DROPS

Document

DOI: 10.4230/LIPIcs.ICALP.2017.48

Tight Lower Bounds for Multiplicative Weights Algorithmic Families

Authors: Nick Gravin, Yuval Peres, and Balasubramanian Sivan

Published in: LIPIcs, Volume 80, 44th International Colloquium on Automata, Languages, and Programming (ICALP 2017)

Abstract

We study the fundamental problem of prediction with expert advice and develop regret lower bounds for a large family of algorithms for this problem. We develop simple adversarial primitives, that lend themselves to various combinations leading to sharp lower bounds for many algorithmic families. We use these primitives to show that the classic Multiplicative Weights Algorithm (MWA) has a regret of (T*ln(k)/2)^{0.5} (where T is the time horizon and k is the number of experts), there by completely closing the gap between upper and lower bounds. We further show a regret lower bound of (2/3)* (T*ln(k)/2)^{0.5} for a much more general family of algorithms than MWA, where the learning rate can be arbitrarily varied over time, or even picked from arbitrary distributions over time. We also use our primitives to construct adversaries in the geometric horizon setting for MWA to precisely characterize the regret at 0.391/(\delta)^{0.5} for the case of 2 experts and a lower bound of (1/2)*(ln(k)/(2*\delta))^{0.5}, for the case of arbitrary number of experts k (here \delta is the probability that the game ends in any given round).

Cite as

Nick Gravin, Yuval Peres, and Balasubramanian Sivan. Tight Lower Bounds for Multiplicative Weights Algorithmic Families. In 44th International Colloquium on Automata, Languages, and Programming (ICALP 2017). Leibniz International Proceedings in Informatics (LIPIcs), Volume 80, pp. 48:1-48:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2017)

Copy BibTex To Clipboard

@InProceedings{gravin_et_al:LIPIcs.ICALP.2017.48,
  author =	{Gravin, Nick and Peres, Yuval and Sivan, Balasubramanian},
  title =	{{Tight Lower Bounds for Multiplicative Weights Algorithmic Families}},
  booktitle =	{44th International Colloquium on Automata, Languages, and Programming (ICALP 2017)},
  pages =	{48:1--48:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-041-5},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{80},
  editor =	{Chatzigiannakis, Ioannis and Indyk, Piotr and Kuhn, Fabian and Muscholl, Anca},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ICALP.2017.48},
  URN =		{urn:nbn:de:0030-drops-74997},
  doi =		{10.4230/LIPIcs.ICALP.2017.48},
  annote =	{Keywords: Multiplicative Weights, Lower Bounds, Adversarial Primitives}
}

Search Results

Documents authored by Sivan, Balasubramanian

Tight Lower Bounds for Multiplicative Weights Algorithmic Families

Abstract

Cite as

Thanks for your feedback!

Could not send message