Tracking the best disjunction - Foundations of Computer Science, 1995. Proceedings., 36th Annual Symposium on

نویسنده

  • Peter Auer
چکیده

Littlestone developed a simple deterministic on-line learning algorithm for learning t-literal disjunctions. This algorithm (called Winnow) keeps one weightfor each of the n variables and does multiplicative updates to its weights. We develop a randomized version of Winnow and prove bounds for an adaptation of the algorithm for the case when the disjunction may change over time. In this case a possible target disjunction schedule I is a sequence of disjunctions (one per trial} and the shift size is the total number of literals that are addearemoved from the disjunctions as one progresses through the sequence. We develop an algorithm that predicts nearly as well as the best disjunction schedule for an arbitrary sequence of examples. This algorithm that allows us to track the predictions of the best disjunction is hardly more complex than the original version. However the amortized analysis needed for obtaining worst-case mistake bounds requires new techniques. In some cases our lower bounds show that the upper bounds of our algorithm have the right constant in front of the leading term in the mistake bound and almost the right constant in front of the second leading term. By combining the tracking capability with existing applications of Winnow we are able to enhance these applications to the shifting case as well.

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Pseudorandom Generators, Measure Theory, and Natural Proofs - Foundations of Computer Science, 1995. Proceedings., 36th Annual Symposium on

We prove that i f strong pseudorandom number generators exist, then the class of languages that have polynomialsized circuits (Plpoly) is not measurable within exponential time, in terms of the resource-bounded measure theory of Lutz. We prove our result by showing that i f P/poly has measure zero in exponential time, then there is a natural proof against Plpoly, in the terminology of Razborov ...

متن کامل

A Scheduling Model for Reduced CPU Energy - Foundations of Computer Science, 1995. Proceedings., 36th Annual Symposium on

The energy usage of computer systems is becoming an important consideration, especially for batteryoperated systems. Various methods for reducing energy consumption have been investigated, both at the circuit level and at the operating systems level. In this paper, we propose a simple model of job scheduling aimed at capturing some key aspects of energy minimization. In this model, each job is ...

متن کامل

Gambling in a rigged casino: The adversarial multi-armed bandit problem

In the multi-armed bandit problem, a gambler must decide which arm of K non-identical slot machines to play in a sequence of trials so as to maximize his reward. This classical problem has received much attention because of the simple model it provides of the trade-off between exploration (trying out each arm to find the best one) and exploitation (playing the arm believed to give the best payo...

متن کامل

Improved Depth Lower Bounds for Small Distance Connectivity - Foundations of Computer Science, 1995. Proceedings., 36th Annual Symposium on

We consider the problem of determining, given a graph G and specified nodes s and t , whether or not there is a path of at most k edges in G from s to t . We show that solving this problem on polynomial-size unbounded fan-in circuits, requires depth a(1og log I C ) , improving on a depth lower bound of R(log* I C ) when k = logo(')n given in [2, 81. In addition we show that there is a constant ...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004