NIPS 2015 has ended

Create Your Own Event

NIPS 2015

arrow_back View All Dates

07:30 EST

Breakfast 220 A

09:00 EST

Learning with Intelligent Teacher: Similarity Control and Knowledge Transfer Level 2 room 210 AB

09:50 EST

Less is More: Nyström Computational Regularization Room 210 A

10:10 EST

Collaborative Filtering with Graph Information: Consistency and Scalable Methods Room 210 A Efficient and Parsimonious Agnostic Active Learning Room 210 A Fast and Guaranteed Tensor Decomposition via Sketching Room 210 A Learning with Symmetric Label Noise: The Importance of Being Unhinged Room 210 A Logarithmic Time Online Multiclass prediction Room 210 A Matrix Completion with Noisy Side Information Room 210 A Scalable Semi-Supervised Aggregation of Classifiers Room 210 A Spherical Random Features for Polynomial Kernels Room 210 A

10:50 EST

Coffee Break 210 A

11:00 EST

A fast, universal algorithm to learn parametric nonlinear embeddings 210 C #28 A Gaussian Process Model of Quasar Spectral Energy Distributions 210 C #16 A Market Framework for Eliciting Private Data 210 C #56 A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA 210 C #50 Active Learning from Weak and Strong Labelers 210 C #46 Adaptive Low-Complexity Sequential Inference for Dirichlet Process Mixture Models 210 C #100 Adaptive Stochastic Optimization: From Sets to Paths 210 C #69 Algorithmic Stability and Uniform Generalization 210 C #84 Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits 210 C #73 Analysis of Robust PCA via Local Incoherence 210 C #83 Asynchronous stochastic convex optimization: the noise is in the noise and SGD don't care 210 C #96 Bayesian dark knowledge 210 C #21 Bayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM) 210 C #29 Bounding the Cost of Search-Based Lifted Inference 210 C #39 Collaborative Filtering with Graph Information: Consistency and Scalable Methods 210 C #62 Column Selection via Adaptive Sampling 210 C #76 Compressive spectral embedding: sidestepping the SVD 210 C #52 Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting 210 C #11 Convolutional Networks on Graphs for Learning Molecular Fingerprints 210 C #10 Convolutional spike-triggered covariance analysis for neural subunit models 210 C #18 Copeland Dueling Bandits 210 C #88 Cornering Stationary and Restless Mixing Bandits with Remix-UCB 210 C #94 Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling 210 C #34 Cross-Domain Matching for Bag-of-Words Data via Kernel Embeddings of Latent Distributions 210 C #15 Differentially private subspace clustering 210 C #51 Discriminative Robust Transformation Learning 210 C #31 Efficient and Parsimonious Agnostic Active Learning 210 C #61 Efficient Compressive Phase Retrieval with Constrained Sensing Vectors 210 C #86 Efficient Learning by Directed Acyclic Graph For Resource Constrained Prediction 210 C #40 Efficient Thompson Sampling for Online Matrix-Factorization Recommendation 210 C #43 Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images 210 C #20 End-to-end Learning of LDA by Mirror-Descent Back Propagation over a Deep Architecture 210 C #23 Enforcing balance allows local supervised learning in spiking recurrent networks 210 C #4 Estimating Jaccard Index with Missing Observations: A Matrix Calibration Approach 210 C #41 Fast and Guaranteed Tensor Decomposition via Sketching 210 C #47 Fast Classification Rates for High-dimensional Gaussian Generative Models 210 C #60 Fast Distributed k-Center Clustering with Outliers on Massive Data 210 C #58 Fast Lifted MAP Inference via Partitioning 210 C #45 Fast Rates for Exp-concave Empirical Risk Minimization 210 C #99 Fighting Bandits with a New Kind of Smoothness 210 C #95 From random walks to distances on unweighted graphs 210 C #74 Generalization in Adaptive Data Analysis and Holdout Reuse 210 C #53 GP Kernels for Cross-Spectrum Analysis 210 C #22 Improved Iteration Complexity Bounds of Cyclic Block Coordinate Descent for Convex Problems 210 C #93 Learnability of Influence in Networks 210 C #49 Learning structured densities via infinite dimensional exponential families 210 C #70 Learning to Linearize Under Uncertainty 210 C #7 Learning with Incremental Iterative Regularization 210 C #80 Learning with Symmetric Label Noise: The Importance of Being Unhinged 210 C #72 Less is More: Nyström Computational Regularization 210 C #63 Lifelong Learning with Non-i.i.d. Tasks 210 C #71 Local Causal Discovery of Direct Causes and Effects 210 C #30 Logarithmic Time Online Multiclass prediction 210 C #37 M-Best-Diverse Labelings for Submodular Energies and Beyond 210 C #33 Matrix Completion with Noisy Side Information 210 C #55 Max-Margin Deep Generative Models 210 C #14 Max-Margin Majority Voting for Learning from Crowds 210 C #32 Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction 210 C #13 Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path 210 C #85 Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms 210 C #77 Natural Neural Networks 210 C #9 Neural Adaptive Sequential Monte Carlo 210 C #17 No-Regret Learning in Bayesian Games 210 C #81 On the Optimality of Classifier Chain for Multi-label Classification 210 C #65 On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs 210 C #92 Online F-Measure Optimization 210 C #54 Online Learning for Adversaries with Memory: Price of Past Mistakes 210 C #90 Online Learning with Gaussian Payoffs and Side Observations 210 C #98 Optimal Linear Estimation under Unknown Nonlinear Transform 210 C #78 Optimal Ridge Detection using Coverage Risk 210 C #57 Orthogonal NMF through Subspace Exploration 210 C #59 Parallel Recursive Best-First AND/OR Search for Exact MAP Inference in Graphical Models 210 C #36 Parallelizing MCMC with Random Partition Trees 210 C #44 Particle Gibbs for Infinite Hidden Markov Models 210 C #24 Predtron: A Family of Online Algorithms for General Prediction Problems 210 C #64 Rectified Factor Networks 210 C #19 Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring 210 C #89 Revenue Optimization against Strategic Buyers 210 C #91 Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach 210 C #79 Robust Regression via Hard Thresholding 210 C #75 Robust Spectral Inference for Joint Stochastic Matrix Factorization 210 C #26 Saliency, Scale and Information: Towards a Unifying Theory 210 C #2 Sample Efficient Path Integral Control under Uncertainty 210 C #42 Scalable Semi-Supervised Aggregation of Classifiers 210 C #38 Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks 210 C #12 Secure Multi-party Differential Privacy 210 C #68 Semi-supervised Learning with Ladder Networks 210 C #3 Semi-supervised Sequence Learning 210 C #5 Skip-Thought Vectors 210 C #6 Smooth Interactive Submodular Set Cover 210 C #66 Space-Time Local Embeddings 210 C #27 Sparse and Low-Rank Tensor Decomposition 210 C #82 Sparse Local Embeddings for Extreme Multi-label Classification 210 C #25 Spherical Random Features for Polynomial Kernels 210 C #48 Synaptic Sampling: A Bayesian Approach to Neural Network Plasticity and Rewiring 210 C #8 Teaching Machines to Read and Comprehend 210 C #1 The Pareto Regret Frontier for Bandits 210 C #97 Time-Sensitive Recommendation From Recurrent User Activities 210 C #35 Tractable Bayesian Network Structure Learning with Bounded Vertex Cover Number 210 C #67 Unified View of Matrix Completion under General Structural Constraints 210 C #87

15:00 EST

Algorithms Among Us: the Societal Impacts of Machine Learning 210 e, f Level 2 Brains, Minds and Machines Level 5 Room 510 BD Deep Learning Symposium 210 a,b Level 2

16:15 EST

18:00 EST

Hors d'oeuvres 220A