研究园简易版 · 经典书籍 · 期刊文章 · 有原文 · 完整版(可多选筛选、搜索) · 首页
2021 年 · JMLR
Journal of Machine Learning Research,2021 年发表的 290 篇,新的在前。点标题看作者和摘要。回到 2021 年
- sklvq: Scikit Learning Vector Quantization · JMLR · 2021 · 在第 29 页
- mvlearn: Multiview Machine Learning in Python · JMLR · 2021 · 在第 29 页
- mlr3pipelines - Flexible Machine Learning Pipelines in R · JMLR · 2021 · 在第 29 页
- giotto-tda: : A Topological Data Analysis Toolkit for Machine Learning and Data Exploration · JMLR · 2021 · 在第 29 页
- dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python · JMLR · 2021 · 在第 29 页
- When random initializations help: a study of variational inference for community detection · JMLR · 2021 · 在第 30 页
- When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? · JMLR · 2021 · 在第 30 页
- What Causes the Test Error? Going Beyond Bias-Variance via ANOVA · JMLR · 2021 · 在第 30 页
- Wasserstein distance estimates for the distributions of numerical approximations to ergodic stochastic differential equations · JMLR · 2021 · 在第 30 页
- Wasserstein barycenters can be computed in polynomial time in fixed dimension · JMLR · 2021 · 在第 30 页
- Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference · JMLR · 2021 · 在第 30 页
- VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning · JMLR · 2021 · 在第 30 页
- V-statistics and Variance Estimation · JMLR · 2021 · 在第 30 页
- Unlinked Monotone Regression · JMLR · 2021 · 在第 30 页
- Universal consistency and rates of convergence of multiclass prototype algorithms in metric spaces · JMLR · 2021 · 在第 30 页
- Unfolding-Model-Based Visualization: Theory, Method and Applications · JMLR · 2021 · 在第 30 页
- Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory · JMLR · 2021 · 在第 30 页
- Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMap, and PaCMAP for Data Visualization · JMLR · 2021 · 在第 30 页
- Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits · JMLR · 2021 · 在第 30 页
- Transferability of Spectral Graph Convolutional Neural Networks · JMLR · 2021 · 在第 30 页
- Tractable Approximate Gaussian Inference for Bayesian Neural Networks · JMLR · 2021 · 在第 30 页
- Towards a Unified Analysis of Random Fourier Features · JMLR · 2021 · 在第 30 页
- Tighter Risk Certificates for Neural Networks · JMLR · 2021 · 在第 30 页
- Thompson Sampling Algorithms for Cascading Bandits · JMLR · 2021 · 在第 30 页
- The ensmallen library for flexible numerical optimization · JMLR · 2021 · 在第 30 页
- The Ridgelet Prior: A Covariance Function Approach to Prior Specification for Bayesian Neural Networks · JMLR · 2021 · 在第 30 页
- The Decoupled Extended Kalman Filter for Dynamic Exponential-Family Factorization Models · JMLR · 2021 · 在第 30 页
- Testing Conditional Independence via Quantile Regression Based Partial Copulas · JMLR · 2021 · 在第 30 页
- TensorHive: Management of Exclusive GPU Access for Distributed Machine Learning Workloads · JMLR · 2021 · 在第 30 页
- Subspace Clustering through Sub-Clusters · JMLR · 2021 · 在第 30 页
- Structure Learning of Undirected Graphical Models for Count Data · JMLR · 2021 · 在第 31 页
- Strong Consistency, Graph Laplacians, and the Stochastic Block Model · JMLR · 2021 · 在第 31 页
- Stochastic Proximal Methods for Non-Smooth Non-Convex Constrained Sparse Optimization · JMLR · 2021 · 在第 31 页
- Stochastic Proximal AUC Maximization · JMLR · 2021 · 在第 31 页
- Stochastic Online Optimization using Kalman Recursion · JMLR · 2021 · 在第 31 页
- Statistically and Computationally Efficient Change Point Localization in Regression Settings · JMLR · 2021 · 在第 31 页
- Statistical guarantees for local graph clustering · JMLR · 2021 · 在第 31 页
- Statistical Query Lower Bounds for Tensor PCA · JMLR · 2021 · 在第 31 页
- Statistical Guarantees for Local Spectral Clustering on Random Neighborhood Graphs · JMLR · 2021 · 在第 31 页
- Stable-Baselines3: Reliable Reinforcement Learning Implementations · JMLR · 2021 · 在第 31 页
- Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks · JMLR · 2021 · 在第 31 页
- Sparse and Smooth Signal Estimation: Convexification of L0-Formulations · JMLR · 2021 · 在第 31 页
- Sparse Tensor Additive Regression · JMLR · 2021 · 在第 31 页
- Sparse Popularity Adjusted Stochastic Block Model · JMLR · 2021 · 在第 31 页
- Sparse Convex Optimization via Adaptively Regularized Hard Thresholding · JMLR · 2021 · 在第 31 页
- Some Theoretical Insights into Wasserstein GANs · JMLR · 2021 · 在第 31 页
- Soft Tensor Regression · JMLR · 2021 · 在第 31 页
- Single and Multiple Change-Point Detection with Differential Privacy · JMLR · 2021 · 在第 31 页
- Simultaneous Change Point Inference and Structure Recovery for High Dimensional Gaussian Graphical Models · JMLR · 2021 · 在第 31 页
- Simple and Fast Algorithms for Interactive Machine Learning with Random Counter-examples · JMLR · 2021 · 在第 31 页
- Shape-Enforcing Operators for Generic Point and Interval Estimators of Functions · JMLR · 2021 · 在第 31 页
- Safe Policy Iteration: A Monotonically Improving Approximate Policy Iteration Approach · JMLR · 2021 · 在第 31 页
- River: machine learning for streaming data in Python · JMLR · 2021 · 在第 31 页
- Risk-Averse Learning by Temporal Difference Methods with Markov Risk Measures · JMLR · 2021 · 在第 31 页
- Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs · JMLR · 2021 · 在第 31 页
- Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning · JMLR · 2021 · 在第 31 页
- Residual Energy-Based Models for Text · JMLR · 2021 · 在第 31 页
- Reproducing kernel Hilbert C*-module and kernel mean embeddings · JMLR · 2021 · 在第 31 页
- Representer Theorems in Banach Spaces: Minimum Norm Interpolation, Regularized Learning and Semi-Discrete Inverse Problems · JMLR · 2021 · 在第 31 页
- Replica Exchange for Non-Convex Optimization · JMLR · 2021 · 在第 31 页
- Regulating Greed Over Time in Multi-Armed Bandits · JMLR · 2021 · 在第 32 页
- Regularized spectral methods for clustering signed networks · JMLR · 2021 · 在第 32 页
- Refined approachability algorithms and application to regret minimization with global costs · JMLR · 2021 · 在第 32 页
- Ranking and synchronization from pairwise measurements via SVD · JMLR · 2021 · 在第 32 页
- RaSE: Random Subspace Ensemble Classification · JMLR · 2021 · 在第 32 页
- ROOTS: Object-Centric Representation and Rendering of 3D Scenes · JMLR · 2021 · 在第 32 页
- Quasi-Monte Carlo Quasi-Newton in Variational Bayes · JMLR · 2021 · 在第 32 页
- Pykg2vec: A Python Library for Knowledge Graph Embedding · JMLR · 2021 · 在第 32 页
- PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings · JMLR · 2021 · 在第 32 页
- Pseudo-Marginal Hamiltonian Monte Carlo · JMLR · 2021 · 在第 32 页
- Projection-free Decentralized Online Learning for Submodular Maximization over Time-Varying Networks · JMLR · 2021 · 在第 32 页
- Probabilistic Iterative Methods for Linear Systems · JMLR · 2021 · 在第 32 页
- Preference-based Online Learning with Dueling Bandits: A Survey · JMLR · 2021 · 在第 32 页
- Predictive Learning on Hidden Tree-Structured Ising Models · JMLR · 2021 · 在第 32 页
- Prediction against a limited adversary · JMLR · 2021 · 在第 32 页
- Prediction Under Latent Factor Regression: Adaptive PCR, Interpolating Predictors and Beyond · JMLR · 2021 · 在第 32 页
- Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks · JMLR · 2021 · 在第 32 页
- Phase Diagram for Two-layer ReLU Neural Networks at Infinite-width Limit · JMLR · 2021 · 在第 32 页
- PeerReview4All: Fair and Accurate Reviewer Assignment in Peer Review · JMLR · 2021 · 在第 32 页
- Pathwise Conditioning of Gaussian Processes · JMLR · 2021 · 在第 32 页
- Path Length Bounds for Gradient Descent and Flow · JMLR · 2021 · 在第 32 页
- Particle-Gibbs Sampling for Bayesian Feature Allocation Models · JMLR · 2021 · 在第 32 页
- Partial Policy Iteration for L1-Robust Markov Decision Processes · JMLR · 2021 · 在第 32 页
- POT: Python Optimal Transport · JMLR · 2021 · 在第 32 页
- Optimized Score Transformation for Consistent Fair Classification · JMLR · 2021 · 在第 32 页
- Optimization with Momentum: Dynamical, Control-Theoretic, and Symplectic Perspectives · JMLR · 2021 · 在第 32 页
- Optimal Structured Principal Subspace Estimation: Metric Entropy and Minimax Rates · JMLR · 2021 · 在第 32 页
- Optimal Rates of Distributed Regression with Imperfect Kernels · JMLR · 2021 · 在第 32 页
- Optimal Minimax Variable Selection for Large-Scale Matrix Linear Regression Model · JMLR · 2021 · 在第 32 页
- Optimal Feedback Law Recovery by Gradient-Augmented Sparse Polynomial Regression · JMLR · 2021 · 在第 33 页
- Optimal Bounds between f-Divergences and Integral Probability Metrics · JMLR · 2021 · 在第 33 页
- OpenML-Python: an extensible Python API for OpenML · JMLR · 2021 · 在第 33 页
- Online stochastic gradient descent on non-convex losses from high-dimensional inference · JMLR · 2021 · 在第 33 页
- One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Them · JMLR · 2021 · 在第 33 页
- On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift · JMLR · 2021 · 在第 33 页
- On the Stability Properties and the Optimization Landscape of Training Problems with Squared Loss for Neural Networks and General Nonlinear Conic Approximation Schemes · JMLR · 2021 · 在第 33 页
- On the Riemannian Search for Eigenvector Computation · JMLR · 2021 · 在第 33 页
- On the Optimality of Kernel-Embedding Based Goodness-of-Fit Tests · JMLR · 2021 · 在第 33 页
- On the Hardness of Robust Classification · JMLR · 2021 · 在第 33 页
- On the Estimation of Network Complexity: Dimension of Graphons · JMLR · 2021 · 在第 33 页
- On lp-hyperparameter Learning via Bilevel Nonsmooth Optimization · JMLR · 2021 · 在第 33 页
- On efficient multilevel Clustering via Wasserstein distances · JMLR · 2021 · 在第 33 页
- On Universal Approximation and Error Bounds for Fourier Neural Operators · JMLR · 2021 · 在第 33 页
- On Solving Probabilistic Linear Diophantine Equations · JMLR · 2021 · 在第 33 页
- On Multi-Armed Bandit Designs for Dose-Finding Trials · JMLR · 2021 · 在第 33 页
- On ADMM in Deep Learning: Convergence and Saturation-Avoidance · JMLR · 2021 · 在第 33 页
- Oblivious Data for Fairness with Kernels · JMLR · 2021 · 在第 33 页
- Normalizing Flows for Probabilistic Modeling and Inference · JMLR · 2021 · 在第 33 页
- Nonparametric Modeling of Higher-Order Interactions via Hypergraphons · JMLR · 2021 · 在第 33 页
- Nonparametric Continuous Sensor Registration · JMLR · 2021 · 在第 33 页
- Non-parametric Quantile Regression via the K-NN Fused Lasso · JMLR · 2021 · 在第 33 页
- Non-linear, Sparse Dimensionality Reduction via Path Lasso Penalized Autoencoders · JMLR · 2021 · 在第 33 页
- Non-attracting Regions of Local Minima in Deep and Wide Neural Networks · JMLR · 2021 · 在第 33 页
- Neighborhood Structure Assisted Non-negative Matrix Factorization and Its Application in Unsupervised Point-wise Anomaly Detection · JMLR · 2021 · 在第 33 页
- NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization · JMLR · 2021 · 在第 33 页
- NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation · JMLR · 2021 · 在第 33 页
- MushroomRL: Simplifying Reinforcement Learning Research · JMLR · 2021 · 在第 33 页
- Multilevel Monte Carlo Variational Inference · JMLR · 2021 · 在第 33 页
- Multi-view Learning as a Nonparametric Nonlinear Inter-Battery Factor Analysis · JMLR · 2021 · 在第 33 页
- Multi-class Gaussian Process Classification with Noisy Inputs · JMLR · 2021 · 在第 33 页
- Model Linkage Selection for Cooperative Learning · JMLR · 2021 · 在第 33 页
- Mode-wise Tensor Decompositions: Multi-dimensional Generalizations of CUR Decompositions · JMLR · 2021 · 在第 33 页
- Mixture Martingales Revisited with Applications to Sequential Tests and Confidence Intervals · JMLR · 2021 · 在第 33 页
- Mixing Time of Metropolis-Hastings for Bayesian Community Detection · JMLR · 2021 · 在第 34 页
- Method of Contraction-Expansion (MOCE) for Simultaneous Inference in Linear Models · JMLR · 2021 · 在第 34 页
- MetaGrad: Adaptation using Multiple Learning Rates in Online Learning · JMLR · 2021 · 在第 34 页
- Matrix Product States for Inference in Discrete Probabilistic Models · JMLR · 2021 · 在第 34 页
- Locally Private k-Means Clustering · JMLR · 2021 · 在第 34 页
- Locally Differentially-Private Randomized Response for Discrete Distribution Learning · JMLR · 2021 · 在第 34 页
- LocalGAN: Modeling Local Distributions for Adversarial Response Generation · JMLR · 2021 · 在第 34 页
- Linear Bandits on Uniformly Convex Sets · JMLR · 2021 · 在第 34 页
- Limit theorems for out-of-sample extensions of the adjacency and Laplacian spectral embeddings · JMLR · 2021 · 在第 34 页
- Learning with semi-definite programming: statistical bounds based on fixed point analysis and excess risk curvature · JMLR · 2021 · 在第 34 页
- Learning partial correlation graphs and graphical models by covariance queries · JMLR · 2021 · 在第 34 页
- Learning interaction kernels in heterogeneous systems of agents from multiple trajectories · JMLR · 2021 · 在第 34 页
- Learning and Planning for Time-Varying MDPs Using Maximum Likelihood Estimation · JMLR · 2021 · 在第 34 页
- Learning a High-dimensional Linear Structural Equation Model via l1-Regularized Regression · JMLR · 2021 · 在第 34 页
- Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes · JMLR · 2021 · 在第 34 页
- Learning Strategies in Decentralized Matching Markets under Uncertain Preferences · JMLR · 2021 · 在第 34 页
- Learning Sparse Classifiers: Continuous and Mixed Integer Optimization Perspectives · JMLR · 2021 · 在第 34 页
- Learning Laplacian Matrix from Graph Signals with Sparse Spectral Representation · JMLR · 2021 · 在第 34 页
- Learning Bayesian Networks from Ordinal Data · JMLR · 2021 · 在第 34 页
- LassoNet: A Neural Network with Feature Sparsity · JMLR · 2021 · 在第 34 页
- Langevin Monte Carlo: random coordinate descent and variance reduction · JMLR · 2021 · 在第 34 页
- Langevin Dynamics for Adaptive Inverse Reinforcement Learning of Stochastic Gradient Algorithms · JMLR · 2021 · 在第 34 页
- LDLE: Low Distortion Local Eigenmaps · JMLR · 2021 · 在第 34 页
- L-SVRG and L-Katyusha with Arbitrary Sampling · JMLR · 2021 · 在第 34 页
- Knowing what You Know: valid and validated confidence sets in multiclass and multilabel prediction · JMLR · 2021 · 在第 34 页
- Kernel Smoothing, Mean Shift, and Their Learning Theory with Directional Data · JMLR · 2021 · 在第 34 页
- Kernel Operations on the GPU, with Autodiff, without Memory Overflows · JMLR · 2021 · 在第 34 页
- Is SGD a Bayesian sampler? Well, almost · JMLR · 2021 · 在第 35 页
- Interpretable Deep Generative Recommendation Models · JMLR · 2021 · 在第 35 页
- Integrative High Dimensional Multiple Testing with Heterogeneity under Data Sharing Constraints · JMLR · 2021 · 在第 35 页
- Integrative Generalized Convex Clustering Optimization and Feature Selection for Mixed Multi-View Data · JMLR · 2021 · 在第 35 页
- Integrated Principal Components Analysis · JMLR · 2021 · 在第 35 页
- Information criteria for non-normalized models · JMLR · 2021 · 在第 35 页
- Inference for the Case Probability in High-dimensional Logistic Regression · JMLR · 2021 · 在第 35 页
- Inference for Multiple Heterogeneous Networks with a Common Invariant Subspace · JMLR · 2021 · 在第 35 页
- Inference In High-dimensional Single-Index Models Under Symmetric Designs · JMLR · 2021 · 在第 35 页
- Individual Fairness in Hindsight · JMLR · 2021 · 在第 35 页
- Incorporating Unlabeled Data into Distributionally Robust Learning · JMLR · 2021 · 在第 35 页
- Improving Reproducibility in Machine Learning Research(A Report from the NeurIPS 2019 Reproducibility Program) · JMLR · 2021 · 在第 35 页
- Improved Shrinkage Prediction under a Spiked Covariance Structure · JMLR · 2021 · 在第 35 页
- Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning · JMLR · 2021 · 在第 35 页
- Implicit Langevin Algorithms for Sampling From Log-concave Densities · JMLR · 2021 · 在第 35 页
- Hyperparameter Optimization via Sequential Uniform Designs · JMLR · 2021 · 在第 35 页
- Hybrid Predictive Models: When an Interpretable Model Collaborates with a Black-box Model · JMLR · 2021 · 在第 35 页
- How to Gain on Power: Novel Conditional Independence Tests Based on Short Expansion of Conditional Mutual Information · JMLR · 2021 · 在第 35 页
- How Well Generative Adversarial Networks Learn Distributions · JMLR · 2021 · 在第 35 页
- Homogeneity Structure Learning in Large-scale Panel Data with Heavy-tailed Errors · JMLR · 2021 · 在第 35 页
- Hoeffding's Inequality for General Markov Chains and Its Applications to Statistical Learning · JMLR · 2021 · 在第 35 页
- Histogram Transform Ensembles for Large-scale Regression · JMLR · 2021 · 在第 35 页
- High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm · JMLR · 2021 · 在第 35 页
- Hardness of Identity Testing for Restricted Boltzmann Machines and Potts models · JMLR · 2021 · 在第 35 页
- Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls · JMLR · 2021 · 在第 35 页
- Guided Visual Exploration of Relations in Data Sets · JMLR · 2021 · 在第 35 页
- Graph Matching with Partially-Correct Seeds · JMLR · 2021 · 在第 35 页
- Gradient Methods Never Overfit On Separable Data · JMLR · 2021 · 在第 35 页
- Global and Quadratic Convergence of Newton Hard-Thresholding Pursuit · JMLR · 2021 · 在第 35 页
- Geometric structure of graph Laplacian embeddings · JMLR · 2021 · 在第 35 页
- Generalization Properties of hyper-RKHS and its Applications · JMLR · 2021 · 在第 36 页
- Generalization Performance of Multi-pass Stochastic Gradient Descent with Convex Loss Functions · JMLR · 2021 · 在第 36 页
- GemBag: Group Estimation of Multiple Bayesian Graphical Models · JMLR · 2021 · 在第 36 页
- Gaussian Approximation for Bias Reduction in Q-Learning · JMLR · 2021 · 在第 36 页
- GIBBON: General-purpose Information-Based Bayesian Optimisation · JMLR · 2021 · 在第 36 页
- Further results on latent discourse models and word embeddings · JMLR · 2021 · 在第 36 页
- From Low Probability to High Confidence in Stochastic Convex Optimization · JMLR · 2021 · 在第 36 页
- From Fourier to Koopman: Spectral Methods for Long-term Time Series Prediction · JMLR · 2021 · 在第 36 页
- Flexible Signal Denoising via Flexible Empirical Bayes Shrinkage · JMLR · 2021 · 在第 36 页
- First-order Convergence Theory for Weakly-Convex-Weakly-Concave Min-max Problems · JMLR · 2021 · 在第 36 页
- Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime · JMLR · 2021 · 在第 36 页
- Finite Time LTI System Identification · JMLR · 2021 · 在第 36 页
- Fast Learning for Renewal Optimization in Online Task Scheduling · JMLR · 2021 · 在第 36 页
- Failures of Model-dependent Generalization Bounds for Least-norm Interpolation · JMLR · 2021 · 在第 36 页
- Factorization Machines with Regularization for Sparse Feature Interactions · JMLR · 2021 · 在第 36 页
- FLAME: A Fast Large-scale Almost Matching Exactly Approach to Causal Inference · JMLR · 2021 · 在第 36 页
- FATE: An Industrial Grade Platform for Collaborative Learning With Data Protection · JMLR · 2021 · 在第 36 页
- Explaining by Removing: A Unified Framework for Model Explanation · JMLR · 2021 · 在第 36 页
- Explaining Explanations: Axiomatic Feature Interactions for Deep Networks · JMLR · 2021 · 在第 36 页
- Expanding Boundaries of Gap Safe Screening · JMLR · 2021 · 在第 36 页
- Exact Asymptotics for Linear Quadratic Adaptive Control · JMLR · 2021 · 在第 36 页
- Estimation and Optimization of Composite Outcomes · JMLR · 2021 · 在第 36 页
- Estimation and Inference for High Dimensional Generalized Linear Models: A Splitting and Smoothing Approach · JMLR · 2021 · 在第 36 页
- Estimating the Lasso's Effective Noise · JMLR · 2021 · 在第 36 页
- Estimating Uncertainty Intervals from Collaborating Networks · JMLR · 2021 · 在第 36 页
- Entangled Kernels - Beyond Separability · JMLR · 2021 · 在第 36 页
- Empirical Bayes Matrix Factorization · JMLR · 2021 · 在第 36 页
- Edge Sampling Using Local Network Information · JMLR · 2021 · 在第 36 页
- Dynamic Tensor Recommender Systems · JMLR · 2021 · 在第 37 页
- Doubly infinite residual neural networks: a diffusion process approach · JMLR · 2021 · 在第 37 页
- Double Generative Adversarial Networks for Conditional Independence Testing · JMLR · 2021 · 在第 37 页
- Domain adaptation under structural causal models · JMLR · 2021 · 在第 37 页
- Domain Generalization by Marginal Transfer Learning · JMLR · 2021 · 在第 37 页
- Differentially Private Regression and Classification with Sparse Gaussian Processes · JMLR · 2021 · 在第 37 页
- Determining the Number of Communities in Degree-corrected Stochastic Block Models · JMLR · 2021 · 在第 37 页
- Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo · JMLR · 2021 · 在第 37 页
- DeEPCA: Decentralized Exact PCA with Linear Convergence Rate · JMLR · 2021 · 在第 37 页
- DIG: A Turnkey Library for Diving into Graph Deep Learning Research · JMLR · 2021 · 在第 37 页
- Counterfactual Mean Embeddings · JMLR · 2021 · 在第 37 页
- Cooperative SGD: A Unified Framework for the Design and Analysis of Local-Update SGD Algorithms · JMLR · 2021 · 在第 37 页
- Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be · JMLR · 2021 · 在第 37 页
- Convex Geometry and Duality of Over-parameterized Neural Networks · JMLR · 2021 · 在第 37 页
- Convex Clustering: Model, Theoretical Guarantee and Efficient Algorithm · JMLR · 2021 · 在第 37 页
- Convergence Guarantees for Gaussian Process Means With Misspecified Likelihoods and Smoothness · JMLR · 2021 · 在第 37 页
- Contrastive Estimation Reveals Topic Posterior Information to Linear Models · JMLR · 2021 · 在第 37 页
- Continuous Time Analysis of Momentum Methods · JMLR · 2021 · 在第 37 页
- Context-dependent Networks in Multivariate Time Series: Models, Methods, and Risk Bounds in High Dimensions · JMLR · 2021 · 在第 37 页
- Consistent estimation of small masses in feature sampling · JMLR · 2021 · 在第 37 页
- Consistent Semi-Supervised Graph Regularization for High Dimensional Data · JMLR · 2021 · 在第 37 页
- Consistency of Gaussian Process Regression in Metric Spaces · JMLR · 2021 · 在第 37 页
- Consensus-Based Optimization on the Sphere: Convergence to Global Minimizers and Machine Learning · JMLR · 2021 · 在第 37 页
- Conditional independences and causal relations implied by sets of equations · JMLR · 2021 · 在第 37 页
- Communication-Efficient Distributed Covariance Sketch, with Application to Distributed PCA · JMLR · 2021 · 在第 37 页
- Collusion Detection and Ground Truth Inference in Crowdsourcing for Labeling Tasks · JMLR · 2021 · 在第 37 页
- Classification vs regression in overparameterized regimes: Does the loss function matter? · JMLR · 2021 · 在第 37 页
- ChainerRL: A Deep Reinforcement Learning Library · JMLR · 2021 · 在第 37 页
- COKE: Communication-Censored Decentralized Kernel Learning · JMLR · 2021 · 在第 37 页
- CAT: Compression-Aware Training for bandwidth reduction · JMLR · 2021 · 在第 37 页
- Black-Box Reductions for Zeroth-Order Gradient Algorithms to Achieve Lower Query Complexity · JMLR · 2021 · 在第 37 页
- Bifurcation Spiking Neural Network · JMLR · 2021 · 在第 37 页
- Beyond English-Centric Multilingual Machine Translation · JMLR · 2021 · 在第 37 页
- Benchmarking Unsupervised Object Representations for Video Sequences · JMLR · 2021 · 在第 37 页
- Bayesian time-aligned factor analysis of paired multivariate time series · JMLR · 2021 · 在第 38 页
- Bayesian Text Classification and Summarization via A Class-Specified Topic Model · JMLR · 2021 · 在第 38 页
- Bayesian Distance Clustering · JMLR · 2021 · 在第 38 页
- Batch greedy maximization of non-submodular functions: Guarantees and applications to experimental design · JMLR · 2021 · 在第 38 页
- Bandit Learning in Decentralized Matching Markets · JMLR · 2021 · 在第 38 页
- Bandit Convex Optimization in Non-stationary Environments · JMLR · 2021 · 在第 38 页
- Banach Space Representer Theorems for Neural Networks and Ridge Splines · JMLR · 2021 · 在第 38 页
- Attention is Turing-Complete · JMLR · 2021 · 在第 38 页
- Asynchronous Online Testing of Multiple Hypotheses · JMLR · 2021 · 在第 38 页
- Asymptotic Normality, Concentration, and Coverage of Generalized Posteriors · JMLR · 2021 · 在第 38 页
- As You Like It: Localization via Paired Comparisons · JMLR · 2021 · 在第 38 页
- Are We Forgetting about Compositional Optimisers in Bayesian Optimisation? · JMLR · 2021 · 在第 38 页
- Approximate Newton Methods · JMLR · 2021 · 在第 38 页
- Analyzing the discrepancy principle for kernelized spectral filter learning algorithms · JMLR · 2021 · 在第 38 页
- Analysis of high-dimensional Continuous Time Markov Chains using the Local Bouncy Particle Sampler · JMLR · 2021 · 在第 38 页
- An algorithmic view of L2 regularization and some path-following algorithms · JMLR · 2021 · 在第 38 页
- An Online Sequential Test for Qualitative Treatment Effects · JMLR · 2021 · 在第 38 页
- An Inertial Newton Algorithm for Deep Learning · JMLR · 2021 · 在第 38 页
- An Importance Weighted Feature Selection Stability Measure · JMLR · 2021 · 在第 38 页
- An Empirical Study of Bayesian Optimization: Acquisition Versus Partition · JMLR · 2021 · 在第 38 页
- Alibi Explain: Algorithms for Explaining Machine Learning Models · JMLR · 2021 · 在第 38 页
- Aggregated Hold-Out · JMLR · 2021 · 在第 38 页
- Adversarial Monte Carlo Meta-Learning of Optimal Prediction Procedures · JMLR · 2021 · 在第 38 页
- Adaptive estimation of nonparametric functionals · JMLR · 2021 · 在第 38 页
- Achieving Fairness in the Stochastic Multi-Armed Bandit Problem · JMLR · 2021 · 在第 38 页
- Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent · JMLR · 2021 · 在第 38 页
- A general linear-time inference method for Gaussian Processes on one dimension · JMLR · 2021 · 在第 38 页
- A flexible model-free prediction-based framework for feature ranking · JMLR · 2021 · 在第 38 页
- A Unified Sample Selection Framework for Output Noise Filtering: An Error-Bound Perspective · JMLR · 2021 · 在第 38 页
- A Unified Framework for Spectral Clustering in Sparse Graphs · JMLR · 2021 · 在第 38 页
- A Unified Framework for Random Forest Prediction Error Estimation · JMLR · 2021 · 在第 38 页
- A Unified Convergence Analysis for Shuffling-Type Gradient Methods · JMLR · 2021 · 在第 38 页
- A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints · JMLR · 2021 · 在第 39 页
- A Two-Level Decomposition Framework Exploiting First and Second Order Information for SVM Training Problems · JMLR · 2021 · 在第 39 页
- A Theory of the Risk for Optimization with Relaxation and its Application to Support Vector Machines · JMLR · 2021 · 在第 39 页
- A Sharp Blockwise Tensor Perturbation Bound for Orthogonal Iteration · JMLR · 2021 · 在第 39 页
- A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms · JMLR · 2021 · 在第 39 页
- A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning · JMLR · 2021 · 在第 39 页
- A Lyapunov Analysis of Accelerated Methods in Optimization · JMLR · 2021 · 在第 39 页
- A Greedy Algorithm for Quantizing Neural Networks · JMLR · 2021 · 在第 39 页
- A Generalised Linear Model Framework for β-Variational Autoencoders based on Exponential Dispersion Families · JMLR · 2021 · 在第 39 页
- A General Framework for Empirical Bayes Estimation in Discrete Linear Exponential Family · JMLR · 2021 · 在第 39 页
- A General Framework for Adversarial Label Learning · JMLR · 2021 · 在第 39 页
- A Fast Globally Linearly Convergent Algorithm for the Computation of Wasserstein Barycenters · JMLR · 2021 · 在第 39 页
- A Distributed Method for Fitting Laplacian Regularized Stratified Models · JMLR · 2021 · 在第 39 页
- A Contextual Bandit Bake-off · JMLR · 2021 · 在第 39 页
- A Bayesian Contiguous Partitioning Method for Learning Clustered Latent Variables · JMLR · 2021 · 在第 39 页
- A Bayes-Optimal View on Adversarial Examples · JMLR · 2021 · 在第 39 页