OOIR: Observatory of International Research

Papers

(The TQCC of SIAM Journal on Mathematics of Data Science is 5. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2020-11-01 to 2024-11-01.)

Article	Citations
Scalable Semidefinite Programming	50
The Gap between Theory and Practice in Function Approximation with Deep Neural Networks	36
Implicit Deep Learning	35
Greed Works: An Improved Analysis of Sampling Kaczmarz--Motzkin	30
Persistent Laplacians: Properties, Algorithms and Implications	24
Nonbacktracking Eigenvalues under Node Removal: X-Centrality and Targeted Immunization	22
On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case	18
Autodifferentiable Ensemble Kalman Filters	18
Mean-Field Controls with Q-Learning for Cooperative MARL: Convergence and Complexity Analysis	16
Finite-Time Performance of Distributed Temporal-Difference Learning with Linear Function Approximation	15
What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory	15
Multi-Reference Alignment in High Dimensions: Sample Complexity and Phase Transition	14
An AO-ADMM Approach to Constraining PARAFAC2 on All Modes	13
Core-Periphery Detection in Hypergraphs	12
Nonbacktracking Spectral Clustering of Nonuniform Hypergraphs	12
Simplex-Structured Matrix Factorization: Sparsity-Based Identifiability and Provably Correct Algorithms	11
Benefit of Interpolation in Nearest Neighbor Algorithms	11
The Signature Kernel Is the Solution of a Goursat PDE	11
An Improved Central Limit Theorem and Fast Convergence Rates for Entropic Transportation Costs	10
Global Minima of Overparameterized Neural Networks	10
Matrix Denoising for Weighted Loss Functions and Heterogeneous Signals	10
Variational Representations and Neural Network Estimation of Rényi Divergences	10
Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis	9
Two Steps at a Time---Taking GAN Training in Stride with Tseng's Method	9
Tensor Methods for Nonlinear Matrix Completion	9

Satisficing Paths and Independent Multiagent Reinforcement Learning in Stochastic Games	9
Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection	9
A Generalized CUR Decomposition for Matrix Pairs	9
Wasserstein Barycenters Are NP-Hard to Compute	9
Diversity Sampling is an Implicit Regularization for Kernel Methods	8
The Trimmed Lasso: Sparse Recovery Guarantees and Practical Optimization by the Generalized Soft-Min Penalty	8
A Generative Variational Model for Inverse Problems in Imaging	8
Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank Determination	8
Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization	8
Doubly Stochastic Normalization of the Gaussian Kernel Is Robust to Heteroskedastic Noise	8
Interpretable Approximation of High-Dimensional Data	8
Multikernel Regression with Sparsity Constraint	8
A Unifying Generative Model for Graph Learning Algorithms: Label Propagation, Graph Convolutions, and Combinations	7
Post-training Quantization for Neural Networks with Provable Guarantees	7
Wasserstein-Based Projections with Applications to Inverse Problems	7
Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition	7
Identifying 3D Genome Organization in Diploid Organisms via Euclidean Distance Geometry	7
Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees	7
Approximation of Lipschitz Functions Using Deep Spline Neural Networks	6
Semi-supervised Learning for Aggregated Multilayer Graphs Using Diffuse Interface Methods and Fast Matrix-Vector Products	6
Rank $2r$ Iterative Least Squares: Efficient Recovery of Ill-Conditioned Low Rank Matrices from Few Entries	6
Robust Classification Under $\ell_0$ Attack for the Gaussian Mixture Model	6
Balancing Geometry and Density: Path Distances on High-Dimensional Data	6
Binary Component Decomposition Part I: The Positive-Semidefinite Case	5
Analysis of Spatial and Spatiotemporal Anomalies Using Persistent Homology: Case Studies with COVID-19 Data	5
An Optimal Algorithm for Strict Circular Seriation	5
Error Bounds for Dynamical Spectral Estimation	5
Biwhitening Reveals the Rank of a Count Matrix	5
Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning	5
A Metric on Directed Graphs and Markov Chains Based on Hitting Probabilities	5
Approximate Spectral Gaps for Markov Chain Mixing Times in High Dimensions	5
A Variational Formulation of Accelerated Optimization on Riemannian Manifolds	5
Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting, and Regularization	5