NeurIPS(NIPS) 2012 论文列表
Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States.
|
Cardinality Restricted Boltzmann Machines.
Confusion-Based Online Learning and a Passive-Aggressive Scheme.
Risk-Aversion in Multi-armed Bandits.
Interpreting prediction markets: a stochastic approach.
Tight Bounds on Profile Redundancy and Distinguishability.
Trajectory-Based Short-Sighted Probabilistic Planning.
Discriminative Learning of Sum-Product Networks.
Latent Coincidence Analysis: A Hidden Variable Model for Distance Metric Learning.
On the Sample Complexity of Robust PCA.
Best Arm Identification: A Unified Approach to Fixed Budget and Fixed Confidence.
Deep Learning of Invariant Features via Simulated Fixations in Video.
Continuous Relaxations for Discrete Hamiltonian Monte Carlo.
Simultaneously Leveraging Output and Task Structures for Multiple-Output Regression.
Entropy Estimations Using Correlated Symmetric Stable Random Projections.
A latent factor model for highly multi-relational data.
Small-Variance Asymptotics for Exponential Family Dirichlet Process Mixture Models.
Imitation Learning by Coaching.
Fast Bayesian Inference for Non-Conjugate Gaussian Process Regression.
Risk Aversion in Markov Decision Processes via Near Optimal Chernoff Bounds.
Unsupervised Template Learning for Fine-Grained Object Recognition.
One Permutation Hashing.
Efficient and direct estimation of a neural subunit model for sensory coding.
Probabilistic Event Cascades for Alzheimer's disease.
Locating Changes in Highly Dependent Data with Unknown Number of Change Points.
Learning with Partially Absorbing Random Walks.
Cost-Sensitive Exploration in Bayesian Reinforcement Learning.
Complex Inference in Neural Circuits with Probabilistic Population Codes and Topic Models.
Probabilistic n-Choose-k Models for Classification and Ranking.
Human memory search as a random walk in a semantic network.
Hierarchical spike coding of sound.
Projection Retrieval for Classification.
Convergence Rate Analysis of MAP Coordinate Minimization Algorithms.
A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function.
Priors for Diversity in Generative Latent Variable Models.
A nonparametric variable clustering model.
Fusion with Diffusion for Robust Visual Tracking.
The Time-Marginalized Coalescent Prior for Hierarchical Clustering.
Forging The Graphs: A Low Rank and Positive Semidefinite Graph Learning Approach.
Practical Bayesian Optimization of Machine Learning Algorithms.
Minimizing Uncertainty in Pipelines.
Submodular-Bregman and the Lovász-Bregman Divergences with Applications.
Distributed Probabilistic Learning for Camera Networks with Missing Data.
Controlled Recognition Bounds for Visual Learning and Exploration.
Accelerated Training for Matrix-norm Regularization: A Boosting Approach.
Bayesian Pedigree Analysis using Measure Factorization.
Fast Variational Inference in the Conjugate Exponential Family.
Sparse Approximate Manifolds for Differential Geometric MCMC.
Online Sum-Product Computation Over Trees.
Gradient Weights help Nonparametric Regressors.
Scalable imputation of genetic data with a discrete fragmentation-coagulation process.
Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images.
Link Prediction in Graphs with Autoregressive Features.
Learning with Recursive Perceptual Representations.
Learning Label Trees for Probabilistic Modelling of Implicit Feedback.
Topic-Partitioned Multinetwork Embeddings.
FastEx: Hash Clustering with Exponential Families.
Multiclass Learning with Simplex Coding.
Learning Networks of Heterogeneous Influence.
Perceptron Learning of SAT.
Density Propagation and Improved Bounds on the Partition Function.
How They Vote: Issue-Adjusted Models of Legislative Behavior.
Probabilistic Low-Rank Subspace Clustering.
Near-Optimal MAP Inference for Determinantal Point Processes.
Entangled Monte Carlo.
A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes.
A Neural Autoregressive Topic Model.
Truly Nonparametric Online Variational Inference for Hierarchical Dirichlet Processes.
"Burn-in, bias, and the rationality of anchoring".
Emergence of Object-Selective Features in Unsupervised Feature Learning.
Query Complexity of Derivative-Free Optimization.
A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets.
Scaling MPE Inference for Constrained Continuous Markov Random Fields with Consensus Optimization.
Multilabel Classification using Bayesian Compressed Sensing.
Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems.
Exact and Stable Recovery of Sequences of Signals with Sparse Increments via Differential _1-Minimization.
A quasi-Newton proximal splitting method.
Expectation Propagation in Gaussian Process Dynamical Systems.
Modelling Reciprocating Relationships with Hawkes Processes.
Ancestor Sampling for Particle Gibbs.
Factorial LDA: Sparse Multi-Dimensional Text Models.
Non-linear Metric Learning.
Minimization of Continuous Bethe Approximations: A Positive Variation.
Transferring Expectations in Model-based Reinforcement Learning.
Augment-and-Conquer Negative Binomial Processes.
Exponential Concentration for Mutual Information Estimation with Application to Forests.
Semi-supervised Eigenvectors for Locally-biased Learning.
Tensor Decomposition for Fast Parsing with Latent-Variable PCFGs.
Adaptive Learning of Smoothing Functions: Application to Electricity Load Forecasting.
Label Ranking with Partial Abstention based on Thresholded Probabilistic Models.
Learning Probability Measures with respect to Optimal Transport Metrics.
A Polynomial-time Form of Robust Regression.
Iterative ranking from pair-wise comparisons.
Learning Manifolds with K-Means and K-Flats.
Towards a learning-theoretic analysis of spike-timing dependent plasticity.
A Better Way to Pretrain Deep Boltzmann Machines.
Approximate Message Passing with Consistent Parameter Estimation and Applications to Sparse Learning.
Multiple Operator-valued Kernel Learning.
Recovery of Sparse Probability Measures via Convex Programming.
Bayesian models for Large-scale Hierarchical Classification.
No-Regret Algorithms for Unconstrained Online Convex Optimization.
Dip-means: an incremental clustering method for estimating the number of clusters.
Globally Convergent Dual MAP LP Relaxation Solvers using Fenchel-Young Margins.
"Provable ICA with Unknown Gaussian Noise, with Implications for Gaussian Mixtures and Autoencoders".
Learning the Dependency Structure of Latent Factors.
Weighted Likelihood Policy Search with Model Selection.
Bayesian active learning with localized priors for fast receptive field characterization.
A Simple and Practical Algorithm for Differentially Private Data Release.
A Divide-and-Conquer Method for Sparse Inverse Covariance Estimation.
Approximating Equilibria in Sequential Auctions with Incomplete Information and Multi-Unit Demand.
The topographic unsupervised learning of natural sounds in the auditory cortex.
Rational inference of relative preferences.
Collaborative Ranking With 17 Parameters.
Learning optimal spike-based representations.
Why MCA? Nonlinear sparse coding with spike-and-slab prior for neurally plausible image encoding.
A systematic approach to extracting semantic information from functional MRI data.
Online L1-Dictionary Learning with Application to Novel Document Detection.
Scalable Inference of Overlapping Communities.
Slice sampling normalized kernel-weighted completely random measure mixture models.
Learning with Target Prior.
Multimodal Learning with Deep Boltzmann Machines.
Sketch-Based Linear Value Function Approximation.
Clustering Sparse Graphs.
Learning from the Wisdom of Crowds by Minimax Entropy.
Affine Independent Variational Inference.
Algorithms for Learning Markov Field Policies.
"Optimal Neural Tuning Curves for Arbitrary Stimulus Distributions: Discrimax, Infomax and Minimum $L_p$ Loss".
Spectral Learning of General Weighted Automata via Constrained Matrix Completion.
Minimax Multi-Task Learning and a Generalized Loss-Compositional Paradigm for MTL.
Relax and Randomize : From Value to Algorithms.
On Triangular versus Edge Representations --- Towards Scalable Modeling of Networks.
Strategic Impatience in Go/NoGo versus Forced-Choice Decision-Making.
Gradient-based kernel method for feature extraction and variable selection.
Approximating Concavely Parameterized Optimization Problems.
Collaborative Gaussian Processes for Preference Learning.
Structure estimation for discrete graphical models: Generalized covariance matrices and their inverses.
Classification Calibration Dimension for General Multiclass Losses.
Tractable Objectives for Robust Policy Optimization.
Reducing statistical time-series problems to binary classification.
Bayesian nonparametric models for bipartite graphs.
Pointwise Tracking the Optimal Regression Function.
Learning the Architecture of Sum-Product Networks Using Clustering on Variables.
A Geometric take on Metric Learning.
Bayesian estimation of discrete entropy with mixtures of stick-breaking priors.
Phoneme Classification using Constrained Variational Gaussian Process Dynamical System.
From Deformations to Parts: Motion-based Segmentation of 3D Objects.
Multi-Stage Multi-Task Feature Learning.
A mechanistic model of early sensory processing based on subtracting sparse representations.
Learning as MAP Inference in Discrete Graphical Models.
Online allocation and homogeneous partitioning for piecewise constant mean-approximation.
The Coloured Noise Expansion and Parameter Estimation of Diffusion Processes.
Communication/Computation Tradeoffs in Consensus-Based Distributed Optimization.
The Perturbed Variation.
Diffusion Decision Making for Adaptive k-Nearest Neighbor Classification.
Meta-Gaussian Information Bottleneck.
Slice Normalized Dynamic Markov Logic Networks.
Fully Bayesian inference for neural models with negative-binomial spiking.
Repulsive Mixtures.
Efficient Monte Carlo Counterfactual Regret Minimization in Games with Many Player Actions.
Neurally Plausible Reinforcement Learning of Working Memory Tasks.
Fiedler Random Fields: A Large-Scale Spectral Approach to Statistical Network Modeling.
Bayesian Nonparametric Modeling of Suicide Attempts.
MAP Inference in Chains using Column Generation.
Efficient Spike-Coding with Multiplicative Adaptation in a Spike Response Model.
On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes.
Persistent Homology for Learning Densities with Bounded Support.
Mixing Properties of Conditional Markov Chains with Unbounded Feature Functions.
Multiple Choice Learning: Learning to Produce Multiple Structured Outputs.
Kernel Hyperalignment.
Learning curves for multi-task Gaussian process regression.
Semi-Crowdsourced Clustering: Generalizing Crowd Labeling by Robust Distance Metric Learning.
Generalization Bounds for Domain Adaptation.
Online Regret Bounds for Undiscounted Continuous Reinforcement Learning.
Active Comparison of Prediction Models.
Dual-Space Analysis of the Sparse Linear Model.
"Natural Images, Gaussian Mixtures and Dead Leaves".
Causal discovery with scale-mixture model for spatiotemporal variance dependencies.
Semantic Kernel Forests from Multiple Taxonomies.
A lattice filter model of the visual pathway.
Waveform Driven Plasticity in BiFeO3 Memristive Devices: Model and Implementation.
Mixability in Statistical Learning.
Spectral learning of linear dynamics from generalised-linear observations with application to neural population data.
Convex Multi-view Subspace Learning.
On the connections between saliency and tracking.
On Lifting the Gibbs Sampling Algorithm.
Isotropic Hashing.
Multiresolution analysis on the symmetric group.
Nonparametric Reduced Rank Regression.
Bayesian Warped Gaussian Processes.
A Linear Time Active Learning Algorithm for Link Classification.
Parametric Local Metric Learning for Nearest Neighbor Classification.
Monte Carlo Methods for Maximum Margin Supervised Topic Models.
Selecting Diverse Features via Spectral Regularization.
Iterative Thresholding Algorithm for Sparse Inverse Covariance Estimation.
Proper losses for learning from partial labels.
Joint Modeling of a Matrix with Associated Text via Latent Binary Features.
Graphical Gaussian Vector for Image Categorization.
Stochastic optimization and sparse statistical recovery: Optimal algorithms for high dimensions.
Feature-aware Label Space Dimension Reduction for Multi-label Classification.
Bayesian nonparametric models for ranked data.
Identifiability and Unmixing of Latent Parse Trees.
Communication-Efficient Algorithms for Statistical Optimization.
Forward-Backward Activation Algorithm for Hierarchical Hidden Markov Models.
On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization.
Learning Multiple Tasks using Shared Hypotheses.
Active Learning of Multi-Index Function Models.
Sparse Prediction with the $k$-Support Norm.
Hierarchical Optimistic Region Selection driven by Curiosity.
Finite Sample Convergence Rates of Zero-Order Stochastic Optimization Methods.
Privacy Aware Learning.
Q-MKL: Matrix-induced Regularization in Multi-Kernel Learning with Applications to Neuroimaging.
Scaled Gradients on Grassmann Manifolds for Matrix Completion.
Bayesian Probabilistic Co-Subspace Addition.
Symbolic Dynamic Programming for Continuous State and Observation POMDPs.
Convergence and Energy Landscape for Cheeger Cut Clustering.
Co-Regularized Hashing for Multimodal Data.
CPRL -- An Extension of Compressive Sensing to the Phase Retrieval Problem.
Graphical Models via Generalized Linear Models.
"Compressive neural representation of sparse, high-dimensional probabilities".
Value Pursuit Iteration.
Learned Prioritization for Trading Off Accuracy and Speed.
Learning visual motion in recurrent neural networks.
Efficient Sampling for Bipartite Matching Problems.
Efficient coding provides a direct link between prior and likelihood in perceptual Bayesian inference.
Effective Split-Merge Monte Carlo Methods for Nonparametric Models of Sequential Data.
Symmetric Correspondence Topic Models for Multilingual Text Analysis.
High-Order Multi-Task Feature Learning to Identify Longitudinal Phenotypic Markers for Alzheimer's Disease Progression Prediction.
How Prior Probability Influences Decision Making: A Unifying Probabilistic Model.
Fused sparsity and robust estimation for linear models with unknown variance.
A Convex Formulation for Learning Scale-Free Networks via Submodular Relaxation.
Wavelet based multi-scale shape features on arbitrary surfaces for cortical thickness discrimination.
Statistical Consistency of Ranking Methods in A Rank-Differentiable Probability Space.
Large Scale Distributed Deep Networks.
Factoring nonnegative matrices with linear programs.
Optimal kernel choice for large-scale two-sample tests.
Angular Quantization-based Binary Codes for Fast Similarity Search.
A Marginalized Particle Gaussian Process Regression.
Unsupervised Structure Discovery for Semantic Analysis of Audio.
Multi-Task Averaging.
"The Lovasz $\theta$ function, SVMs and finding large dense subgraphs".
On Multilabel Classification and Ranking with Partial Feedback.
GenDeR: A Generic Diversified Ranking Algorithm.
A Bayesian Approach for Policy Learning from Trajectory Preference Queries.
Training sparse natural image models with a fast Gibbs sampler of an extended state space.
Compressive Sensing MRI with Wavelet Tree Sparsity.
Recognizing Activities by Attribute Dynamics.
ImageNet Classification with Deep Convolutional Neural Networks.
A dynamic excitatory-inhibitory network in a VLSI chip for spiking information reregistration.
Delay Compensation with Dynamical Synapses.
Clustering by Nonnegative Matrix Factorization Using Graph Random Walk.
Spiking and saturating dendrites differentially expand single neuron computation capacity.
Hamming Distance Metric Learning.
Learning Mixtures of Tree Graphical Models.
Latent Graphical Model Selection: Efficient Methods for Locally Tree-like Graphs.
Dimensionality Dependent PAC-Bayes Margin Bound.
Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search.
Augmented-SVM: Automatic space partitioning for combining multiple non-linear dynamics.
Inverse Reinforcement Learning through Structured Classification.
Random function priors for exchangeable arrays with applications to graphs and relational data.
Near-optimal Differentially Private Principal Components.
Mirror Descent Meets Fixed Share (and feels no regret).
Perfect Dimensionality Recovery by Variational Bayesian PCA.
Minimizing Sparse High-Order Energies by Submodular Vertex-Cover.
Accuracy at the Top.
Analog readout for optical reservoir computers.
Matrix reconstruction with the local max norm.
Learning Halfspaces with the Zero-One Loss: Time-Accuracy Tradeoffs.
A Spectral Algorithm for Latent Dirichlet Allocation.
Deep Representations and Codes for Image Auto-Annotation.
Nonparanormal Belief Propagation (NPNBP).
Timely Object Recognition.
Searching for objects driven by context.
Predicting Action Content On-Line and in Real Time before Action Onset - an Intracranial Human Study.
Calibrated Elastic Regularization in Matrix Completion.
Synchronization can Control Regularization in Neural Systems via Correlated Noise Processes.
Multi-criteria Anomaly Detection using Pareto Depth Analysis.
Regularized Off-Policy TD-Learning.
Proximal Newton-type methods for convex optimization.
Learning Partially Observable Models Using Temporally Abstract Decision Trees.
Kernel Latent SVM for Visual Recognition.
Transelliptical Graphical Models.
Topology Constraints in Graphical Models.
Clustering Aggregation as Maximum-Weight Independent Set.
Homeostatic plasticity in Bayesian spiking networks as Expectation Maximization with posterior constraints.
Learning to Align from Scratch.
Newton-Like Methods for Sparse Inverse Covariance Estimation.
Localizing 3D cuboids in single-view images.
Multiresolution Gaussian Processes.
Learning High-Density Regions for a Generalized Kolmogorov-Smirnov Test in High-Dimensional Data.
Learning about Canonical Views from Internet Image Collections.
A P300 BCI for the Masses: Prior Information Enables Instant Unsupervised Spelling.
MCMC for continuous-time discrete-state systems.
Variational Inference for Crowdsourcing.
Density-Difference Estimation.
Identification of Recurrent Patterns in the Activation of Brain Networks.
Semi-Supervised Domain Adaptation with Non-Parametric Copulas.
Convolutional-Recursive Deep Learning for 3D Object Classification.
A Scalable CUR Matrix Decomposition Algorithm: Lower Time Complexity and Tighter Bound.
Shifting Weights: Adapting Object Detectors from Image to Video.
A Polylog Pivot Steps Simplex Algorithm for Classification.
Structured Learning of Gaussian Graphical Models.
3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model.
Nonconvex Penalization Using Laplace Exponents and Concave Conjugates.
Analyzing 3D Objects in Cluttered Images.
Discriminatively Trained Sparse Code Gradients for Contour Detection.
Efficient high dimensional maximum entropy modeling via symmetric partition functions.
Ensemble weighted kernel estimators for multivariate entropy estimation.
Majorization for CRFs and Latent Likelihoods.
A Conditional Multinomial Mixture Model for Superset Label Learning.
Learning to Discover Social Circles in Ego Networks.
Scalable nonconvex inexact proximal splitting.
Assessing Blinding in Clinical Trials.
Deep Spatio-Temporal Architectures and Learning for Protein Structure Prediction.
"Neuronal spike generation mechanism as an oversampling, noise-shaping A-to-D converter".
Stochastic Gradient Descent with Only One Projection.
Multiclass Learning Approaches: A Theoretical Comparison with Implications.
Nyström Method vs Random Fourier Features: A Theoretical and Empirical Comparison.
Patient Risk Stratification for Hospital-Associated C. diff as a Time-Series Classification Task.
Multiplicative Forests for Continuous-Time Processes.
Bandit Algorithms boost Brain Computer Interfaces for motor-task selection of a brain-controlled button.
Learning Invariant Representations of Molecules for Atomization Energy Prediction.
Context-Sensitive Decision Forests for Object Detection.
3D Social Saliency from Head-mounted Cameras.
Truncation-free Online Variational Inference for Bayesian Nonparametric Models.
The variational hierarchical EM algorithm for clustering hidden Markov models.
Optimal Regularized Dual Averaging Methods for Stochastic Optimization.
Non-parametric Approximate Dynamic Programming via the Kernel Method.
Visual Recognition using Embedded Feature Selection for Curvature Self-Similarity.
Action-Model Based Multi-agent Plan Recognition.
Transelliptical Component Analysis.
Max-Margin Structured Output Regression for Spatio-Temporal Action Localization.
Image Denoising and Inpainting with Deep Neural Networks.
Volume Regularization for Binary Classification.
Selective Labeling via Error Bound Minimization.
Automatic Feature Induction for Stagewise Collaborative Filtering.
Nonparametric Bayesian Inverse Reinforcement Learning for Multiple Reward Functions.
Memorability of Image Regions.
Multi-task Vector Field Learning.
Fast Resampling Weighted v-Statistics.
Learning Image Descriptors with the Boosting-Trick.
An Integer Optimization Approach to Associative Classification.
Distributed Non-Stochastic Experts.
Adaptive Stratified Sampling for Monte-Carlo integration of Differentiable functions.
Dynamical And-Or Graph Learning for Object Shape Modeling and Detection.
Robustness and risk-sensitivity in Markov decision processes.
Cocktail Party Processing via Structured Prediction.
Supervised Learning with Similarity Functions.
Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress.
"On the (Non-)existence of Convex, Calibrated Surrogate Losses for Ranking".
The representer theorem for Hilbert spaces: a necessary and sufficient condition.
Coding efficiency and detectability of rate fluctuations with non-Poisson neuronal firing.
Semiparametric Principal Component Analysis.
Smooth-projected Neighborhood Pursuit for High-dimensional Nonparanormal Graph Estimation.
Mandatory Leaf Node Prediction in Hierarchical Multilabel Classification.
A new metric on the manifold of kernel matrices with application to matrix geometric means.
Putting Bayes to sleep.
Random Utility Theory for Social Choice.
The Bethe Partition Function of Log-supermodular Graphical Models.
Super-Bit Locality-Sensitive Hashing.
A Generative Model for Parts-based Object Segmentation.
Local Supervised Learning through Space Partitioning.
Dynamic Pruning of Factor Graphs for Maximum Marginal Prediction.
Bayesian Hierarchical Reinforcement Learning.
Nonparametric Max-Margin Matrix Factorization for Collaborative Prediction.
Coupling Nonparametric Mixtures via Latent Dirichlet Processes.
Active Learning of Model Evidence Using Bayesian Quadrature.
Multi-scale Hyper-time Hardware Emulation of Human Motor Nervous System Based on Spiking Neurons using FPGA.
Feature Clustering for Accelerating Parallel Coordinate Descent.
Finding Exemplars from Pairwise Dissimilarities via Simultaneous Sparse Recovery.
Learning from Distributions via Support Measure Machines.
Locally Uniform Comparison Image Descriptor.
