Mittagsseminar (in cooperation with J. Lengler, A. Steger, and D. Steurer)

Date and Time: Tuesday, July 30, 2019, 12:15 pm

Duration: 30 minutes

Location: OAT S15/S16/S17

Speaker: Jasper Lee (Brown University)

A Near-Optimal Adaptive Algorithm for Estimating Binary Mixtures of Unknown Coins

Given a mixture between two populations of coins: "positive" coins that have (unknown and potentially different) probabilities of heads at least 1/2+Δ and "negative" coins with probabilities at most 1/2-Δ, we consider the task of estimating the fraction ρ of coins of each type to within additive error ε, with a constant probability of success.

In this talk, we will focus on the construction of an algorithm with sample complexity O((ρ/ε²Δ²)(1+ρ log 1/ε)), which matches the fully-adaptive lower bound of Ω(ρ/ε²Δ²) shown in our paper, except for the regime where ρ = ω(1/log 1/ε).

The fine-grained adaptive flavour of both our algorithm and lower bound contrasts with much previous work in distributional testing and learning.

Joint work with Paul Valiant, available on arXiv at https://arxiv.org/abs/1904.09228

Upcoming talks     |     All previous talks     |     Talks by speaker     |     Upcoming talks in iCal format (beta version!)

Previous talks by year:   2024  2023  2022  2021  2020  2019  2018  2017  2016  2015  2014  2013  2012  2011  2010  2009  2008  2007  2006  2005  2004  2003  2002  2001  2000  1999  1998  1997  1996  

Information for students and suggested topics for student talks

Automatic MiSe System Software Version 1.4803M   |   admin login