JMLR 2022 papers on Learning theory and algorithms
108 of the 283 papers published in JMLR 2022 (38.2%) are on Learning theory and algorithms, compared with 29.8% at JMLR 2021. They fall into 8 topics.
See JMLR 2022 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Sample complexity · 26 papers
- Asymptotic Analysis of Sampling Estimators for Randomized Numerical Linear Algebra Algorithms (38 citations)
- Universal Approximation of Functions on Sets (29 citations)
- Minimax Mixing Time of the Metropolis-Adjusted Langevin Algorithm for Log-Concave Sampling (28 citations)
- Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons (24 citations)
- Neural Estimation of Statistical Divergences (21 citations)
- Universal Approximation Theorems for Differentiable Geometric Deep Learning (21 citations)
- Advantage of Deep Neural Networks for Estimating Functions with Singularity on Hypersurfaces (20 citations)
- Universal Approximation in Dropout Neural Networks (14 citations)
- Maximum sampled conditional likelihood for informative subsampling (10 citations)
- Multiple Testing in Nonparametric Hidden Markov Models: An Empirical Bayes Approach (7 citations)
- Active Structure Learning of Bayesian Networks in an Observational Setting (6 citations)
- When Hardness of Approximation Meets Hardness of Learning (5 citations)
and 14 more in the interactive map.
Kernels and regression theory · 25 papers
- A Kernel Two-Sample Test for Functional Data (34 citations)
- Kernel Partial Correlation Coefficient --- a Measure of Conditional Dependence (30 citations)
- Interpolating Predictors in High-Dimensional Factor Regression (21 citations)
- Nonparametric adaptive control and prediction: theory and randomized algorithms (17 citations)
- Functional Linear Regression with Mixed Predictors (10 citations)
- Multiple-Splitting Projection Test for High-Dimensional Mean Vectors (10 citations)
- The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks (9 citations)
- The Weighted Generalised Covariance Measure (9 citations)
- Kernel Autocovariance Operators of Stationary Processes: Estimation and Convergence (7 citations)
- A universally consistent learning rule with a universally monotone error (6 citations)
- Gauss-Legendre Features for Gaussian Process Regression (5 citations)
- A Perturbation-Based Kernel Approximation Framework (2 citations)
and 13 more in the interactive map.
Matrix and tensor methods · 23 papers
- Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements (25 citations)
- Solving Large-Scale Sparse PCA to Certifiable (Near) Optimality (19 citations)
- Power Iteration for Tensor PCA (12 citations)
- A Random Matrix Perspective on Random Tensors (10 citations)
- Smooth Robust Tensor Completion for Background/Foreground Separation with Missing Pixels: Novel Algorithm with Convergence Guarantee (9 citations)
- Vector-Valued Least-Squares Regression under Output Regularity Assumptions (5 citations)
- EiGLasso for Scalable Sparse Kronecker-Sum Inverse Covariance Estimation (2 citations)
- Novel Min-Max Reformulations of Linear Inverse Problems (2 citations)
- Projected Robust PCA with Application to Smooth Image Recovery (2 citations)
- Nonconvex Matrix Completion with Linearly Parameterized Factors (1 citation)
- Reverse-mode differentiation in arbitrary tensor network format: with application to supervised learning (1 citation)
- Debiased Distributed Learning for Sparse Partial Linear Models in High Dimensions
and 11 more in the interactive map.
Prediction and decision losses · 18 papers
- Sampling Permutations for Shapley Value Estimation (87 citations)
- PECOS: Prediction for Enormous and Correlated Output Spaces (38 citations)
- CD-split and HPD-split: Efficient Conformal Regions in High Dimensions (29 citations)
- More Powerful Conditional Selective Inference for Generalized Lasso by Parametric Programming (24 citations)
- Metrics of Calibration for Probabilistic Predictions (20 citations)
- Tree-Values: Selective Inference for Regression Trees (17 citations)
- Getting Better from Worse: Augmented Bagging and A Cautionary Tale of Variable Importance (14 citations)
- Distributed Bootstrap for Simultaneous Inference Under High Dimensionality (8 citations)
- Under-bagging Nearest Neighbors for Imbalanced Classification (8 citations)
- Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features (5 citations)
- A Forward Approach for Sufficient Dimension Reduction in Binary Classification
- Empirical Risk Minimization under Random Censorship
and 6 more in the interactive map.
Optimal transport · 7 papers
- Optimal Transport for Stationary Markov Chains via Policy Iteration (5 citations)
- On Regularized Square-root Regression Problems: Distributionally Robust Interpretation and Fast Computations (3 citations)
- The EM Algorithm is Adaptively-Optimal for Unbalanced Symmetric Gaussian Mixtures (3 citations)
- Averaging Spatio-temporal Signals using Optimal Transport and Soft Alignment
- On the Complexity of Approximating Multimarginal Optimal Transport
- On the Efficiency of Entropic Regularized Algorithms for Optimal Transport
- Projected Statistical Methods for Distributional Data on the Real Line with the Wasserstein Metric
Clustering · 5 papers
- The Geometry of Uniqueness, Sparsity and Clustering in Penalized Estimation (16 citations)
- ALMA: Alternating Minimization Algorithm for Clustering Mixture Multilayer Network (11 citations)
- Clustering with Semidefinite Programming and Fixed Point Iteration (1 citation)
- Regularized K-means Through Hard-Thresholding (1 citation)
- Dependent randomized rounding for clustering and partition systems with knapsack constraints
Combinatorial and search optimization · 3 papers
- Learning to Optimize: A Primer and A Benchmark (173 citations)
- OMLT: Optimization & Machine Learning Toolkit (27 citations)
- Faster Randomized Interior Point Methods for Tall/Wide Linear Programs (4 citations)
