paper-with-me

Papers

Learning Boolean Halfspaces with Small Weights from Membership Queries

2014-05-07 · Hasan Abasi, Ali Z. Abdi, Nader H. Bshouty

We consider the problem of proper learning a Boolean Halfspace with integer weights $\{0,1,\ldots,t\}$ from membership queries only. The best known algorithm for this problem is an adaptive algorithm that asks $n^{O(t^5)}$ membership queries where the best lower bound for the number of membership queries is $n^t$ [Learning Threshold Functions with Small Weights Using Membership Queries. COLT 1999] In this paper we close this gap and give an adaptive proper learning algorithm with two rounds that asks $n^{O(t)}$ membership queries. We also give a non-adaptive proper learning algorithm that asks $n^{O(t^3)}$ membership queries.

📄 PDF Abstract BibTeX arXiv:1405.1535

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning Disjunctions of Predicates

2017-06-15 · Nader H. Bshouty, Dana Drachsler-Cohen, Martin Vechev, Eran Yahav

Let $F$ be a set of boolean functions. We present an algorithm for learning $F_\vee := \{\vee_{f\in S} f \mid S \subseteq F\}$ from membership queries. Our algorithm asks at most $|F| \cdot OPT(F_\vee)$ membership querie…

Program Synthesis

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

2026-05-13 · Steve Hanneke, Anay Mehrotra, Grigoris Velegkas, Manolis Zampetakis arxiv

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 …

Learning Halfspaces With Membership Queries

2020-12-20 · Ori Kelner

Active learning is a subfield of machine learning, in which the learning algorithm is allowed to choose the data from which it learns. In some cases, it has been shown that active learning can yield an exponential gain i…

Active Learning

Active Learning of General Halfspaces: Label Queries vs Membership Queries

2024-12-31 · Ilias Diakonikolas, Daniel M. Kane, Mingchen Ma

We study the problem of learning general (i.e., not necessarily homogeneous) halfspaces under the Gaussian distribution on $R^d$ in the presence of some form of query access. In the classical pool-based active learning m…

Active Learning

Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift

2026-05-07 · Adam R. Klivans, Shyamal Patel, Konstantinos Stavropoulos, Arsen Vasilyan arxiv

Recent work on provably efficient algorithms for learning with distribution shift has focused on two models: PQ learning (Goldwasser et al. (2020)) and TDS learning (Klivans et al. (2024)). Algorithms for TDS learning ar…