2026-09-19T13:15:59Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1598952025-07-08T03:06:50Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Edelman, Alan Dixit, Vaibhav Kumar Massachusetts Institute of Technology. Center for Computational Science and Engineering 2025-07-07T17:37:27Z 2025-07-07T17:37:27Z 2025-05 2025-05-20T21:15:15.192Z https://hdl.handle.net/1721.1/159895 This thesis introduces theoretical and computational frameworks for nonlinear, nonconvex optimization problems in statistics, machine learning, and optimal control. Disciplined Geodesically Convex Programming (DGCP) extends convexity verification to Riemannian manifolds, enabling optimization on curved spaces with global optimality guarantees. We develop rules and atoms for Cartan-Hadamard manifolds, particularly symmetric positive definite matrices, transforming non-convex problems into tractable ones through Riemannian geometry. We also present Optimization.jl, a unified interface for diverse optimization methods that supports specialized implementations for specific problem classes. Its modular architecture integrates automatic differentiation with an extensible plugin system. The framework’s capabilities are demonstrated through a GPU-accelerated hybrid method combining Particle Swarm Optimization with L-BFGS, and an augmented Lagrangian approach with stochastic inner optimizers that connects constrained optimization with machine learning techniques. Our work combines theoretical foundations with practical implementation, providing researchers tools to use advanced optimization methods without specialized mathematical knowledge. S.M. Massachusetts Institute of Technology In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ Traversing Rugged Domains: Explorations in Non-convex Optimization Theory and Software Thesis application/pdf Master Master of Science in Computational Science and Engineering Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="1fc2c718-6c8b-4fbf-944f-76eb14ffb54f"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Title>Traversing Rugged Domains: Explorations in Non-convex Optimization Theory and Software</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2025-05</PublicationDate> <Authors> <Author> <DisplayName>Dixit, Vaibhav Kumar</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>https://rightsstatements.org/page/InC-EDU/1.0/</License> <Abstract>This thesis introduces theoretical and computational frameworks for nonlinear, nonconvex optimization problems in statistics, machine learning, and optimal control. Disciplined Geodesically Convex Programming (DGCP) extends convexity verification to Riemannian manifolds, enabling optimization on curved spaces with global optimality guarantees. We develop rules and atoms for Cartan-Hadamard manifolds, particularly symmetric positive definite matrices, transforming non-convex problems into tractable ones through Riemannian geometry. We also present Optimization.jl, a unified interface for diverse optimization methods that supports specialized implementations for specific problem classes. Its modular architecture integrates automatic differentiation with an extensible plugin system. The framework’s capabilities are demonstrated through a GPU-accelerated hybrid method combining Particle Swarm Optimization with L-BFGS, and an augmented Lagrangian approach with stochastic inner optimizers that connects constrained optimization with machine learning techniques. Our work combines theoretical foundations with practical implementation, providing researchers tools to use advanced optimization methods without specialized mathematical knowledge.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>