Predictor-corrector algorithms for stochastic optimization under gradual distribution shift
Time-varying stochastic optimization problems frequently arise in machine learning practice (e.g. gradual domain shift, object tracking, strategic classification). Although most problems are solved in discrete time, the underlying process is often continuous in nature. We exploit this underlying continuity by developing predictor-corrector algorithms for time-varying stochastic optimizations. We provide error bounds for the iterates, both in presence of pure and noisy access to the queries from the relevant derivatives of the loss function. Furthermore, we show (theoretically and empirically in several examples) that our method outperforms non-predictor corrector methods that do not exploit the underlying continuous process.
Code (1)
Tasks
Object TrackingStochastic OptimizationSimilar Papers 제목 키워드 기반
A predictor-corrector method for the training of deep neural networks
The training of deep neural nets is expensive. We present a predictor- corrector method for the training of deep neural nets. It alternates a predictor pass with a corrector pass using stochastic gradient descent with ba…
Efficient first-order predictor-corrector multiple objective optimization for fair misinformation detection
Multiple-objective optimization (MOO) aims to simultaneously optimize multiple conflicting objectives and has found important applications in machine learning, such as minimizing classification loss and discrepancy in tr…
FairnessMisinformationPredictor-Corrector(PC) Temporal Difference(TD) Learning (PCTD)
Using insight from numerical approximation of ODEs and the problem formulation and solution methodology of TD learning through a Galerkin relaxation, I propose a new class of TD learning algorithms. After applying the im…
Reinforcement Learning (RL)Predictor-Corrector Policy Optimization
We present a predictor-corrector framework, called PicCoLO, that can transform a first-order model-free reinforcement or imitation learning algorithm into a new hybrid method that leverages predictive models to accelerat…
Imitation LearningNeural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning
The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization, polynomial root-finding, and sampling. Practical solvers for t…
Reinforcement Learning