• Corpus ID: 16018339

Bounds on Query Convergence

  title={Bounds on Query Convergence},
  author={Barak A. Pearlmutter},
The problem of finding an optimum using noisy evaluations of a smooth cost function arises in many contexts, including economics, business, medicine, experiment design, and foraging theory. We derive an asymptotic bound E[ (x_t - x*)^2 ] >= O(1/sqrt(t)) on the rate of convergence of a sequence (x_0, x_1, >...) generated by an unbiased feedback process observing noisy evaluations of an unknown quadratic function maximised at x*. The bound is tight, as the proof leads to a simple algorithm which… 

Figures from this paper

How Expensive Is Link Utilization?

A generic algorithm Optimal Delay-Utilization control of t (ODU-t) that is designed with a performance goal of maximizing this benefit in an online manner, without requiring knowledge of the traffic conditions, specific delay-utilization models, nor does it require complex parameter estimation.

Router-based algorithms for improving internet quality of service.

A novel, stateless, queue management scheme is designed: Multi-Level Comparisons with index l (MLC(l), which enforces max-min fairness in a network of TCP flows and proposes an adaptive scheme that regulates the available queue space to keep utilization at desired, high, level.



Strategy Under the Unknown Stochastic Environment: the Nonparametric Lob—Pass Problem

This paper treats a more realistic situation of nonparametric estimation of the environment structure which includes an infinite number (a functional degree) of unknown parameters and proves that the cumulative regret can be made of the order O(log t) , O(( log t)2) , or O(t1-σ)(0< σ <1) depending on the dynamics of the Environment.

The Lob-Pass Problem

A model of tennis play, in which the only actions that the player can take are a pass and a lob, and the opponent is modeled by two linear (probabilistic) functions fL(r)=a1r+b1 and fP( r)=a2r+ b2 is considered.

The “lob-pass” problem and an on-line learning model of rational choice

We consider an on-line learning model of rational choice, in which the goal of an agent is to choose its actions so as to maximize the number of successes, while learning about its reacting

A Stochastic Approximation Method

Let M(x) denote the expected value at level x of the response to a certain experiment. M(x) is assumed to be a monotone function of x but is unknown tot he experiment, and it is desire to find the

Playing the matching-shoulders lob-pass game with logarithmic regret

An algorithm is described which beats that bound and meets the information-theoretic lower bound of O(log t) regret by converging to the best lob rate without accurately estimating the opponent's payoff lines.

Rational Choice Theory

It has long appeared to many people that economics is the most successful of the social sciences. It has assumed that people are motivated by money and by the possibility of making a profit, and this

Analysis of Recursive Stochastic Algorithms

Stationary and nonstationary learning characteristics of the LMS adaptive filter

It is shown that for stationary inputs the LMS adaptive algorithm, based on the method of steepest descent, approaches the theoretical limit of efficiency in terms of misadjustment and speed of adaptation when the eigenvalues of the input correlation matrix are equal or close in value.