JMLR 2024 papers on Learning theory and algorithms
132 of the 391 papers published in JMLR 2024 (33.8%) are on Learning theory and algorithms, compared with 32.2% at JMLR 2023. They fall into 9 topics.
See JMLR 2024 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
Kernels and regression theory · 40 papers
- The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective (31 citations)
- Data Thinning for Convolution-Closed Distributions (21 citations)
- On the Optimality of Misspecified Spectral Algorithms (15 citations)
- Improved Random Features for Dot Product Kernels (13 citations)
- Classification with Deep Neural Networks and Logistic Loss (12 citations)
- Statistical Optimality of Divide and Conquer Kernel-based Functional Linear Regression (12 citations)
- Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Condition (10 citations)
- On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains (10 citations)
- More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime validity (9 citations)
- Multiple Descent in the Multiple Random Feature Model (8 citations)
- A General Framework for the Analysis of Kernel-based Tests (6 citations)
- Random Forest Weighted Local Fréchet Regression with Random Objects (6 citations)
and 28 more in the interactive map.
Sample complexity · 29 papers
- Learning from many trajectories (25 citations)
- Bagging Provides Assumption-free Stability (13 citations)
- On Efficient and Scalable Computation of the Nonparametric Maximum Likelihood Estimator in Mixture Models (7 citations)
- Deep Neural Network Approximation of Invariant Functions through Dynamical Systems (6 citations)
- Nonparametric Regression Using Over-parameterized Shallow ReLU Neural Networks (5 citations)
- Variance estimation in graphs with the fused lasso (5 citations)
- On the Concentration of the Minimizers of Empirical Risks (4 citations)
- Lower Bounds on the Bayesian Risk via Information Measures (3 citations)
- Operator learning without the adjoint (3 citations)
- Statistical analysis for a penalized EM algorithm in high-dimensional mixture linear regression model (3 citations)
- MAP- and MLE-Based Teaching (2 citations)
- Adjusted Wasserstein Distributionally Robust Estimator in Statistical Learning (1 citation)
and 17 more in the interactive map.
Prediction and decision losses · 19 papers
- Conformal Inference for Online Prediction with Arbitrary Distribution Shifts (63 citations)
- Optimal Weighted Random Forests (14 citations)
- Fast Rates in Pool-Based Batch Active Learning (10 citations)
- An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates (5 citations)
- Inference on High-dimensional Single-index Models with Streaming Data (5 citations)
- Stage-Aware Learning for Dynamic Treatments (5 citations)
- Unified Binary and Multiclass Margin-Based Classification (1 citation)
- Estimating the Replication Probability of Significant Classification Benchmark Experiments
- False discovery proportion envelopes with m-consistency
- Learning Optimal Dynamic Treatment Regimens Subject to Stagewise Risk Controls
- Optimal Decision Tree and Adaptive Submodular Ranking with Noisy Outcomes
- Fréchet Random Forests for Metric Space Valued Regression with Non Euclidean Predictors
and 7 more in the interactive map.
Matrix and tensor methods · 19 papers
- Accelerating Nuclear-norm Regularized Low-rank Matrix Optimization Through Burer-Monteiro Decomposition (7 citations)
- Sharp analysis of power iteration for tensor PCA (5 citations)
- A minimax optimal approach to high-dimensional double sparse linear regression (4 citations)
- Guaranteed Nonconvex Factorization Approach for Tensor Train Recovery (4 citations)
- Revisiting RIP Guarantees for Sketching Operators on Mixture Models (1 citation)
- Robust Principal Component Analysis using Density Power Divergence (1 citation)
- The Non-Overlapping Statistical Approximation to Overlapping Group Lasso (1 citation)
- Triple Component Matrix Factorization: Untangling Global, Local, and Noisy Components (1 citation)
- More Efficient Estimation of Multivariate Additive Models Based on Tensor Decomposition and Penalization
- A Note on Entrywise Consistency for Mixed-data Matrix Completion
- A Statistical Experimental Design Method for Constructing Deterministic Sensing Matrices for Compressed Sensing
- Efficient Active Manifold Identification via Accelerated Iteratively Reweighted Nuclear Norm Minimization
and 7 more in the interactive map.
Clustering · 8 papers
- Fermat Distances: Metric Approximation, Spectral Convergence, and Clustering Algorithms (8 citations)
- Robust Spectral Clustering with Rank Statistics (2 citations)
- Contamination-source based K-sample clustering
- Distributed Kernel-Driven Data Clustering
- Pursuit of the Cluster Structure of Network Lasso: Recovery Condition and Non-convex Extension
- Spectral learning of multivariate extremes
- Stable and Consistent Density-Based Clustering via Multiparameter Persistence
- Sum-of-norms clustering does not separate nearby balls
Fairness · 6 papers
- Aequitas Flow: Streamlining Fair ML Experimentation (9 citations)
- Consistent Multiclass Algorithms for Complex Metrics and Constraints (6 citations)
- Fairness in Survival Analysis with Distributionally Robust Optimization (1 citation)
- Transport-based Counterfactual Models
- Fairness guarantees in multi-class classification with demographic parity
- Interpretable algorithmic fairness in structured and unstructured data
Optimal transport · 6 papers
- Lower Complexity Adaptation for Empirical Entropic Optimal Transport (15 citations)
- An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classification (3 citations)
- Characterization of translation invariant MMD on Rd and connections with Wasserstein distances
- Functional optimal transport: regularized map estimation and domain adaptation for functional data
- On the Convergence of Projected Alternating Maximization for Equitable and Optimal Transport
- Permuted and Unlinked Monotone Regression in R^d: an approach based on mixture modeling and optimal transport
