superpolynomial number of samples to learn. This reveals a surprising separation for learnability between generative access and online access models.
  arXiv  Detail & Related papers  (2023-10-09T19:40:54Z)
• Distributional PAC-Learning from Nisan's Natural Proofs [0.0]
  Natural proofs of circuit lower bounds for $Lambda imply efficient algorithms for learning $Lambda-circuits. We consider whether this implication can be generalized to $Lambda notsupseteq AC0[p]$, and to learning algorithms which use only random examples and learn over arbitrary example distributions.
  arXiv  Detail & Related papers  (2023-10-05T16:13:29Z)
• Learnability, Sample Complexity, and Hypothesis Class Complexity for Regression Models [10.66048003460524]
  This work is inspired by the foundation of PAC and is motivated by the existing regression learning issues. The proposed approach, denoted by epsilon-Confidence Approximately Correct (epsilon CoAC), utilizes Kullback Leibler divergence (relative entropy) It enables the learner to compare hypothesis classes of different complexity orders and choose among them the optimum with the minimum epsilon.
  arXiv  Detail & Related papers  (2023-03-28T15:59:12Z)
• Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classes [5.194264506657145]
  We introduce comparative learning as a combination of the realizable and agnostic settings in PAC learning. Even when both $S$ and $B$ have infinite VC dimensions, comparative learning can still have a small sample complexity. We show that the sample complexity of comparative learning is characterized by the mutual VC dimension $mathsfVC(S,B)$.
  arXiv  Detail & Related papers  (2022-11-16T18:38:24Z)
• KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal [70.15267479220691]
  We consider and analyze the sample complexity of model reinforcement learning with a generative variance-free model. Our analysis shows that it is nearly minimax-optimal for finding an $varepsilon$-optimal policy when $varepsilon$ is sufficiently small.
  arXiv  Detail & Related papers  (2022-05-27T19:39:24Z)
• Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity [67.02490430380415]
  We show that model-based MARL achieves a sample complexity of $tilde O(|S||B|(gamma)-3epsilon-2)$ for finding the Nash equilibrium (NE) value up to some $epsilon$ error. We also show that such a sample bound is minimax-optimal (up to logarithmic factors) if the algorithm is reward-agnostic, where the algorithm queries state transition samples without reward knowledge.
  arXiv  Detail & Related papers  (2020-07-15T03:25:24Z)

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.