Numerical Analysis

Local and Global Convergence of General Burer-Monteiro Tensor Optimizations AAAI 2022 Local and Global Linear Convergence of General Low-Rank Matrix Recovery Problems AAAI 2022 MAgNet: Mesh Agnostic Neural PDE Solver NeurIPS 2022 Multilevel Optimization for Inverse Problems COLT 2022 Noisy Riemannian Gradient Descent for Eigenvalue Computation with Application to Inexact Stochastic Recursive Gradient Algorithm ACML 2022 Non-Convex Optimization with Certificates and Fast Rates Through Kernel Sums of Squares COLT 2022 On the Instability of Relative Pose Estimation and RANSAC's Role CVPR 2022 Optimal Query Complexities for Dynamic Trace Estimation NeurIPS 2022 Optimizing Elimination Templates by Greedy Parameter Search CVPR 2022 Pick-and-Mix Information Operators for Probabilistic ODE Solvers AISTATS 2022 Positively Weighted Kernel Quadrature via Subsampling NeurIPS 2022 Probabilistic ODE Solutions in Millions of Dimensions ICML 2022 Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out ICML 2022 PROX-QP: Yet another Quadratic Programming Solver for Robotics and beyond RSS 2022 Quantum-Inspired Algorithms from Randomized Numerical Linear Algebra ICML 2022 Sketching Algorithms and Lower Bounds for Ridge Regression ICML 2022 Subquadratic Kronecker Regression with Applications to Tensor Decomposition NeurIPS 2022 Taylor-Lagrange Neural Ordinary Differential Equations: Toward Fast Training and Evaluation of Neural ODEs IJCAI 2022 The Fast Kernel Transform AISTATS 2022 Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis NeurIPS 2022 Transform Once: Efficient Operator Learning in Frequency Domain NeurIPS 2022 Accumulations of Projections—A Unified Framework for Random Sketches in Kernel Ridge Regression AISTATS 2021 A Comprehensively Tight Analysis of Gradient Descent for PCA NeurIPS 2021 Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality ICML 2021 Additive Error Guarantees for Weighted Low Rank Approximation ICML 2021