Teaching and Compressing for Low VC-Dimension

DOI10.1007/978-3-319-44479-6_26zbMATH Open1425.68352arXiv1502.06187OpenAlexW2962808814MaRDI QIDQ4604393FDOQ4604393

Shay Moran, A. Wigderson, Amir Shpilka, Amir Yehudayoff

Publication date: 26 February 2018

Published in: A Journey Through Discrete Mathematics (Search for Journal in Brave)

Abstract: In this work we study the quantitative relation between VC-dimension and two other basic parameters related to learning and teaching. Namely, the quality of sample compression schemes and of teaching sets for classes of low VC-dimension. Let $C$ be a binary concept class of size $m$ and VC-dimension $d$. Prior to this work, the best known upper bounds for both parameters were $log(m)$, while the best lower bounds are linear in $d$. We present significantly better upper bounds on both as follows. Set $k=O(d{2}^{d}loglog|C|)$. We show that there always exists a concept $c$ in $C$ with a teaching set (i.e. a list of $c$-labeled examples uniquely identifying $c$ in $C$) of size $k$. This problem was studied by Kuhlmann (1999). Our construction implies that the recursive teaching (RT) dimension of $C$ is at most $k$ as well. The RT-dimension was suggested by Zilles et al. and Doliwa et al. (2010). The same notion (under the name partial-ID width) was independently studied by Wigderson and Yehudayoff (2013). An upper bound on this parameter that depends only on $d$ is known just for the very simple case $d=1$, and is open even for $d=2$. We also make small progress towards this seemingly modest goal. We further construct sample compression schemes of size $k$ for $C$, with additional information of $klog(k)$ bits. Roughly speaking, given any list of $C$-labelled examples of arbitrary length, we can retain only $k$ labeled examples in a way that allows to recover the labels of all others examples in the list, using additional $klog(k)$ information bits. This problem was first suggested by Littlestone and Warmuth (1986).

Full work available at URL: https://arxiv.org/abs/1502.06187

Recommendations

• Recursive teaching dimension, VC-dimension and sample compression
• Learning in compressed space
• Compressed representation of learning spaces
• Combined compression and classification with learning vector quantization
• Learning as Data Compression
• Unlabeled compression schemes exceeding the VC-dimension
• Sample Compression Schemes for VC Classes

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32) Coding and information theory (compaction, compression, models of communication, encoding schemes, etc.) (aspects in computer science) (68P30)

Cites Work

• An introduction to support vector machines and other kernel-based learning methods.
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• On the density of families of sets
• Population recovery and partial identification
• Restriction access
• Learnability and the Vapnik-Chervonenkis dimension
• \(\epsilon\)-nets and simplex range queries
• Boosting a weak learning algorithm by majority
• Central limit theorems for empirical measures
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• A theory of the learnable
• Occam's razor
• Teaching a smarter learner.
• 10.1162/jmlr.2003.3.4-5.723
• Density and dimension
• Externally definable sets and dependent pairs
• Inferring decision trees using the minimum description length principle
• On the complexity of teaching
• Shifting: one-inclusion mistake bounds and sample compression
• Title not available (Why is that?)
• Algebraic methods proving Sauer's bound for teaching complexity
• Recursive Teaching Dimension, Learning Complexity, and Maximum Classes
• Title not available (Why is that?)
• Teachability in computational learning
• Learning from different teachers
• Learning Binary Relations and Total Orders
• Teaching Dimension and the Complexity of Active Learning
• Sample Compression Schemes for VC Classes
• Learning Integer Lattices
• Combinatorial variability of Vapnik-Chervonenkis classes with applications to sample compression schemes
• Title not available (Why is that?)
• A Geometric Approach to Sample Compression
• On weak learning

Cited In (5)

• Labeled Compression Schemes for Extremal Classes
• Sample Compression Schemes for VC Classes
• On Version Space Compression
• A note on hardness of computing recursive teaching dimension
• The VC-dimension of axis-parallel boxes on the torus

This page was built for publication: Teaching and Compressing for Low VC-Dimension

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4604393)