27
25

Fast and Reliable Parameter Estimation from Nonlinear Observations

Abstract

In this paper we study the problem of recovering a structured but unknown parameter θ{\bf{\theta}}^* from nn nonlinear observations of the form yi=f(xi,θ)y_i=f(\langle {\bf{x}}_i,{\bf{\theta}}^*\rangle) for i=1,2,,ni=1,2,\ldots,n. We develop a framework for characterizing time-data tradeoffs for a variety of parameter estimation algorithms when the nonlinear function ff is unknown. This framework includes many popular heuristics such as projected/proximal gradient descent and stochastic schemes. For example, we show that a projected gradient descent scheme converges at a linear rate to a reliable solution with a near minimal number of samples. We provide a sharp characterization of the convergence rate of such algorithms as a function of sample size, amount of a-prior knowledge available about the parameter and a measure of the nonlinearity of the function ff. These results provide a precise understanding of the various tradeoffs involved between statistical and computational resources as well as a-prior side information available for such nonlinear parameter estimation problems.

View on arXiv
Comments on this paper