Boosting Using Branching Programs
نویسندگان
چکیده
منابع مشابه
Boosting Using Branching Programs
It is known that decision tree learning can be viewed as a form of boosting. Given a weak learning hypothesis one can show that the training error of a decision tree declines as |T| where |T| is the size of the decision tree and b is a constant determined by the weak learning hypothesis. Here we consider the case of decision DAGs—decision trees in which a given node can be shared by different b...
متن کاملOn the Practice of Branching Program Boosting
Branching programs are a generalization of decision trees. From the viewpoint of boosting theory the former appear to be exponentially more eecient. However, earlier experience demonstrates that such results do not necessarily translate to practical success. In this paper we develop a practical version of Mansour and McAllester's 13] algorithm for branching program boosting. We test the algorit...
متن کاملExtremely uniform branching programs
We propose a new descriptive complexity notion of uniformity for branching programs solving problems defined on structured data. We observe that FO[=]-uniform (n-way) branching programs are unable to solve the tree evaluation problem studied by Cook, McKenzie, Wehr, Braverman and Santhanam [8] because such programs possess a variant of their thriftiness property. Similarly, FO[=]-uniform (n-way...
متن کاملOn Arithmetic Branching Programs
The model of arithmetic branching programs is an algebraic model of computation generalizing the model of modular branching programs. We show that, up to a polynomial factor in size, arithmetic branching programs are equivalent to complements of dependency programs, a model introduced by Pudll ak and Sgall 20]. Using this equivalence we prove that dependency programs are closed under conjunctio...
متن کاملSolving Semi-infinite Linear Programs Using Boosting-Like Methods
Linear optimization problems (LPs) with a very large or even infinite number of constraints frequently appear in many forms in machine learning. A linear program with m constraints can be written as min x∈P n c x with a where I assume for simplicity that the domain of x is the n dimensional probability simplex P n. Optimization problems with an infinite number of constraints of the form a j x ≤...
متن کاملذخیره 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: Journal of Computer and System Sciences
سال: 2002
ISSN: 0022-0000
DOI: 10.1006/jcss.2001.1796