A framework for polynomial-time query learnability
نویسندگان
چکیده
منابع مشابه
Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks
We consider the problem of learning function classes computed by neural networks with various activations (e.g. ReLU or Sigmoid), a task believed to be computationally intractable in the worst-case. A major open problem is to understand the minimal assumptions under which these classes admit provably efficient algorithms. In this work we show that a natural distributional assumption correspondi...
متن کاملPolynomial-Time Query Languages for Untyped Lists
We present a language for querying list-based complex objects. These objects are constructible with untyped nodes and hence permit arbitrary-depth sublists. The language is shown to express precisely the polynomial-time generic functions. The language controls complexity by carefully restricting the replication of values and limiting the form and nesting of recursion.
متن کاملA Sufficient Condition for Polynomial Distribution-dependent Learnability
We investigate upper bounds on the sample-size sufficient for ‘solid’ learnability with respect to a probability distribution. We obtain a sufficient condition for feasible (polynomially bounded) sample-size bounds for distributionspecific (solid) learnability.
متن کاملPolynomial Learnability and Locality of Formal Grammars
We apply a complexity theoretic notion of feasible learnability called "polynomial learnability" to the evaluation of grammatical formalisms for linguistic description. We show that a novel, nontrivial constraint on the degree of "locality" of grammars allows not only context free languages but also a rich class of mildly context sensitive languages to be polynomially learnable. We discuss poss...
متن کاملPolynomial Time Learnability of Simple Deterministic Languages from MAT and a Representative Sample
We propose a learning algorithm for simple deterministic languages from queries and a priori knowledge. To the learner, a special finite subset of the target language, called a representative sample, is provided at the beginning and two types of queries, equivalence queries and membership queries, are available. This learning algorithm constructs nonterminals of a hypothesis grammar based on Is...
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: Mathematical Systems Theory
سال: 1994
ISSN: 0025-5661,1433-0490
DOI: 10.1007/bf01578843