a.rb

learning mixtures of ranking models
consistency of spectral partitioning of uniform hypergraphs under
optimal rates for $k$-nn density and mode estimation
bayesian inference for structured spike and slab priors
grouping-based low-rank video completion and 3d reconstruction
tightening after relax: minimax-optimal sparse pca in polynomial
belief propagation recursive neural networks
communication efficient distributed machine learning with the
on the statistical consistency of plug-in classifiers for
distributed context-aware bayesian posterior sampling via
neurons as monte carlo samplers: bayesian +inference and learning
feedback detection for live predictors
serialrank: spectral ranking using seriation
multi-class deep boosting
bandit convex optimization: towards tight bounds
concavity of reweighted kikuchi approximation
a framework for studying synaptic plasticity with neural spike
efficient structured matrix rank minimization
large-scale l-bfgs using mapreduce
a framework for testing identifiability of bayesian models of
dynamic topic modeling via rank factor analysis
global sensitivity analysis for map inference in graphical models
computing nash equilibria in generalized interdependent security
robust kernel density estimation by scaling and projection in
projective dictionary pair learning for pattern classification
blossom tree graphical models
capturing semantically meaningful word dependencies with an
reputation-based user filtering in crowd-sourcing systems
distance-based network recovery under feature correlation
zeta hull pursuits: learning non-convex data hulls
optimizing f-measures by cost-sensitive classification
submodular attribute selection for action recognition in video
online decision-making in general combinatorial spaces
robust logistic regression and classification
saga: a fast incremental gradient method with support for
provable submodular minimization using wolfe's algorithm
deep fragment embeddings for bidirectional image sentence mapping
learning shuffle ideals under restricted distributions
stochastic proximal gradient descent with acceleration techniques
efficient learning by implicit exploration in bandit problems with
inferring sparse representations of continuous signals with
a statistical decision-theoretic framework for social choice
unsupervised transcription of piano music
bounded regret for finite-armed structured bandits
tight continuous relaxation of the balanced k-cut problem
diverse sequential subset selection for supervised video
discrete graph hashing
learning to discover efficient mathematical identities
a boosting framework on grounds of online learning
multilabel structured output learning with random spanning trees of
stochastic variational inference for hidden markov models
fast multivariate spatio-temporal analysis via low rank tensor
convolutional neural network architectures for matching natural
message passing inference for large scale graphical models with
weakly-supervised discovery of visual pattern configurations
a complete variational tracker
probabilistic low-rank matrix completion on finite alphabets
improved multimodal deep learning with variation of information
oracle sparse pca and its inference
deep recursive neural networks for compositionality in language
bayesian nonlinear support vector machines and discriminative
efficient partial monitoring with prior information
structure learning of antiferromagnetic ising models
scalable methods for nonnegative matrix factorizations of
learning multiple tasks in parallel with a shared annotator
a wild bootstrap for degenerate kernel tests
communication-efficient distributed dual coordinate ascent
learning generative models with visual attention
shape and illumination from shading using the generic viewpoint
articulated pose estimation by a graphical model with image
unsupervised learning of an efficient short-term memory network
two-layer feature reduction for sparse-group lasso via
latent support measure machines for bag-of-words data
approximating hierarchical mv-sets for hierarchical clustering
local decorrelation for improved pedestrian detection
dependent nonparametric trees for dynamic hierarchical clustering
exact post model selection inference for marginal screening
generalized higher-order orthogonal iteration for tensor
on the computational efficiency of training neural networks
extracting certainty from uncertainty: transductive pairwise
joint training of a convolutional network and a graphical model for
online combinatorial optimization with stochastic decision sets and
fast kernel learning for multidimensional pattern extrapolation
randomized experimental design for causal graph discovery
pre-training of recurrent neural networks via linear autoencoders
sampling for inference in probabilistic models with fast bayesian
making pairwise binary graphical models attractive
incremental local gaussian regression
do deep nets really need to be deep?
mind the nuisance: gaussian process classification using privileged
new rules for domain independent lifted map inference
graphical models for recovering probabilistic and causal queries
the residual bootstrap for high-dimensional regression with
flexible transfer learning under support and model shift
top rank optimization in linear time
optimization methods for sparse pseudo-likelihood graphical model
tight bounds for influence in diffusion networks and application to
speeding-up graphical model optimization via a coarse-to-fine
spectral clustering of graphs with the bethe hessian
online and stochastic gradient methods for non-decomposable loss
a multi-world approach to question answering about real-world
general stochastic networks for classification
modeling sequences with a predictive gating network
combinatorial pure exploration of multi-armed bandits
ranking via robust binary classification
sequence to sequence learning with neural networks
simultaneous model selection and optimization through
fast and robust least squares estimation in corrupted linear models
parallel direction method of multipliers
transportability from multiple environments with limited
spectral methods for supervised topic models
a differential equation for modeling nesterov's accelerated
diverse randomized agents vote to win
learning mixtures of submodular functions for image collection
augmentative message passing for traveling salesman problem and
cone-constrained principal component analysis
elementary estimators for graphical models
active learning and best-response dynamics
a probabilistic framework for multimodal retrieval using
learning to optimize via information-directed sampling
simple map inference via low-rank relaxations
log-hilbert-schmidt metric between positive definite operators on
learning a concept hierarchy from multi-labeled documents
low rank approximation lower bounds in row-update streams
weighted importance sampling for off-policy learning with linear
a safe screening rule for sparse logistic regression
analysis of learning from positive and unlabeled data
multivariate regression with calibration
analysis of brain states from multi-region lfp time-series
mcmc sampling in hdps using sub-clusters
extremal mechanisms for local differential privacy
a representation theory for ranking functions
predictive entropy search for efficient global optimization of
estimation with norm regularization
beyond the birkhoff polytope: convex relaxations for vector
scaling-up importance sampling for markov logic networks
shaping social activity by incentivizing users
automatic discovery of cognitive skills to improve the prediction
efficient inference of continuous markov random fields with
clustering from labels and time-varying graphs
probabilistic ode solvers with runge-kutta means
best-arm identification in linear bandits
convex optimization procedure for clustering: theoretical revisit
greedy algorithms for finding diverse subsets in
a provable svd-based algorithm for learning topics in dominant
parallel double greedy submodular maximization
information-based learning by agents in unbounded state spaces
dimensionality reduction with subspace structure preservation
rates of convergence for nearest neighbor classification
graph clustering with missing data: convex algorithms and analysis
sensory integration and density estimation
nonparametric bayesian inference on multivariate exponential
trajectory optimization under unknown dynamics for policy search
fast sampling-based inference in balanced neuronal networks
optimal teaching for limited-capacity human learners
a filtering approach to stochastic variational inference
analysis of variational bayesian latent dirichlet allocation:
asynchronous anytime sequential monte carlo
optimal neural codes for control and estimation
conditional swap regret and conditional correlated equilibrium
multi-scale graphical models for spatio-temporal processes
a multiplicative model for learning distributed text-based
quantized kernel learning for feature matching
active regression by stratification
signal aggregate constraints in additive factorial hmms, with
positive curvature and hamiltonian monte carlo
on prior distributions and approximate inference for structured
non-convex robust pca
multi-resolution cascades for multiclass object detection
learning chordal markov networks by dynamic programming
on integrated clustering and outlier detection
an accelerated proximal coordinate gradient method
the linear convergence rate of decomposable submodular function
on multiplicative multitask feature learning
semi-separable hamiltonian monte carlo for inference in bayesian
multiscale fields of patterns
deep networks with internal selective attention through feedback
zero-shot recognition with unreliable attributes
joint task learning via deep neural networks with application to
the large margin mechanism for differentially private maximization
recursive context propagation network for semantic scene labeling
clustered factor analysis of multineuronal spike data
learning deep features for scene recognition using places database
on iterative hard thresholding methods for high-dimensional
provable tensor factorization with missing data
robust bayesian max-margin clustering
improved distributed principal component analysis
metric learning for temporal sequence alignment
generalized dantzig selector: application to the k-support norm
finding a sparse vector in a subspace: linear sparsity using
a synaptical story of persistent activity with graded lifetime in a
self-adaptable patterns for feature coding
from map to marginals: variational inference in bayesian submodular
hardness of parameter estimation in graphical models
delay-tolerant algorithms for asynchronous distributed online
generative adversarial nets
sparse dependent bayesian structure learning
localized data fusion for kernel k-means clustering with
an autoencoder approach to learning bilingual word representations
streaming, memory limited algorithms for community detection
content-based recommendations with poisson factorization
spectral methods for indian buffet process inference
learning to search in branch and bound algorithms
factoring variations in natural images with deep gaussian mixture
iterative neural autoregressive distribution estimator nade-k
minimax-optimal inference from partial rankings
discovering, learning and exploiting relevance
self-paced learning with diversity
spatio-temporal representations of uncertainty in spiking neural
smoothed gradients for stochastic variational inference
multi-step stochastic admm in high dimensions: applications to
spike frequency adaptation implements anticipative tracking in
feedforward learning of mixture models
mode estimation for high dimensional discrete tree graphical models
on communication cost of distributed statistical estimation and
distributed estimation, information loss and exponential families
distributed parameter estimation in probabilistic graphical models
on the information theoretic limits of learning ising models
fairness in multi-agent sequential decision-making
probabilistic differential dynamic programming
proximal quasi-newton for computationally intensive
clamping variables and approximate inference
spectral k-support norm regularization
exponential concentration of a density functional estimator
multitask learning meets tensor factorization: task imputation via
near-optimal-sample estimators for spherical gaussian mixtures
inferring synaptic conductances from spike trains with a
effective deep face representation comes from both identification
just-in-time learning for fast and flexible inference
pac-bayesian auc classification and scoring
on the relations of lfps & neural spike trains
optimal decision-making with time-varying evidence reliability
sparse polynomial learning and graph sketching
decoupled variational gaussian inference
bregman alternating direction method of multipliers
biclustering by message passing
expectation backpropagation: parameter-free training of multilayer
universal option models
latent case model: a generative approach for case-based reasoning
automated variational inference for gaussian process models
unsupervised learning by deep scattering contractions
learning time-varying coverage functions
discriminative unsupervised feature learning with convolutional
neural word embedding as implicit matrix factorization
searching for higgs boson decay modes with deep learning
rounding-based moves for metric labeling
nonparametric pairwise similarity for clustering
spectral methods meet em: a provably optimal algorithm for
bayes-adaptive simulation-based search with value function
a dual algorithm for olfactory computation in the locust brain
dfacto: distributed factorization of tensors
distributed balanced clustering via mapping coresets
efficient sampling for learning sparse additive models in high
predicting useful neighborhoods for lazy local learning
multi-scale spectral decomposition of massive graphs
large-margin convex polytope machine
parallel successive convex approximation for nonsmooth nonconvex
a drifting-games analysis for online learning and applications to
beyond disagreement-based agnostic active learning
convex deep learning via normalized kernels
subspace embeddings for the polynomial kernel
poisson process jumping between an unknown number of rates:
identifying and attacking the saddle point problem in
conditional random field autoencoders for unsupervised structured
local linear convergence of forward--backward under partial
learning from weakly supervised data by the expectation loss svm
learning the learning rate for prediction with expert advice
distributed variational inference in sparse gaussian process
efficient minimax strategies for square loss games
consistency of weighted majority votes
time--data tradeoffs by smoothing
a state-space model for decoding auditory attentional modulation
deep learning for real-time atari game play using offline
bayesian sampling using stochastic gradient thermostats
discovering structure in high-dimensional data through correlation
recovery of coherent data via low-rank dictionary pursuit
on the number of linear regions of deep neural networks
two-stream convolutional networks for action recognition in videos
optimizing energy production using policy search and predictive
separable deep convolutional neural network for image deconvolution
design principles of the hippocampal cognitive map
augur: data-parallel probabilistic modelling
asymmetric lsh (alsh) for sublinear time maximum inner product
deterministic symmetric positive semidefinite matrix completion
kernel mean estimation via spectral filtering
expectation-maximization for learning determinantal point processes
do convnets learn correspondence?
causal inference through a witness protection program
sparse space-time deconvolution for calcium image analysis
causal strategic inference in networked microfinance economies
stochastic network design in bidirected trees
algorithms for cvar optimization in mdps
from large-scale object classifiers to large-scale object
orbit regularization
robust classification under sample selection bias
deep symmetry networks
object localization based on structural svm using privileged
fast prediction for large-scale kernel machines
the limits of squared euclidean distance regularization
extreme bandits
from stochastic mixability to fast rates
stochastic multi-armed-bandit problem with non-stationary rewards
constant nullspace strong convexity and fast convergence of
semi-supervised learning with deep generative models
restricted boltzmann machines modeling human choice
learning convolution filters for inverse covariance estimation of
optimal regret minimization in posted-price auctions with strategic
attentional neural network: feature selection using cognitive
a block-coordinate descent approach for large-scale sparse inverse
quantized estimation of gaussian sequence models in euclidean balls
exploiting linear structure within convolutional networks for
altitude training: strong bounds for single-layer dropout
greedy subspace clustering
consistent binary classification with generalized performance
learning mixed multinomial logit model from ordinal data
exploiting easy data in online optimization
algorithm selection by rational metareasoning as a model of human
efficient optimization for average precision svm
compressive sensing of signals from a gmm with sparse precision
large scale canonical correlation analysis with iterative least
parallel feature selection inspired by group testing
partition-wise linear models
recursive inversion models for permutations
the noisy power method: a meta algorithm with applications
multivariate f-divergence estimation with confidence
fundamental limits of online and distributed algorithms for
stochastic gradient descent, weighted sampling, and the randomized
gibbs-type indian buffet processes
depth map prediction from a single image using a multi-scale deep
testing unfaithful gaussian graphical models
hamming ball auxiliary sampling for factorial hidden markov models
difference of convex functions programming for reinforcement
permutation diffusion maps (pdm) with application to the image
fast training of pose detectors in the fourier domain
sparse pca via covariance thresholding
the infinite mixture of infinite gaussian mixtures
scalable inference for neuronal connectivity from calcium imaging
incremental clustering: the case for extra clusters
general table completion using a bayesian nonparametric model
accelerated mini-batch randomized block coordinate descent method
distributed power-law graph computing: theoretical and empirical
online optimization for max-norm regularization
covariance shrinkage for autocorrelated data
deep learning multi-view representation for face recognition
low-dimensional models of neural population activity in sensory
tight convex relaxations for sparse matrix factorization
scalable kernel methods via doubly stochastic gradients
divide-and-conquer learning by anchoring a conical hull
magnitude-sensitive preference formation`
low-rank time-frequency synthesis
learning with pseudo-ensembles
efficient minimax signal detection on graphs
sparse random feature algorithm as coordinate descent in hilbert
a latent source model for online collaborative filtering
coresets for k-segmentation of streaming data
mondrian forests: efficient online random forests
scalable non-linear learning with adaptive polynomial expansions
near-optimal density estimation in near-linear time using
variational gaussian process state-space models
sequential monte carlo for graphical models
learning with fredholm kernels
projecting markov random field parameters for fast mixing
learning distributional representations for structured output
an integer polynomial programming based framework for lifted map
optimistic planning in markov decision processes using a generative
sparse multi-task reinforcement learning
encoding high dimensional local features by sparse coding based
deconvolution of high dimensional mixtures via boosting, with
learning on graphs using orthonormal representation is
raam: the benefits of robustness in approximating aggregated mdps
learning from latent and observable patterns on multi-relational
a statistical model for tensor pca
quantifying the transferability of features in deep neural networks
on sparse gaussian chain graph models
robust tensor decomposition with gross corruption
quic & dirty: a quadratic approximation approach for dirty
scale adaptive blind deblurring
constrained convex minimization via model-based excessive gap
real-time decoding of an integrate and fire encoder
advances in learning bayesian networks of bounded treewidth
pewa: patch-based exponentially weighted aggregation for image
extracting latent structure from multiple interacting neural
extended and unscented gaussian processes
primitives for dynamic big model parallelism
decomposing parameter estimation problems
median selection subset aggregation for parallel inference
model-based reinforcement learning and the eluder dimension
feature cross-substitution in adversarial classification
exclusive feature learning on arbitrary structures
using convolutional neural networks to recognize rhythm +stimuli
convolutional kernel networks
discriminative metric learning by neighborhood gerrymandering
repeated contextual auctions with strategic buyers
a unified semantic embedding with discriminative / generative
controlling privacy in recommender systems
gaussian process volatility model
beta-negative binomial process and exchangeable +random partitions
near-optimal sample compression for nearest neighbors
learning to think like a drug dealer: efficient optimization
analog memories in a balanced rate-based network of e-i neurons
optimal prior-dependent neural population coding under shared input
recurrent models of visual attention
a bayesian model for identifying hierarchically organised states in
tree-structured gaussian process approximations
spectral learning of mixture of hidden markov models
the blinded bandit: learning with adaptive feedback
near-optimal reinforcement learning in factored mdps
generalized unsupervised manifold alignment