Manopt, a Matlab toolbox for optimization on manifolds

Abstract

Optimization on manifolds is a rapidly developing branch of nonlinear optimization. Its focus is on problems where the smooth geometry of the search space can be leveraged to design efficient numerical algorithms. In particular, optimization on manifolds is well-suited to deal with rank and orthogonality constraints. Such structured constraints appear pervasively in machine learning applications, including low-rank matrix completion, sensor network localization, camera network registration, independent component analysis, metric learning, dimensionality reduction and so on. The Manopt toolbox, available at www.manopt.org, is a user-friendly, documented piece of software dedicated to simplify experimenting with state of the art Riemannian optimization algorithms. We aim particularly at reaching practitioners outside our field.

References in corpus (4)

• Generalized power method for sparse principal component analysis
• Low-rank optimization for semidefinite convex problems
• Low-rank optimization for distance matrix completion
• Regression on fixed-rank positive semidefinite matrices: a Riemannian approach

Cited by in corpus (189)

• Alternating Minimization Algorithms for Hybrid Precoding in Millimeter Wave MIMO Systems
• Linear Dimensionality Reduction: Survey, Insights, and Generalizations
• Global rates of convergence for nonconvex optimization on manifolds
• Tensor Networks for Dimensionality Reduction and Large-Scale Optimizations. Part 2 Applications and Future Perspectives
• Joint Transceiver and Large Intelligent Surface Design for Massive MIMO MmWave Systems
• A Geometric Analysis of Phase Retrieval
• Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach
• Nonconvex phase synchronization
• Tightness of the maximum likelihood semidefinite relaxation for angular synchronization
• Conic geometric optimisation on the manifold of positive definite matrices
• Complete Dictionary Recovery over the Sphere II: Recovery by Riemannian Trust-region Method
• Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent
• Bispectrum Inversion with Application to Multireference Alignment
• Geomstats: A Python Package for Riemannian Geometry in Machine Learning
• Wasserstein Discriminant Analysis
• Minimal subspace rotation on the Stiefel manifold for stabilization and enhancement of projection-based reduced order models for the compressible Navier-Stokes equations
• Low-rank tensor completion: a Riemannian manifold preconditioning approach
• Riemannian stochastic variance reduced gradient algorithm with retraction and vector transport
• Computation of Ground States of the Gross-Pitaevskii Functional via Riemannian Optimization
• Delay-Constrained Joint Power Control, User Detection and Passive Beamforming in Intelligent Reflecting Surface Assisted Uplink mmWave System
• Riemannian preconditioning
• Interactive Dimensionality Reduction for Comparative Analysis
• Geoopt: Riemannian Optimization in PyTorch
• Spectral Variability Aware Blind Hyperspectral Image Unmixing Based on Convex Geometry
• A Riemannian low-rank method for optimization over semidefinite matrices with block-diagonal constraints
• Learning Based User Scheduling in Reconfigurable Intelligent Surface Assisted Multiuser Downlink
• Generalized BackPropagation, Étude De Cas: Orthogonality
• RIS Empowered Near-Field Covert Communications
• Analyzing Dynamical Brain Functional Connectivity As Trajectories on Space of Covariance Matrices
• Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
• Optimization on Submanifolds of Convolution Kernels in CNNs
• Manifold Optimization Over the Set of Doubly Stochastic Matrices: A Second-Order Geometry
• 6-DoF Object Pose from Semantic Keypoints
• The non-convex Burer-Monteiro approach works on smooth semidefinite programs
• MMES: Mixture Model based Evolution Strategy for Large-Scale Optimization
• Canonical Correlation Analysis (CCA) Based Multi-View Learning: An Overview
• Riemannian Optimization on the Symplectic Stiefel Manifold
• A Riemannian trust-region method for low-rank tensor completion
• Intelligent Reflecting Surface Enhanced Resilient Design for MEC Offloading over Millimeter Wave Links
• Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope
• QGOpt: Riemannian optimization for quantum technologies
• Weighted Sum-Rate Maximization for Reconfigurable Intelligent Surface Aided Wireless Networks
• Manifold-regression to predict from MEG/EEG brain signals without source modeling
• Hybrid Analog-Digital Beamforming for Massive MIMO Systems
• Supervised LogEuclidean Metric Learning for Symmetric Positive Definite Matrices
• Fast and Accurate Intrinsic Symmetry Detection
• Riemannian adaptive stochastic gradient algorithms on matrix manifolds
• McTorch, a manifold optimization library for deep learning
• Location-free Spectrum Cartography
• Training Beam Design for Channel Estimation in Hybrid mmWave MIMO Systems
• Understanding symmetries in deep networks
• Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion
• MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
• Fixed-point algorithms for learning determinantal point processes
• Generalized Rank Pooling for Activity Recognition
• The generalized method of moments for multi-reference alignment
• Multi-target Detection with an Arbitrary Spacing Distribution
• Riemannian Newton-type methods for joint diagonalization on the Stiefel manifold with application to independent component analysis
• The condition number of Riemannian approximation problems
• Manifolds.jl: An Extensible Julia Framework for Data Analysis on Manifolds
• Data Multiplexing in Radio Interferometric Calibration
• MixEst: An Estimation Toolbox for Mixture Models
• Subjectively Interesting Subgroup Discovery on Real-valued Targets
• Provably robust estimation of modulo 1 samples of a smooth function with applications to phase unwrapping
• Symmetry-invariant optimization in deep networks
• Partial Functional Correspondence
• MU-MIMO Communications with MIMO Radar: From Co-existence to Joint Transmission
• A Survey of Recent Scalability Improvements for Semidefinite Programming with Applications in Machine Learning, Control, and Robotics
• Low-rank geometric mean metric learning
• New Riemannian preconditioned algorithms for tensor completion via polyadic decomposition
• Riemannian stochastic variance reduced gradient on Grassmann manifold
• 3D Shape Estimation from 2D Landmarks: A Convex Relaxation Approach
• MM Algorithms for Distance Covariance based Sufficient Dimension Reduction and Sufficient Variable Selection
• Quadratic Detection in Noncoherent Massive SIMO Systems over Correlated Channels
• Sensor Network Localization via Riemannian Conjugate Gradient and Rank Reduction: An Extended Version
• Jacobi-type algorithm for low rank orthogonal approximation of symmetric tensors and its convergence analysis
• Semantic keypoint-based pose estimation from single RGB frames
• On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry
• Robust Discriminative Clustering with Sparse Regularizers
• Riemannian preconditioning for tensor completion
• Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold
• MADMM: a generic algorithm for non-smooth optimization on manifolds
• Joint Constellation Design for the Two-User Non-Coherent Multiple-Access Channel
• Second order elastic metrics on the shape space of curves
• Functional correspondence by matrix completion
• New vector transport operators extending a Riemannian CG algorithm to generalized Stiefel manifold with low-rank applications
• Escaping Saddle Points in Ill-Conditioned Matrix Completion with a Scalable Second Order Method
• Manifold Optimization for Gaussian Mixture Models
• Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold
• Intelligent Reflecting Surfaces and Next Generation Wireless Systems
• Tensor completion using geodesics on Segre manifolds
• Statistical Estimation of the Poincar{é} constant and Application to Sampling Multimodal Distributions
• Fast and Robust Certifiable Estimation of the Relative Pose Between Two Calibrated Cameras
• Empirical Bayes Matrix Completion
• A universal framework for learning the elliptical mixture model
• An Alternative to EM for Gaussian Mixture Models: Batch and Stochastic Riemannian Optimization
• Terahertz-Band Joint Ultra-Massive MIMO Radar-Communications: Model-Based and Model-Free Hybrid Beamforming
• Generalized Left-Localized Cayley Parametrization for Optimization with Orthogonality Constraints
• A Riemannian approach to low-rank algebraic Riccati equations
• Solving Interpretable Kernel Dimension Reduction
• Low-Rank Modeling and Its Applications in Image Analysis
• Boosting Spectral Efficiency with Data-Carrying Reference Signals on the Grassmann Manifold
• Simple algorithms for optimization on Riemannian manifolds with constraints
• Inference and Mixture Modeling with the Elliptical Gamma Distribution
• Multi-reference factor analysis: low-rank covariance estimation under unknown translations
• Riemannian optimization on the simplex of positive definite matrices
• Intelligent reflecting surface assisted multi-cell multi-band wireless networks
• Second-order optimization for tensors with fixed tensor-train rank
• Noisy Euclidean distance realization: robust facial reduction and the Pareto frontier
• Fenchel Duality Theory and A Primal-Dual Algorithm on Riemannian Manifolds
• First- and Second-Order Analysis for Optimization Problems with Manifold-Valued Constraints
• A Framework for Population-Based Stochastic Optimization on Abstract Riemannian Manifolds
• A Riemannian gossip approach to decentralized matrix completion
• Reconfigurable Intelligent Surface for Interference Alignment in MIMO Device-to-Device Networks
• Heterogeneous multireference alignment for images with application to 2-D classification in single particle reconstruction
• R3MC: A Riemannian three-factor algorithm for low-rank matrix completion
• Sliced Wasserstein Generative Models
• Robust Hybrid Precoding for Beam Misalignment in Millimeter-Wave Communications
• An inexact augmented Lagrangian method for nonsmooth optimization on Riemannian manifold
• Self-Paced Multi-Label Learning with Diversity
• Riemannian stochastic recursive momentum method for non-convex optimization
• Hyperspherical Dirac Mixture Reapproximation
• Sparse Quadratic Optimisation over the Stiefel Manifold with Application to Permutation Synchronisation
• NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning
• Rank Estimation for Third-Order Tensor Completion in the Tensor-Train Format
• An Inexact Projected Gradient Method with Rounding and Lifting by Nonlinear Programming for Solving Rank-One Semidefinite Relaxation of Polynomial Optimization
• Cube-Split: A Structured Grassmannian Constellation for Non-Coherent SIMO Communications
• Orthogonal Trace-Sum Maximization: Applications, Local Algorithms, and Global Optimality
• Robust Seriation and Applications to Cancer Genomics
• A Sparse and Low-Rank Optimization Framework for Index Coding via Riemannian Optimization
• Low-Rank Matrix Completion for Topological Interference Management by Riemannian Pursuit
• Blind Demixing for Low-Latency Communication
• A Riemannian gossip approach to subspace learning on Grassmann manifold
• Distributed Optimization on Riemannian Manifolds for multi-agent networks
• Structured low-rank matrix learning: algorithms and applications
• Free Component Analysis: Theory, Algorithms & Applications
• Learning with symmetric positive definite matrices via generalized Bures-Wasserstein geometry
• Contrastive Video Representation Learning via Adversarial Perturbations
• Tangent Space Backpropagation for 3D Transformation Groups
• Riemannian Trust-Region based Adaptive Kalman filter with unknown noise Covariance matrices
• Operator-valued formulas for Riemannian Gradient and Hessian and families of tractable metrics
• Active Community Detection with Maximal Expected Model Change
• Manifold Optimization for High Accuracy Spatial Location Estimation Using Ultrasound Waves
• Stein-based preconditioners for weak-constraint 4D-var
• Riemannian optimal model reduction of stable linear systems
• Geometric Learning of Hidden Markov Models via a Method of Moments Algorithm
• Learning an Invariant Hilbert Space for Domain Adaptation
• Dimensionality Reduction on Grassmannian via Riemannian Optimization: A Generalized Perspective
• Topological Interference Management with User Admission Control via Riemannian Optimization
• Manifold optimization for non-linear optimal transport problems
• Human Motion Capture Using a Drone
• Smoothed analysis of the low-rank approach for smooth semidefinite programs
• Strong Convexity of Sets in Riemannian Manifolds
• Shape-from-Template with Generalised Camera
• Generalized One-Class Learning Using Pairs of Complementary Classifiers
• Overcoming barriers to scalability in variational quantum Monte Carlo
• ICLR 2021 Challenge for Computational Geometry & Topology: Design and Results
• On Riemannian Approach for Constrained Optimization Model in Extreme Classification Problems
• Riemannian Stochastic Hybrid Gradient Algorithm for Nonconvex Optimization
• Locally Feasibly Projected Sequential Quadratic Programming for Nonlinear Programming on Arbitrary Smooth Constraint Manifolds
• MSR-GAN: Multi-Segment Reconstruction via Adversarial Learning
• Learning with Semi-Definite Programming: new statistical bounds based on fixed point analysis and excess risk curvature
• A Novel Riemannian Optimization Approach to the Radial Distribution Network Load Flow Problem
• A Probabilistic approach for Learning Embeddings without Supervision
• Riemannian joint dimensionality reduction and dictionary learning on symmetric positive definite manifold
• Accelerated Stochastic Quasi-Newton Optimization on Riemann Manifolds
• Sequence Summarization Using Order-constrained Kernelized Feature Subspaces
• Low-Rank Matrix Completion for Mobile Edge Caching in Fog-RAN via Riemannian Optimization
• Joint Representation of Multiple Geometric Priors via a Shape Decomposition Model for Single Monocular 3D Pose Estimation
• Scalable Incremental Nonconvex Optimization Approach for Phase Retrieval
• On denoising modulo 1 samples of a function
• A Supervised Geometry-Aware Mapping Approach for Classification of Hyperspectral Images
• Manifold Optimization Assisted Gaussian Variational Approximation
• Rayleigh Quotient Iteration, cubic convergence, and second covariant derivative
• Detecting Approximate Reflection Symmetry in a Point Set using Optimization on Manifold
• Discriminative Video Representation Learning Using Support Vector Classifiers
• Multi-Label Learning with Global and Local Label Correlation
• Spectral Non-Convex Optimization for Dimension Reduction with Hilbert-Schmidt Independence Criterion
• A Low-Complexity Algorithmic Framework for Large-Scale IRS-Assisted Wireless Systems
• Supervised PCA: A Multiobjective Approach
• Riemannian Geometry with differentiable ambient space and metric operator
• Faster Randomized Methods for Orthogonality Constrained Problems
• Vector Transport Free Riemannian LBFGS for Optimization on Symmetric Positive Definite Matrix Manifolds
• Riemannian preconditioned coordinate descent for low multi-linear rank approximation
• Jacobi-type algorithms for homogeneous polynomial optimization on Stiefel manifolds with applications to tensor approximations
• Partial Least Squares Regression on Riemannian Manifolds and Its Application in Classifications
• Heterogeneous Tensor Decomposition for Clustering via Manifold Optimization
• Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
• Double Intelligent Reflecting Surface-assisted Multi-User MIMO mmWave Systems with Hybrid Precoding