Learning Sparse Polynomial Functions
نویسندگان
چکیده
We study the question of learning a sparse multivariate polynomial over the real domain. In particular, for some unknown polynomial f(~x) of degree-d and k monomials, we show how to reconstruct f , within error , given only a set of examples x̄i drawn uniformly from the n-dimensional cube (or an n-dimensional Gaussian distribution), together with evaluations f(x̄i) on them. The result holds even in the “noisy setting”, where we have only values f(x̄i) + g where g is noise (say, modeled as a Gaussian random variable). The runtime of our algorithm is polynomial in n, k, 1/ and Cd where Cd depends only on d. Note that, in contrast, in the “boolean version” of this problem, where x̄ is drawn from the hypercube, the problem is at least as hard as the “noisy parity problem,” where we do not know how to break the n time barrier, even for k = 1, and some believe it may be impossible to do so.
منابع مشابه
Learning Decision Trees Using the Fourier Spectrum
This work gives a polynomial time algorithm for learning decision trees with respect to the uniform distribution. (This algorithm uses membership queries.) The decision tree model that is considered is an extension of the traditional boolean decision tree model that allows linear operations in each node (i.e., summation of a subset of the input variables over GF(2)). This paper shows how to lea...
متن کاملSparse Polynomial Mapping for Manifold Learning
Manifold learning is an approach for nonlinear dimensionality reduction and has been a hot research topic in the field of computer science. A disadvantage of manifold learning methods is, however, that there are no explicit mappings from the high-dimensional feature space to the low-dimensional representation space. It restricts the application of manifold learning methods in many practical pro...
متن کاملSparse Polynomial Learning and Graph Sketching
Let f : {−1, 1} → R be a polynomial with at most s non-zero real coefficients. We give an algorithm for exactly reconstructing f given random examples from the uniform distribution on {−1, 1} that runs in time polynomial in n and 2 and succeeds if the function satisfies the unique sign property: there is one output value which corresponds to a unique set of values of the participating parities....
متن کاملAdaptive Basis Function Construction: An Approach for Adaptive Building of Sparse Polynomial Regression Models 127 Adaptive Basis Function Construction: An Approach for Adaptive Building of Sparse Polynomial Regression Models
The task of learning useful models from available data is common in virtually all fields of science, engineering, and finance. The goal of the learning task is to estimate unknown (input, output) dependency (or model) from training data (consisting of a finite number of samples) with good prediction (generalization) capabilities for future (test) data (Cherkassky & Mulier, 2007; Hastie et al., ...
متن کاملLearning sparse, overcomplete representations of time-varying natural images
I show how to adapt an overcomplete dictionary of spacetime functions so as to represent time-varying natural images with maximum sparsity. The basis functions are considered as part of a probabilistic model of image sequences, with a sparse prior imposed over the coefficients. Learning is accomplished by maximizing the log-likelihood of the model, using natural movies as training data. The bas...
متن کاملLearning Sparse Potential Games in Polynomial Time and Sample Complexity
We consider the problem of learning sparse potential games — a nonparametric class of graphical games where the payoffs are given by potential functions — from observations of strategic interactions. We show that a polynomial time method based on `1,2-group regularized logistic regression recovers the -Nash equilibria set of the true game in O ( m4d4 log(pd) ) samples, wherem is the maximum num...
متن کامل