Date of this Version
IEEE Transactions on Information Theory
We study the intrinsic limitations of sequential convex optimization through the lens of feedbackinformation theory. In the oracle model of optimization, an algorithm queries an oracle for noisyinformation about the unknown objective function and the goal is to (approximately) minimize every function in a given class using as few queries as possible. We show that, in order for a function to be optimized, the algorithm must be able to accumulate enough information about the objective. This, in turn, puts limits on the speed of optimization under specific assumptions on the oracle and the type offeedback. Our techniques are akin to the ones used in statistical literature to obtain minimax lower bounds on the risks of estimation procedures; the notable difference is that, unlike in the case of i.i.d. data, a sequential optimization algorithm can gather observations in a controlled manner, so that the amount of information at each step is allowed to change in time. In particular, we show that optimization algorithms often obey the law of diminishing returns: the signal-to-noise ratio drops as the optimization algorithm approaches the optimum. To underscore the generality of the tools, we use our approach to derive fundamental lower bounds for a certain active learning problem. Overall, the present work connects the intuitive notions of “information” in optimization, experimental design, estimation, and active learning to the quantitative notion of Shannon information.
convex programming, feedback, information theory, minimax techniques, sequential estimation, Shannon information, active learning problem, feedback information theory, information-based complexity, minimax lower bound, quantitative notion, sequential convex optimization, sequential optimization algorithm, signal-to-noise ratio, statistical literature, accuracy, complexity theory, convex functions, Markov processes, noise measurement, optimization, random variables, convex optimization, Fano's inequality, feedback information theory, hypothesis testing with controlled observations, information-based complexity, information-theoretic converse, minimax lower bounds, sequential optimization algorithms, statistical estimation
Raginsky, M., & Rakhlin, A. (2011). Information-Based Complexity, Feedback and Dynamics in Convex Programming. IEEE Transactions on Information Theory, 57 (10), 7036-7056. http://dx.doi.org/10.1109/TIT.2011.2154375
Date Posted: 27 November 2017
This document has been peer reviewed.