Learning Bounded Subsets of L

Shahar Mendelson

doi:10.1109/TIT.2021.3083553

Learning Bounded Subsets of L

Shahar Mendelson^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

We study learning problems in which the underlying class is a bounded subset of L-{p} and the target Y belongs to L-{p}. Previously, minimax sample complexity estimates were known under such boundedness assumptions only when p= . We present a sharp sample complexity estimate that holds for any p > 4 it is based on a learning procedure that is suited for heavy-Tailed problems.

Original language	English
Article number	9440415
Pages (from-to)	5269-5282
Number of pages	14
Journal	IEEE Transactions on Information Theory
Volume	67
Issue number	8
DOIs	https://doi.org/10.1109/TIT.2021.3083553
Publication status	Published - Aug 2021
Externally published	Yes

Access to Document

10.1109/TIT.2021.3083553

Cite this

@article{9b7252c83da54a5b81e2a0e9f894a2b7,

title = "Learning Bounded Subsets of L",

abstract = "We study learning problems in which the underlying class is a bounded subset of L-\{p\} and the target Y belongs to L-\{p\}. Previously, minimax sample complexity estimates were known under such boundedness assumptions only when p= . We present a sharp sample complexity estimate that holds for any p > 4 it is based on a learning procedure that is suited for heavy-Tailed problems.",

keywords = "Statistical learning",

author = "Shahar Mendelson",

note = "Publisher Copyright: {\textcopyright} 1963-2012 IEEE.",

year = "2021",

month = aug,

doi = "10.1109/TIT.2021.3083553",

language = "English",

volume = "67",

pages = "5269--5282",

journal = "IEEE Transactions on Information Theory",

issn = "0018-9448",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "8",

}

TY - JOUR

T1 - Learning Bounded Subsets of L

AU - Mendelson, Shahar

PY - 2021/8

Y1 - 2021/8

N2 - We study learning problems in which the underlying class is a bounded subset of L-{p} and the target Y belongs to L-{p}. Previously, minimax sample complexity estimates were known under such boundedness assumptions only when p= . We present a sharp sample complexity estimate that holds for any p > 4 it is based on a learning procedure that is suited for heavy-Tailed problems.

AB - We study learning problems in which the underlying class is a bounded subset of L-{p} and the target Y belongs to L-{p}. Previously, minimax sample complexity estimates were known under such boundedness assumptions only when p= . We present a sharp sample complexity estimate that holds for any p > 4 it is based on a learning procedure that is suited for heavy-Tailed problems.

KW - Statistical learning

UR - http://www.scopus.com/inward/record.url?scp=85107214379&partnerID=8YFLogxK

U2 - 10.1109/TIT.2021.3083553

DO - 10.1109/TIT.2021.3083553

M3 - Article

SN - 0018-9448

VL - 67

SP - 5269

EP - 5282

JO - IEEE Transactions on Information Theory

JF - IEEE Transactions on Information Theory

IS - 8

M1 - 9440415

ER -

Learning Bounded Subsets of L

Abstract

Access to Document

Other files and links

Fingerprint

Cite this