Adaptive Sequential Optimization with Applications to Machine Learning
This work addresses optimization challenges in machine learning applications where data distributions evolve over time, though it appears incremental as it builds on existing methods like SGD.
The paper tackles the problem of solving a sequence of slowly changing optimization problems, such as those in regression and classification, by introducing a framework that adaptively selects sample sizes to control excess risk, with experiments confirming its effectiveness.
A framework is introduced for solving a sequence of slowly changing optimization problems, including those arising in regression and classification applications, using optimization algorithms such as stochastic gradient descent (SGD). The optimization problems change slowly in the sense that the minimizers change at either a fixed or bounded rate. A method based on estimates of the change in the minimizers and properties of the optimization algorithm is introduced for adaptively selecting the number of samples needed from the distributions underlying each problem in order to ensure that the excess risk, i.e., the expected gap between the loss achieved by the approximate minimizer produced by the optimization algorithm and the exact minimizer, does not exceed a target level. Experiments with synthetic and real data are used to confirm that this approach performs well.