JMLR

2,517 papers2,097 directions
The Journal of Machine Learning Research (JMLR) is a venue for the dissemination of research in machine learning and artificial intelligence. It publishes work spanning a variety of subfields, including statistical learning theory, optimization, and neural network analysis. The venue is characterized by its focus on formal methodologies and the mathematical foundations of computational learning. Recent publications at JMLR cover diverse technical areas such as differential privacy, Gaussian process interpolation, and Bayesian optimization. Research also explores dimensionality reduction techniques, network embeddings, and policy optimization using forward and reverse KL divergences. Additionally, the venue includes studies on the convergence rates of generative adversarial networks and the hierarchical properties of random fully connected neural networks. The venue features contributions from a range of researchers, including Sharan Narang, Aukosh Jagannath, and Kelly Ramsay. By hosting detailed investigations into topics like Gaussian graphical models and latent feature sharing, JMLR serves as a repository for technical advancements and theoretical insights. Its recent activity reflects an ongoing role in documenting the evolution of algorithmic and statistical approaches within the machine learning community.

Papers by Year

2026 36
2025 29
2024 185
2023 258
2022 237
2021 217
2020 162
2019 146
2018 76
2017 162
2016 176
2015 92
2014 91
2013 87
2012 94
2011 80
2010 87
2009 65
2008 40
2007 53
2006 64
2005 55
2004 33
2003 42
2002 31
2001 7
2000 2

Top Research Directions

Research directions most represented by papers from this venue.

Overcoming the Convexity Constraint in Modern Optimization 27
The Empirical Validation Gap 25
Scaling Gaussian Processes Beyond Cubic Complexity 22
Overcoming the Cubic Complexity of Kernel Methods 21
Kernel Hyperparameter Sensitivity in Distributional Metrics 20
Variational Inference as an Optimization Problem 19
Tightening Theoretical Bounds by Optimizing Constant Factors 17
Overcoming the Gaussian Assumption in High-Dimensional Learning 16
Decoupled Modular Frameworks for Rapid Scientific Experimentation 16
Generalizing Provable Control to Nonlinear Systems 16
Stationary Point Convergence in Nonconvex Optimization 15
Generalizing Machine Learning Guarantees to Alternative Kernels 13
Handling Mixed Discrete and Continuous Data Types 13
Kernel Mean Embeddings for Distribution Matching 13
Analytical and Automated Regularization Parameter Selection 13

Top Authors

AuthorPapers
Michael Jordan38
Tong Zhang26
Francis Bach24
Martin J Wainwright23
Bernhard Schölkopf20
Chih-Jen Lin18
Michael W. Mahoney18
Masashi Sugiyama17
Cynthia Rudin16
Shai Shalev-Shwartz15
Alex Smola14
Ingo Steinwart14
Yoshua Bengio14
Arthur Gretton13
Andreas Krause12
Inderjit S Dhillon12
Ohad Shamir12
Cho-Jui Hsieh11
Kenji Fukumizu11
Aapo Hyvarinen10

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Ground metric learning2014
High-dimensional learning of linear causal networks via inverse covariance estimation2014
Hitting and commute times in large random neighborhood graphs2014
Improving Markov network structure learning using decision trees2014
Information theoretical estimators toolbox2014
International Conference on Machine Learning, ICML 2014, 21-26 June, Beijing, P. R. China2014
Iteration complexity of feasible descent methods for convex optimization2014
Learning graphical models with hubs2014
LIBOL: a library for online learning algorithms2014
Link prediction in graphs with autoregressive features2014
Manopt, a matlab toolbox for optimization on manifolds2014
Matrix completion with the trace norm: learning, bounding, and transducing2014
Multi-objective reinforcement learning using sets of pareto dominating policies2014
Natural evolution strategies2014
New learning methods for supervised and unsupervised preference aggregation2014
Node-based learning of multiple Gaussian graphical models2014
Off-policy learning with eligibility traces: a survey2014
On multilabel classification and ranking with bandit feedback2014
On the bayes-optimality of F-measure maximizers2014
Optimal data collection for informative rankings expose well-connected graphs2014
Optimality of graphlet screening in high dimensional variable selection2014
Parallelizing exploration-exploitation tradeoffs in Gaussian process bandit optimization2014
Parallel MCMC with generalized elliptical slice sampling2014
Particle gibbs with ancestor sampling2014
Policy evaluation with temporal differences: a survey and comparison2014
Prediction and clustering in signed networks: a local to global perspective.2014
PyStruct: learning structured prediction in python.2014
QUIC: quadratic approximation for sparse inverse covariance estimation2014
Ramp loss linear programming support vector machine2014
Recursive teaching dimension, VC-dimension and sample compression2014
Revisiting Bayesian blind deconvolution2014
Revisiting Stein's paradox: multi-task averaging2014
Robust hierarchical clustering2014
Robust near-separable nonnegative matrix factorization using linear optimization2014
Seeded graph matching for correlated Erdös-Rényi graphs2014
Semi-supervised eigenvectors for large-scale locally-biased learning2014
Set-valued approachability and online learning with partial monitoring2014
Sparse factor analysis for learning and content analytics2014
Sparse factor analysis for learning and content analytics.2014
Spectral learning of latent-variable PCFGs: algorithms and sample complexity2014
SPMF: a Java open-source pattern mining library2014
Statistical analysis of metric graph reconstruction2014
Structured prediction via output space search.2014
Surrogate regret bounds for bipartite ranking via strongly proper losses2014
Tensor decompositions for learning latent variable models2014
The fastclime package for linear programming and large-scale precision matrix estimation in R2014
The No-U-turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo2014
Towards ultrahigh dimensional feature selection for big data2014
Training highly multiclass classifiers2014
Using trajectory data to improve bayesian optimization for reinforcement learning.2014

« prev Page 36/51 next »