Finite-Sum Optimization: A New Perspective for Convergence to a Global Solution
Deep neural networks (DNNs) have shown great success in many machine learning tasks. Their training is challenging since the loss surface of the network architecture is generally non-convex, or even non-smooth. How and under what assumptions is guaranteed convergence to a \textit{global} minimum possible? We propose a reformulation of the minimization problem allowing for a new recursive algorithmic framework. By using bounded style assumptions, we prove convergence to an $\varepsilon$-(global) minimum using $\mathcal{\tilde{O}}(1/\varepsilon^3)$ gradient computations. Our theoretical foundation motivates further study, implementation, and optimization of the new algorithmic framework and further investigation of its non-standard bounded style assumptions. This new direction broadens our understanding of why and under what circumstances training of a DNN converges to a global minimum.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
New Perspective on the Global Convergence of Finite-Sum Optimization
Deep neural networks (DNNs) have shown great success in many machine learning tasks. Their training is challenging since the loss surface of the network architecture is generally non-convex, or even non-smooth. How and u…
Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies
Policy gradient (PG) methods are a widely used reinforcement learning methodology in many applications such as video games, autonomous driving, and robotics. In spite of its empirical success, a rigorous understanding of…
Autonomous DrivingPolicy Gradient MethodsReinforcement LearningGeneralization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics
We introduce a new theoretical framework to analyze deep learning optimization with connection to its generalization error. Existing frameworks such as mean field theory and neural tangent kernel theory for neural networ…
Sharp global convergence guarantees for iterative nonconvex optimization: A Gaussian process perspective
We consider a general class of regression models with normally distributed covariates, and the associated nonconvex problem of fitting these models from data. We develop a general recipe for analyzing the convergence of …
parameter estimationRetrievalGlobal Convergence of Adjoint-Optimized Neural PDEs
Many engineering and scientific fields have recently become interested in modeling terms in partial differential equations (PDEs) with neural networks. The resulting neural-network PDE model, being a function of the neur…