Complexity Approximation Principle

نویسندگان

  • Vladimir Vovk
  • Alexander Gammerman
چکیده

We propose a new inductive principle, which we call the complexity approximation principle (CAP). This principle is a natural generalization of Rissanen’s minimum description length (MDL) principle and Wallace’s minimum message length (MML) principle and is based on the notion of predictive complexity, a recent generalization of Kolmogorov complexity. Like the MDL principle, CAP can be regarded as an implementation of Occam’s razor.

برای دانلود 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

A Novel Successive Approximation Method for Solving a Class of Optimal Control Problems

This paper presents a successive approximation method (SAM) for solving a large class of optimal control problems. The proposed analytical-approximate method, successively solves the Two-Point Boundary Value Problem (TPBVP), obtained from the Pontryagin's Maximum Principle (PMP). The convergence of this method is proved and a control design algorithm with low computational complexity is present...

متن کامل

Approximation Solutions for Time-Varying Shortest Path Problem

Abstract. Time-varying network optimization problems have tradition-ally been solved by specialized algorithms. These algorithms have NP-complement time complexity. This paper considers the time-varying short-est path problem, in which can be optimally solved in O(T(m + n)) time,where T is a given integer. For this problem with arbitrary waiting times,we propose an approximation algorithm, whic...

متن کامل

Complexity and approximation ratio of semitotal domination in graphs

A set $S subseteq V(G)$ is a semitotal dominating set of a graph $G$ if it is a dominating set of $G$ andevery vertex in $S$ is within distance 2 of another vertex of $S$. Thesemitotal domination number $gamma_{t2}(G)$ is the minimumcardinality of a semitotal dominating set of $G$.We show that the semitotal domination problem isAPX-complete for bounded-degree graphs, and the semitotal dominatio...

متن کامل

On-line Prediction with Kernels and the Complexity Approximation Principle

The paper describes an application of Aggregating Algorithm to the problem of regression. It generalizes earlier results concerned with plain linear regression to kernel techniques and presents an on-line algorithm which performs nearly as well as any oblivious kernel predictor. The paper contains the derivation of an estimate on the performance of this algorithm. The estimate is then used to d...

متن کامل

On Small Size Approximation Models

In this paper we continue the study of the method of approximations in Boolean complexity. We introduce a framework which naturally generalizes previously known ones. The main result says that in this framework there exist approximation models providing in principle exponential lower bounds for almost all Boolean functions, and such that the number of testing functionals is only singly exponent...

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

برای دانلود 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

عنوان ژورنال:
  • Comput. J.

دوره 42  شماره 

صفحات  -

تاریخ انتشار 1999