Malicious Experts Versus the Multiplicative Weights Algorithm in Online Prediction

نویسندگان

چکیده

We consider a prediction problem with two experts and forecaster. assume that one of the is honest makes correct probability μ at each round. The other malicious, who knows true outcomes round predictions in order to maximize loss Assuming forecaster adopts classical multiplicative weights algorithm, we find an upper bound (5) for value function malicious expert, also lower (19). Our results imply algorithm cannot resist corruption experts. show adaptive asymptotically optimal forecaster, hence more resistant

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Multiplicative Weights with Switching Experts

Due: Wednesday, April 20, 2016 – 7 pm Dropbox Outside Stata G5 Collaboration policy: collaboration is strongly encouraged. However, remember that 1. You must write up your own solutions, independently. 2. You must record the name of every collaborator. 3. You must actually participate in solving all the problems. This is difficult in very large groups, so you should keep your collaboration grou...

متن کامل

The Multiplicative Weights Algorithm

Professors Greenwald and Oyakawa 2017-04-19 In these notes, we improve on the basic expert advice algorithms previously introduced. The basis for this technique is that we give each expert a weight, which influences how much sway she has in the algorithm’s decision. An expert who is wrong will frequently have her weight reduced and will therefore have less of an impact on the algorithm’s decisi...

متن کامل

Tight Lower Bounds for the Multiplicative Weights Algorithm on the Experts Problem

We develop tight lower bounds for the regret achievable by the widely used Multiplicative Weights Algorithm (MWA) on the fundamental problem of prediction with expert advice. It is well known that with k experts and T steps, MWA suffers a (minimax) regret of at most √ T ln k 2 [7]. In this work, we show that as T → ∞, MWA suffers a regret of at least √ T ln k 2 for every even k, thereby precise...

متن کامل

Lecture 24 : The Multiplicative Weights Algorithm

In the next two lectures, we will present an alternative algorithm for solving LPs and SDPs. Multiplicative weights is a term for the simple iterative rule underlying these algorithms; it is known by different names in the various fields where it was (re)discovered. The detailed content can be found in a survey by Arora, Hazan and Kale [AHK05]; and our discussion is mainly based on their treatm...

متن کامل

Beating the Multiplicative Weights Update Algorithm

Multiplicative weights update algorithms have been used extensively in designing iterative algorithms for many computational tasks. The core idea is to maintain a distribution over a set of experts and update this distribution in an online fashion based on the parameters of the underlying optimization problem. In this report, we study the behavior of a special MWU algorithm used for generating ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Transactions on Information Theory

سال: 2021

ISSN: ['0018-9448', '1557-9654']

DOI: https://doi.org/10.1109/tit.2020.3025866