NeurIPS 2014

416 papers

Top Research Directions

Research directions most represented by NeurIPS 2014 papers.

Scaling Gaussian Processes Beyond Cubic Complexity 13
Tensor Decomposition for Latent Parameter Recovery 7
Overcoming the Cubic Complexity of Kernel Methods 7
Convergence of Message Passing on Loopy Graphs 6
Basins of Attraction in Nonconvex Optimization 6
Learning Densities with Intractable Normalizing Constants 6
The Statistical Computational Gap in High Dimensions 5
Multi-Agent Learning Under Bandit Feedback 5
Non-Conjugate Inference for Gaussian Processes 5
Expectation Propagation for Approximate Bayesian Inference 4
Submodular Optimization for Diverse Subset Selection 4
Parameter Identifiability in Complex Statistical Models 4
Breaking the Sequential Bottleneck in Black-Box Optimization 4
Mitigating Gradient Variance in Stochastic Optimization 4
Parallelizing Sequential Sampling for High Dimensional Inference 4

Top Authors

AuthorPapers
Pradeep Kumar Ravikumar9
Inderjit S Dhillon8
Jonathan W. Pillow5
Prateek Jain5
Prateek Jain5
Remi Munos5
Yoshua Bengio5
Devavrat Shah4
Han Liu4
huan xu4
Jun Zhu4
Lawrence Carin4
Le Song4
Maria Florina Balcan4
Michael Jordan4
Sewoong Oh4
Shuicheng YAN4
Stefanie Jegelka4
Alessandro Lazaric3
Andrea Montanari3

Impactful Papers

Papers from NeurIPS 2014 that shaped research clusters.

Foundational

Influential

Papers

Title
Partition-wise Linear Models
Permutation Diffusion Maps (PDM) with Application to the Image Association Problem in Computer Vision
PEWA: Patch-based Exponentially Weighted Aggregation for image denoising
Poisson Process Jumping between an Unknown Number of Rates: Application to Neural Spike Data
Positive Curvature and Hamiltonian Monte Carlo
Predicting Useful Neighborhoods for Lazy Local Learning
Predictive Entropy Search for Efficient Global Optimization of Black-box Functions
Pre-training of Recurrent Neural Networks via Linear Autoencoders
Probabilistic Differential Dynamic Programming
Probabilistic low-rank matrix completion on finite alphabets
Probabilistic ODE Solvers with Runge-Kutta Means
Projecting Markov Random Field Parameters for Fast Mixing
Projective dictionary pair learning for pattern classification
Provable Submodular Minimization using Wolfe's Algorithm
Provable Tensor Factorization with Missing Data
Proximal Quasi-Newton for Computationally Intensive L1-regularized M-estimators
Quantized Estimation of Gaussian Sequence Models in Euclidean Balls
Quantized Kernel Learning for Feature Matching
QUIC & DIRTY: A Quadratic Approximation Approach for Dirty Statistical Models
RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning
Randomized Experimental Design for Causal Graph Discovery
Ranking via Robust Binary Classification
Rates of Convergence for Nearest Neighbor Classification
Real-Time Decoding of an Integrate and Fire Encoder
Recovery of Coherent Data via Low-Rank Dictionary Pursuit
Recurrent Models of Visual Attention
Recursive Context Propagation Network for Semantic Scene Labeling
Recursive Inversion Models for Permutations
Reducing the Rank in Relational Factorization Models by Including Observable Patterns
Repeated Contextual Auctions with Strategic Buyers
Reputation-based Worker Filtering in Crowdsourcing
Restricted Boltzmann machines modeling human choice
Robust Bayesian Max-Margin Clustering
Robust Classification Under Sample Selection Bias
Robust Kernel Density Estimation by Scaling and Projection in Hilbert Space
Robust Logistic Regression and Classification
Robust Tensor Decomposition with Gross Corruption
Rounding-based Moves for Metric Labeling
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives
Sampling for Inference in Probabilistic Models with Fast Bayesian Quadrature
Scalable Inference for Neuronal Connectivity from Calcium Imaging
Scalable Kernel Methods via Doubly Stochastic Gradients
Scalable Methods for Nonnegative Matrix Factorizations of Near-separable Tall-and-skinny Matrices
Scalable Non-linear Learning with Adaptive Polynomial Expansions
Scale Adaptive Blind Deblurring
Scaling-up Importance Sampling for Markov Logic Networks
Searching for Higgs Boson Decay Modes with Deep Learning
Self-Adaptable Templates for Feature Coding
Self-Paced Learning with Diversity
Semi-Separable Hamiltonian Monte Carlo for Inference in Bayesian Hierarchical Models

« prev Page 7/9 next »