ICML 2016 accepted papers on Learning theory and algorithms
99 of the 322 papers accepted at ICML 2016 (30.7%) are on Learning theory and algorithms. They fall into 8 topics.
See ICML 2016 in the interactive map
Submitting to ICML? Checklist →
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
Matrix and tensor methods · 33 papers
- PD-Sparse : A Primal and Dual Sparse Approach to Extreme Multiclass and Multilabel Classification (130 citations)
- Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow (72 citations)
- Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms (60 citations)
- Online Low-Rank Subspace Clustering by Basis Dictionary Pursuit (42 citations)
- Estimating Structured Vector Autoregressive Models (39 citations)
- Dictionary Learning for Massive Matrix Factorization (37 citations)
- Low-Rank Matrix Approximation with Stability (36 citations)
- Robust Principal Component Analysis with Side Information (33 citations)
- A Subspace Learning Approach for High Dimensional Matrix Decomposition with Efficient Column/Row Sampling (31 citations)
- Fast methods for estimating the Numerical rank of large matrices (29 citations)
- Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity (25 citations)
- Binary embeddings with structured hashed projections (24 citations)
and 21 more in the interactive map.
Prediction and decision losses · 21 papers
- Evasion and Hardening of Tree Ensemble Classifiers (101 citations)
- Asymmetric Multi-task Learning Based on Task Relatedness and Loss (82 citations)
- Geometric Mean Metric Learning (57 citations)
- Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs (42 citations)
- Minimizing the Maximal Loss: How and Why (35 citations)
- Stratified Sampling Meets Machine Learning (34 citations)
- Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms (30 citations)
- ForecastICU: A Prognostic Decision Support System for Timely Prediction of Intensive Care Unit Admission (27 citations)
- The knockoff filter for FDR control in group-sparse and multitask regression (23 citations)
- Data-driven Rank Breaking for Efficient Rank Aggregation (21 citations)
- Power of Ordered Hypothesis Testing (21 citations)
- On the Consistency of Feature Selection With Lasso for Non-linear Targets (16 citations)
and 9 more in the interactive map.
Sample complexity · 18 papers
- Mixture Proportion Estimation via Kernel Embeddings of Distributions (87 citations)
- Stochastically Transitive Models for Pairwise Comparisons: Statistical and Computational Issues (79 citations)
- L1-regularized Neural Networks are Improperly Learnable in Polynomial Time (61 citations)
- Faster Eigenvector Computation via Shift-and-Invert Preconditioning (32 citations)
- Estimating Maximum Expected Value through Gaussian Approximation (31 citations)
- Linking losses for density ratio and class-probability estimation (30 citations)
- Exact Exponent in Optimal Rates for Crowdsourcing (29 citations)
- Truthful Univariate Estimators (22 citations)
- Fast Algorithms for Segmented Regression (19 citations)
- Provable Algorithms for Inference in Topic Models (16 citations)
- Square Root Graphical Models: Multivariate Generalizations of Univariate Exponential Families that Permit Positive Dependencies (15 citations)
- Optimality of Belief Propagation for Crowdsourced Classification (13 citations)
and 6 more in the interactive map.
Clustering · 8 papers
- Compressive Spectral Clustering (57 citations)
- Fast k-means with accurate bounds (41 citations)
- Speeding up k-means by approximating Euclidean distances via block vectors (31 citations)
- The Information-Theoretic Requirements of Subspace Clustering with Missing Data (29 citations)
- K-Means Clustering with Distributed Dimensions (9 citations)
- Clustering High Dimensional Categorical Data via Topographical Features (8 citations)
- k-variates++: more pluses in the k-means++ (4 citations)
- Correlation Clustering and Biclustering with Locally Bounded Errors
Kernels and regression theory · 7 papers
- Persistence weighted Gaussian kernel for topological data analysis (115 citations)
- Nonparametric Canonical Correlation Analysis (68 citations)
- Fast DPP Sampling for Nystrom with Application to Kernel Methods (40 citations)
- Recycling Randomness with Structure for Sublinear time Kernel Expansions (30 citations)
- Additive Approximations in High Dimensional Nonparametric Regression via the SALSA (20 citations)
- The Teaching Dimension of Linear Learners (19 citations)
- No penalty no tears: Least squares in high-dimensional linear models (8 citations)
Combinatorial and search optimization · 6 papers
- Learning and Inference via Maximum Inner Product Search (28 citations)
- Learning Simple Algorithms from Examples (23 citations)
- A Box-Constrained Approach for Hard Permutation Problems (7 citations)
- A Convex Atomic-Norm Approach to Multiple Sequence Alignment and Motif Discovery (5 citations)
- Fast k-Nearest Neighbour Search via Dynamic Continuous Indexing (5 citations)
- Train and Test Tightness of LP Relaxations in Structured Prediction (2 citations)
Submodular and game algorithms · 5 papers
- Greedy Column Subset Selection: New Bounds and Distributed Algorithms (31 citations)
- Algorithms for Optimizing the Ratio of Submodular Functions (19 citations)
- Horizontally Scalable Submodular Maximization (1 citation)
- Fast Constrained Submodular Maximization: Personalized Data Summarization
- Learning Sparse Combinatorial Representations via Two-stage Submodular Maximization
Optimal transport · 1 paper
- Gromov-Wasserstein Averaging of Kernel and Distance Matrices (216 citations)
