A Geometric Approach to Problems in Optimization and Data Science
We give new results for problems in computational and statistical machine learning using tools from high-dimensional geometry and probability. We break up our treatment into two parts. In Part I, we focus on computational considerations in optimization. Specifically, we give new algorithms for approximating convex polytopes in a stream, sparsification and robust least squares regression, and dueling optimization. In Part II, we give new statistical guarantees for data science problems. In particular, we formulate a new model in which we analyze statistical properties of backdoor data poisoning attacks, and we study the robustness of graph clustering algorithms to ``helpful'' misspecification.
Code (0)
등록된 구현이 없습니다.
Tasks
Data PoisoningGraph ClusteringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Riemannian optimization with a preconditioning scheme on the generalized Stiefel manifold
Optimization problems on the generalized Stiefel manifold (and products of it) are prevalent across science and engineering. For example, in computational science they arise in symmetric (generalized) eigenvalue problems…
Dimensionality ReductionRiemannian optimizationFinding the Sparsest Vectors in a Subspace: Theory, Algorithms, and Applications
The problem of finding the sparsest vector (direction) in a low dimensional subspace can be considered as a homogeneous variant of the sparse recovery problem, which finds applications in robust subspace recovery, dictio…
Dictionary LearningRepresentation LearningDeformable Graph Matching
Graph matching (GM) is a fundamental problem in computer science, and it has been successfully applied to many problems in computer vision. Although widely used, existing GM algorithms cannot incorporate global consisten…
Graph MatchingGeoFunFlow: Geometric Function Flow Matching for Inverse Operator Learning over Complex Geometries
Inverse problems governed by partial differential equations (PDEs) are crucial in science and engineering. They are particularly challenging due to ill-posedness, data sparsity, and the added complexity of irregular geom…
Physics-informed neural networks for transformed geometries and manifolds
Physics-informed neural networks (PINNs) effectively embed physical principles into machine learning, but often struggle with complex or alternating geometries. We propose a novel method for integrating geometric transfo…