In [1]:
import numpy as np
from nltk.cluster.util import cosine_distance
from nltk.cluster.kmeans import KMeansClusterer
import matplotlib.pylab as plt
%matplotlib inline

from make_index import build_index, get_vocabulary, build_inverted_index, get_tf_matrix, normalize

In [2]:
dir_path = "./txt/"
index, doc_id_to_path = build_index(dir_path)
vocabulary, term_to_id = get_vocabulary(index)
voc_size = vocabulary.shape[0]
inverted_index = build_inverted_index(index, term_to_id)

num_docs = len(index)
del index

tf_matrix = get_tf_matrix(inverted_index, num_docs)
tf_matrix = normalize(tf_matrix)

In [3]:
print num_docs, "документа"


403 документа

Не нашёл библиотеки, которая позволяла бы делать разложение на 1000 сингулярных чисел (>403). Есть имплементации с параметром full_matrices, но для них не хватает оперативной памяти. Поэтому делаю разложение на размер наименьшей оси (кол-во документов).


In [4]:
%%time
T, S, Dt = np.linalg.svd(tf_matrix, full_matrices=False)


CPU times: user 11.7 s, sys: 2.56 s, total: 14.3 s
Wall time: 2.05 s

Посчитаем и изобразим норму разности истинной нормированной матрицы и восстановленной по неполному сингулярному разложению: $\left \| \hat{A} - \hat{A}_{r} \right \|$ в зависимости от числа взятых сингулярных чисел.


In [5]:
sub_norms = np.cumsum((S**2)[::-1])[::-1]
sub_norms = list(sub_norms[1:]) + [0]

plt.figure(figsize=(10,7))
plt.ylabel("Matrices' subtraction norm")
plt.xlabel("r")
plt.plot(range(num_docs), sub_norms);


Выберем r=403, т.к.

1) на всей длине кривая имеет дост-но большую производную (по модулю)

2) 403 не очень большое число для семантического пространства

Получим представления документов.


In [6]:
r = 403
D_lsi = Dt[:r,:].transpose()

Откластеризуем их.

Я смотрел на названия работ и на топовые (по нормированному tf) слова. Но попытки интерпретировать кластеры оказались тщетны. Поэтому выбрал число кластеров 10.


In [8]:
from utils import STOP_WORDS, get_top_terms
stop_words_ids = [term_to_id[term] for term in STOP_WORDS if term in term_to_id]

top5_terms = get_top_terms(tf_matrix, vocabulary, stop_words_ids, k=5)

In [9]:
def print_clusters(clusters, doc_id_to_path, top_terms = None):
    clusters = np.array(clusters)
    num_clusters = np.unique(clusters).shape[0]
    for c in range(num_clusters):
        print c, "cluster"
        doc_ids = np.where(clusters == c)[0]
        for doc_id in doc_ids:
            doc_path = doc_id_to_path[doc_id]
            if top_terms is None:
                print doc_path[doc_path.find("-") + 1:]
            else:
                print top_terms[doc_id]            
        print

In [10]:
NUM_CLUSTERS = 10

kmeans = KMeansClusterer(NUM_CLUSTERS, distance=cosine_distance, repeats=20)
assigned_clusters = kmeans.cluster(D_lsi, assign_clusters=True)
print_clusters(assigned_clusters, doc_id_to_path)


0 cluster
revenue-optimization-against-strategic-buyers.txt
rethinking-lda-moment-matching-for-discrete-ica.txt
variational-information-maximisation-for-intrinsically-motivated-reinforcement-learning.txt
next-a-system-for-real-world-development-evaluation-and-application-of-active-learning.txt
a-structural-smoothing-framework-for-robust-graph-comparison.txt
the-pareto-regret-frontier-for-bandits.txt
variational-consensus-monte-carlo.txt
inverse-reinforcement-learning-with-locally-consistent-reward-functions.txt
bayesian-active-model-selection-with-an-application-to-automated-audiometry.txt
automatic-variational-inference-in-stan.txt
deep-visual-analogy-making.txt
statistical-topological-data-analysis-a-kernel-perspective.txt
sum-of-squares-lower-bounds-for-sparse-pca.txt
3d-object-proposals-for-accurate-object-class-detection.txt
a-universal-primal-dual-convex-optimization-framework.txt
preconditioned-spectral-descent-for-deep-learning.txt
when-are-kalman-filter-restless-bandits-indexable.txt
a-dual-augmented-block-minimization-framework-for-learning-with-limited-memory.txt
winner-take-all-autoencoders.txt
gap-safe-screening-rules-for-sparse-multi-task-and-multi-class-models.txt
rapidly-mixing-gibbs-sampling-for-a-class-of-factor-graphs-using-hierarchy-width.txt
backpropagation-for-energy-efficient-neuromorphic-computing.txt
visalogy-answering-visual-analogy-questions.txt
collaborative-filtering-with-graph-information-consistency-and-scalable-methods.txt
fast-and-guaranteed-tensor-decomposition-via-sketching.txt
probabilistic-variational-bounds-for-graphical-models.txt
unsupervised-learning-by-program-synthesis.txt
sample-complexity-of-episodic-fixed-horizon-reinforcement-learning.txt
adaptive-low-complexity-sequential-inference-for-dirichlet-process-mixture-models.txt
precision-recall-gain-curves-pr-analysis-done-right.txt
kullback-leibler-proximal-variational-inference.txt
variance-reduced-stochastic-gradient-descent-with-neighbors.txt
learning-theory-and-algorithms-for-forecasting-non-stationary-time-series.txt
weighted-theta-functions-and-embeddings-with-applications-to-max-cut-clustering-and-summarization.txt
distributed-submodular-cover-succinctly-summarizing-massive-data.txt
m-best-diverse-labelings-for-submodular-energies-and-beyond.txt
anytime-influence-bounds-and-the-explosive-behavior-of-continuous-time-diffusion-networks.txt

1 cluster
pointer-networks.txt
m-statistic-for-kernel-change-point-detection.txt
a-gaussian-process-model-of-quasar-spectral-energy-distributions.txt
tractable-learning-for-complex-probability-queries.txt
local-causal-discovery-of-direct-causes-and-effects.txt
evaluating-the-statistical-significance-of-biclusters.txt
deep-learning-with-elastic-averaging-sgd.txt
principal-differences-analysis-interpretable-characterization-of-differences-between-distributions.txt
fast-classification-rates-for-high-dimensional-gaussian-generative-models.txt
adversarial-prediction-games-for-multivariate-losses.txt
segregated-graphs-and-marginals-of-chain-graph-models.txt
quartz-randomized-dual-coordinate-ascent-with-arbitrary-sampling.txt
parallel-correlation-clustering-on-big-graphs.txt
decomposition-bounds-for-marginal-map.txt
policy-gradient-for-coherent-risk-measures.txt
space-time-local-embeddings.txt
semi-supervised-learning-with-ladder-networks.txt
associative-memory-via-a-sparse-recovery-model.txt
recursive-training-of-2d-3d-convolutional-networks-for-neuronal-boundary-prediction.txt
asynchronous-stochastic-convex-optimization-the-noise-is-in-the-noise-and-sgd-dont-care.txt
adaptive-primal-dual-splitting-methods-for-statistical-learning-and-image-processing.txt
learnability-of-influence-in-networks.txt
generative-image-modeling-using-spatial-lstms.txt
mixed-robustaverage-submodular-partitioning-fast-algorithms-guarantees-and-applications.txt
hessian-free-optimization-for-learning-deep-multidimensional-recurrent-neural-networks.txt
accelerated-mirror-descent-in-continuous-and-discrete-time.txt
convolutional-networks-on-graphs-for-learning-molecular-fingerprints.txt
embedding-inference-for-structured-multilabel-prediction.txt
max-margin-majority-voting-for-learning-from-crowds.txt
compressive-spectral-embedding-sidestepping-the-svd.txt
spatial-transformer-networks.txt
binaryconnect-training-deep-neural-networks-with-binary-weights-during-propagations.txt
local-smoothness-in-variance-reduced-optimization.txt
fast-bidirectional-probability-estimation-in-markov-models.txt
deep-generative-image-models-using-a-laplacian-pyramid-of-adversarial-networks.txt
fast-two-sample-testing-with-analytic-representations-of-probability-measures.txt
online-learning-for-adversaries-with-memory-price-of-past-mistakes.txt
algorithmic-stability-and-uniform-generalization.txt

2 cluster
lifelong-learning-with-non-iid-tasks.txt
minimax-time-series-prediction.txt
a-theory-of-decision-making-under-dynamic-context.txt
efficient-thompson-sampling-for-online-matrix-factorization-recommendation.txt
faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks.txt
a-recurrent-latent-variable-model-for-sequential-data.txt
communication-complexity-of-distributed-convex-learning-and-optimization.txt
the-consistency-of-common-neighbors-for-link-prediction-in-stochastic-blockmodels.txt
fast-distributed-k-center-clustering-with-outliers-on-massive-data.txt
asynchronous-parallel-stochastic-gradient-for-nonconvex-optimization.txt
discrete-renyi-classifiers.txt
robust-feature-sample-linear-discriminant-analysis-for-brain-disorders-diagnosis.txt
linear-response-methods-for-accurate-covariance-estimates-from-mean-field-variational-bayes.txt
spectral-learning-of-large-structured-hmms-for-comparative-epigenomics.txt
online-f-measure-optimization.txt
learning-from-small-samples-an-analysis-of-simple-decision-heuristics.txt
fixed-length-poisson-mrf-adding-dependencies-to-the-multinomial.txt
deeply-learning-the-messages-in-message-passing-inference.txt
efficient-output-kernel-learning-for-multiple-tasks.txt
training-very-deep-networks.txt
learning-visual-biases-from-human-imagination.txt
high-dimensional-em-algorithm-statistical-optimization-and-asymptotic-normality.txt
gradient-free-hamiltonian-monte-carlo-with-efficient-kernel-exponential-families.txt
tree-guided-mcmc-inference-for-normalized-random-measure-mixture-models.txt
monotone-k-submodular-function-maximization-with-size-constraints.txt
sgd-algorithms-based-on-incomplete-u-statistics-large-scale-minimization-of-empirical-risk.txt
biologically-inspired-dynamic-textures-for-probing-motion-perception.txt
unified-view-of-matrix-completion-under-general-structural-constraints.txt
testing-closeness-with-unequal-sized-samples.txt
character-level-convolutional-networks-for-text-classification.txt
end-to-end-memory-networks.txt
on-the-consistency-theory-of-high-dimensional-variable-screening.txt
a-market-framework-for-eliciting-private-data.txt
submodboxes-near-optimal-search-for-a-set-of-diverse-object-proposals.txt
is-approval-voting-optimal-given-approval-votes.txt
bounding-the-cost-of-search-based-lifted-inference.txt
saliency-scale-and-information-towards-a-unifying-theory.txt
fast-and-accurate-inference-of-plackettluce-models.txt
principal-geodesic-analysis-for-probability-measures-under-the-optimal-transport-metric.txt
on-the-job-learning-with-bayesian-decision-theory.txt
rectified-factor-networks.txt
backshift-learning-causal-cyclic-graphs-from-unknown-shift-interventions.txt
spectral-representations-for-convolutional-neural-networks.txt
estimating-jaccard-index-with-missing-observations-a-matrix-calibration-approach.txt
decoupled-deep-neural-network-for-semi-supervised-semantic-segmentation.txt
structured-estimation-with-atomic-norms-general-bounds-and-applications.txt
tensorizing-neural-networks.txt

3 cluster
local-expectation-gradients-for-black-box-variational-inference.txt
supervised-learning-for-dynamical-system-learning.txt
lasso-with-non-linear-measurements-is-equivalent-to-one-with-linear-measurements.txt
column-selection-via-adaptive-sampling.txt
streaming-min-max-hypergraph-partitioning.txt
bayesian-manifold-learning-the-locally-linear-latent-variable-model-ll-lvm.txt
efficient-and-robust-automated-machine-learning.txt
multi-layer-feature-reduction-for-tree-structured-group-lasso-via-hierarchical-projection.txt
linear-multi-resource-allocation-with-semi-bandit-feedback.txt
a-convergent-gradient-descent-algorithm-for-rank-minimization-and-semidefinite-programming-from-random-linear-measurements.txt
probabilistic-line-searches-for-stochastic-optimization.txt
gp-kernels-for-cross-spectrum-analysis.txt
subset-selection-by-pareto-optimization.txt
gaussian-process-random-fields.txt
high-dimensional-neural-spike-train-analysis-with-generalized-count-linear-dynamical-systems.txt
bayesian-dark-knowledge.txt
a-tractable-approximation-to-optimal-point-process-filtering-application-to-neural-encoding.txt
regret-lower-bound-and-optimal-algorithm-in-finite-stochastic-partial-monitoring.txt
practical-and-optimal-lsh-for-angular-distance.txt
bandits-with-unobserved-confounders-a-causal-approach.txt
convolutional-lstm-network-a-machine-learning-approach-for-precipitation-nowcasting.txt
online-rank-elicitation-for-plackett-luce-a-dueling-bandits-approach.txt
convolutional-neural-networks-with-intra-layer-recurrent-connections-for-scene-labeling.txt
skip-thought-vectors.txt
the-self-normalized-estimator-for-counterfactual-learning.txt
spectral-norm-regularization-of-orthonormal-representations-for-graph-transduction.txt
variational-dropout-and-the-local-reparameterization-trick.txt
matrix-manifold-optimization-for-gaussian-mixtures.txt
matrix-completion-from-fewer-entries-spectral-detectability-and-rank-estimation.txt
efficient-compressive-phase-retrieval-with-constrained-sensing-vectors.txt
discriminative-robust-transformation-learning.txt
double-or-nothing-multiplicative-incentive-mechanisms-for-crowdsourcing.txt
parallel-predictive-entropy-search-for-batch-global-optimization-of-expensive-objective-functions.txt
secure-multi-party-differential-privacy.txt

4 cluster
learning-structured-densities-via-infinite-dimensional-exponential-families.txt
the-brain-uses-reliability-of-stimulus-information-when-making-perceptual-decisions.txt
information-theoretic-lower-bounds-for-convex-optimization-with-erroneous-oracles.txt
planar-ultrametrics-for-image-segmentation.txt
learning-with-group-invariant-features-a-kernel-perspective.txt
mixing-time-estimation-in-reversible-markov-chains-from-a-single-sample-path.txt
reflection-refraction-and-hamiltonian-monte-carlo.txt
covariance-controlled-adaptive-langevin-thermostat-for-large-scale-bayesian-sampling.txt
maximum-likelihood-learning-with-arbitrary-treewidth-via-fast-mixing-parameter-sets.txt
on-top-k-selection-in-multi-armed-bandits-and-hidden-bipartite-graphs.txt
deep-temporal-sigmoid-belief-networks-for-sequence-modeling.txt
collaboratively-learning-preferences-from-ordinal-data.txt
model-based-relative-entropy-stochastic-search.txt
convergence-rates-of-sub-sampled-newton-methods.txt
beyond-convexity-stochastic-quasi-convex-optimization.txt
combinatorial-cascading-bandits.txt
mcmc-for-variationally-sparse-gaussian-processes.txt
learning-wake-sleep-recurrent-attention-models.txt
on-the-global-linear-convergence-of-frank-wolfe-optimization-variants.txt
robust-pca-with-compressed-data.txt
online-learning-with-gaussian-payoffs-and-side-observations.txt
super-resolution-off-the-grid.txt
large-scale-probabilistic-predictors-with-and-without-guarantees-of-validity.txt
parallel-recursive-best-first-andor-search-for-exact-map-inference-in-graphical-models.txt
basis-refinement-strategies-for-linear-value-function-approximation-in-mdps.txt
subspace-clustering-with-irrelevant-features-via-robust-dantzig-selector.txt
robust-gaussian-graphical-modeling-with-the-trimmed-graphical-lasso.txt
interpolating-convex-and-non-convex-tensor-decompositions-via-the-subspace-norm.txt
learning-with-relaxed-supervision.txt
sparse-local-embeddings-for-extreme-multi-label-classification.txt
frank-wolfe-bayesian-quadrature-probabilistic-integration-with-theoretical-guarantees.txt
deep-knowledge-tracing.txt
stochastic-online-greedy-learning-with-semi-bandit-feedbacks.txt
learning-to-segment-object-candidates.txt
online-prediction-at-the-limit-of-zero-temperature.txt
parallel-multi-dimensional-lstm-with-application-to-fast-biomedical-volumetric-image-segmentation.txt
the-return-of-the-gating-network-combining-generative-models-and-discriminative-training-in-natural-image-priors.txt
empirical-localization-of-homogeneous-divergences-on-discrete-sample-spaces.txt
path-sgd-path-normalized-optimization-in-deep-neural-networks.txt
learning-large-scale-poisson-dag-models-based-on-overdispersion-scoring.txt
a-reduced-dimension-fmri-shared-response-model.txt
the-population-posterior-and-bayesian-modeling-on-streams.txt
orthogonal-nmf-through-subspace-exploration.txt
differentially-private-subspace-clustering.txt
fast-second-order-stochastic-backpropagation-for-variational-inference.txt
an-active-learning-framework-using-sparse-graph-codes-for-sparse-polynomials-and-graph-sketching.txt

5 cluster
shepard-convolutional-neural-networks.txt
taming-the-wild-a-unified-analysis-of-hogwild-style-algorithms.txt
lifted-symmetry-detection-and-breaking-for-map-inference.txt
lifted-inference-rules-with-constraints.txt
a-class-of-network-models-recoverable-by-spectral-clustering.txt
training-restricted-boltzmann-machine-via-the-thouless-anderson-palmer-free-energy.txt
the-human-kernel.txt
on-the-pseudo-dimension-of-nearly-optimal-auctions.txt
barrier-frank-wolfe-for-marginal-inference.txt
combinatorial-bandits-revisited.txt
scale-up-nonlinear-component-analysis-with-doubly-stochastic-gradients.txt
softstar-heuristic-guided-probabilistic-inference.txt
inference-for-determinantal-point-processes-without-spectral-knowledge.txt
time-sensitive-recommendation-from-recurrent-user-activities.txt
regressive-virtual-metric-learning.txt
sparse-linear-programming-via-primal-and-dual-augmented-coordinate-descent.txt
natural-neural-networks.txt
optimal-ridge-detection-using-coverage-risk.txt
efficient-non-greedy-optimization-of-decision-trees.txt
generalization-in-adaptive-data-analysis-and-holdout-reuse.txt
statistical-model-criticism-using-kernel-two-sample-tests.txt
attention-based-models-for-speech-recognition.txt
coevolve-a-joint-point-process-model-for-information-diffusion-and-network-co-evolution.txt
a-nonconvex-optimization-framework-for-low-rank-matrix-estimation.txt
honor-hybrid-optimization-for-non-convex-regularized-problems.txt
expectation-particle-belief-propagation.txt
cornering-stationary-and-restless-mixing-bandits-with-remix-ucb.txt
efficient-learning-by-directed-acyclic-graph-for-resource-constrained-prediction.txt
accelerated-proximal-gradient-methods-for-nonconvex-programming.txt
scheduled-sampling-for-sequence-prediction-with-recurrent-neural-networks.txt
semi-supervised-convolutional-neural-networks-for-text-categorization-via-region-embedding.txt
structured-transforms-for-small-footprint-deep-learning.txt
smooth-interactive-submodular-set-cover.txt
a-universal-catalyst-for-first-order-optimization.txt
interactive-control-of-diverse-complex-characters-with-neural-networks.txt
minimum-weight-perfect-matching-via-blossom-belief-propagation.txt
probabilistic-curve-learning-coulomb-repulsion-and-the-electrostatic-gaussian-process.txt
learning-with-a-wasserstein-loss.txt
adaptive-online-learning.txt
learning-with-symmetric-label-noise-the-importance-of-being-unhinged.txt
no-regret-learning-in-bayesian-games.txt
infinite-factorial-dynamical-model.txt
on-the-accuracy-of-self-normalized-log-linear-models.txt

6 cluster
regularization-free-estimation-in-trace-regression-with-symmetric-positive-semidefinite-matrices.txt
fast-and-memory-optimal-low-rank-matrix-approximation.txt
galileo-perceiving-physical-object-properties-by-integrating-a-physics-engine-with-deep-learning.txt
efficient-learning-of-continuous-time-hidden-markov-models-for-disease-progression.txt
nonparametric-von-mises-estimators-for-entropies-divergences-and-mutual-informations.txt
sampling-from-probabilistic-submodular-models.txt
large-scale-bayesian-multi-label-learning-via-topic-based-label-embeddings.txt
top-k-multiclass-svm.txt
action-conditional-video-prediction-using-deep-networks-in-atari-games.txt
the-poisson-gamma-belief-network.txt
risk-sensitive-and-robust-decision-making-a-cvar-optimization-approach.txt
robust-spectral-inference-for-joint-stochastic-matrix-factorization.txt
regret-based-pruning-in-extensive-form-games.txt
gradient-estimation-using-stochastic-computation-graphs.txt
competitive-distribution-estimation-why-is-good-turing-good.txt
learning-with-incremental-iterative-regularization.txt
submodular-hamming-metrics.txt
learning-causal-graphs-with-small-interventions.txt
parallelizing-mcmc-with-random-partition-trees.txt
rate-agnostic-causal-structure-learning.txt
alternating-minimization-for-regression-problems-with-vector-valued-outputs.txt
regularized-em-algorithms-a-unified-framework-and-statistical-guarantees.txt
a-fast-universal-algorithm-to-learn-parametric-nonlinear-embeddings.txt
latent-bayesian-melding-for-integrating-individual-and-population-models.txt
online-gradient-boosting.txt
solving-random-quadratic-systems-of-equations-is-nearly-as-easy-as-solving-linear-systems.txt
sample-efficient-path-integral-control-under-uncertainty.txt
adaptive-stochastic-optimization-from-sets-to-paths.txt
active-learning-from-weak-and-strong-labelers.txt
convolutional-spike-triggered-covariance-analysis-for-neural-subunit-models.txt
a-bayesian-framework-for-modeling-confidence-in-perceptual-decision-making.txt
convergence-analysis-of-prediction-markets-via-randomized-subspace-descent.txt
community-detection-via-measure-space-embedding.txt
spherical-random-features-for-polynomial-kernels.txt
b-bit-marginal-regression.txt
hidden-technical-debt-in-machine-learning-systems.txt
recovering-communities-in-the-general-stochastic-block-model-without-knowing-the-parameters.txt
copeland-dueling-bandits.txt

7 cluster
matrix-completion-under-monotonic-single-index-models.txt
explore-no-more-improved-high-probability-regret-bounds-for-non-stochastic-bandits.txt
a-complete-recipe-for-stochastic-gradient-mcmc.txt
fast-randomized-kernel-ridge-regression-with-statistical-guarantees.txt
matrix-completion-with-noisy-side-information.txt
bidirectional-recurrent-neural-networks-as-generative-models.txt
market-scoring-rules-act-as-opinion-pools-for-risk-averse-agents.txt
particle-gibbs-for-infinite-hidden-markov-models.txt
optimization-monte-carlo-efficient-and-embarrassingly-parallel-likelihood-free-inference.txt
expressing-an-image-stream-with-a-sequence-of-natural-sentences.txt
halting-in-random-walk-kernels.txt
estimating-mixture-models-via-mixtures-of-polynomials.txt
learning-spatiotemporal-trajectories-from-manifold-valued-longitudinal-data.txt
individual-planning-in-infinite-horizon-multiagent-settings-inference-structure-and-scalability.txt
texture-synthesis-using-convolutional-neural-networks.txt
semi-supervised-factored-logistic-regression-for-high-dimensional-neuroimaging-data.txt
color-constancy-by-learning-to-predict-chromaticity-from-luminance.txt
learning-to-transduce-with-unbounded-memory.txt
fighting-bandits-with-a-new-kind-of-smoothness.txt
scalable-adaptation-of-state-complexity-for-nonparametric-hidden-markov-models.txt
grammar-as-a-foreign-language.txt
learning-structured-output-representation-using-deep-conditional-generative-models.txt
a-normative-theory-of-adaptive-dimensionality-reduction-in-neural-networks.txt
newton-stein-method-a-second-order-method-for-glms-via-steins-lemma.txt
multi-class-svms-from-tighter-data-dependent-generalization-bounds-to-novel-algorithms.txt
tractable-bayesian-network-structure-learning-with-bounded-vertex-cover-number.txt
semi-supervised-sequence-learning.txt
where-are-they-looking.txt

8 cluster
synaptic-sampling-a-bayesian-approach-to-neural-network-plasticity-and-rewiring.txt
calibrated-structured-prediction.txt
a-hybrid-sampler-for-poisson-kingman-mixture-models.txt
bidirectional-recurrent-convolutional-networks-for-multi-frame-super-resolution.txt
a-framework-for-individualizing-predictions-of-disease-trajectories-by-exploiting-multi-resolution-structure.txt
analysis-of-robust-pca-via-local-incoherence.txt
distributionally-robust-logistic-regression.txt
are-you-talking-to-a-machine-dataset-and-methods-for-multilingual-image-question.txt
extending-gossip-algorithms-to-distributed-estimation-of-u-statistics.txt
learning-to-linearize-under-uncertainty.txt
unlocking-neural-population-non-stationarities-using-hierarchical-dynamics-models.txt
efficient-and-parsimonious-agnostic-active-learning.txt
sample-complexity-of-learning-mahalanobis-distance-metrics.txt
measuring-sample-quality-with-steins-method.txt
robust-portfolio-optimization.txt
human-memory-search-as-initial-visit-emitting-random-walk.txt
learning-both-weights-and-connections-for-efficient-neural-network.txt
bayesian-optimization-with-exponential-convergence.txt
max-margin-deep-generative-models.txt
efficient-exact-gradient-update-for-training-deep-networks-with-very-large-sparse-targets.txt
semi-proximal-mirror-prox-for-nonsmooth-composite-minimization.txt
weakly-supervised-disentangling-with-recurrent-transformations-for-3d-view-synthesis.txt
optimal-linear-estimation-under-unknown-nonlinear-transform.txt
differentially-private-learning-of-structured-discrete-distributions.txt
deep-convolutional-inverse-graphics-network.txt
algorithms-with-logarithmic-or-sublinear-regret-for-constrained-contextual-bandits.txt
from-random-walks-to-distances-on-unweighted-graphs.txt
robust-regression-via-hard-thresholding.txt
regularization-path-of-cross-validation-error-lower-bounds.txt
beyond-sub-gaussian-measurements-high-dimensional-structured-estimation-with-sub-exponential-designs.txt
data-generation-as-sequential-decision-making.txt
sample-complexity-bounds-for-iterative-stochastic-policy-optimization.txt
on-the-limitation-of-spectral-methods-from-the-gaussian-hidden-clique-problem-to-rank-one-perturbations-of-gaussian-tensors.txt
enforcing-balance-allows-local-supervised-learning-in-spiking-recurrent-networks.txt
optimal-rates-for-random-fourier-features.txt
a-pseudo-euclidean-iteration-for-optimal-recovery-in-noisy-ica.txt
exploring-models-and-data-for-image-question-answering.txt
scalable-semi-supervised-aggregation-of-classifiers.txt
logarithmic-time-online-multiclass-prediction.txt
closed-form-estimators-for-high-dimensional-generalized-linear-models.txt
on-some-provably-correct-cases-of-variational-inference-for-topic-models.txt
on-variance-reduction-in-stochastic-gradient-descent-and-its-asynchronous-variants.txt
randomized-block-krylov-methods-for-stronger-and-faster-approximate-singular-value-decomposition.txt
sparse-and-low-rank-tensor-decomposition.txt
predtron-a-family-of-online-algorithms-for-general-prediction-problems.txt
subsampled-power-iteration-a-unified-algorithm-for-block-models-and-planted-csps.txt
black-box-optimization-of-noisy-functions-with-unknown-smoothness.txt
stopwasting-my-gradients-practical-svrg.txt

9 cluster
improved-iteration-complexity-bounds-of-cyclic-block-coordinate-descent-for-convex-problems.txt
end-to-end-learning-of-lda-by-mirror-descent-back-propagation-over-a-deep-architecture.txt
convergence-rates-of-active-learning-for-maximum-likelihood-estimation.txt
fast-rates-for-exp-concave-empirical-risk-minimization.txt
recognizing-retinal-ganglion-cells-in-the-dark.txt
scalable-inference-for-gaussian-process-models-with-black-box-likelihoods.txt
approximating-sparse-pca-from-incomplete-data.txt
bandit-smooth-convex-optimization-improving-the-bias-variance-tradeoff.txt
nearly-optimal-private-lasso.txt
attractor-network-dynamics-enable-preplay-and-rapid-path-planning-in-mazelike-environments.txt
deep-poisson-factor-modeling.txt
online-learning-with-adversarial-delays.txt
on-elicitation-complexity.txt
inferring-algorithmic-patterns-with-stack-augmented-recurrent-nets.txt
equilibrated-adaptive-learning-rates-for-non-convex-optimization.txt
consistent-multilabel-classification.txt
cross-domain-matching-for-bag-of-words-data-via-kernel-embeddings-of-latent-distributions.txt
copula-variational-inference.txt
embed-to-control-a-locally-linear-latent-dynamics-model-for-control-from-raw-images.txt
on-the-optimality-of-classifier-chain-for-multi-label-classification.txt
neural-adaptive-sequential-monte-carlo.txt
smooth-and-strong-map-inference-with-linear-convergence.txt
non-convex-statistical-optimization-for-sparse-tensor-graphical-model.txt
less-is-more-nystrom-computational-regularization.txt
learning-bayesian-networks-with-thousands-of-variables.txt
mind-the-gap-a-generative-approach-to-interpretable-feature-selection-and-extraction.txt
a-generalization-of-submodular-cover-via-the-diminishing-return-property-on-the-integer-lattice.txt
bounding-errors-of-expectation-propagation.txt
dependent-multinomial-models-made-easy-stick-breaking-with-the-polya-gamma-augmentation.txt
streaming-distributed-variational-inference-for-bayesian-nonparametrics.txt
stochastic-expectation-propagation.txt
on-the-convergence-of-stochastic-gradient-mcmc-algorithms-with-high-order-integrators.txt
finite-time-analysis-of-projected-langevin-monte-carlo.txt
teaching-machines-to-read-and-comprehend.txt
private-graphon-estimation-for-sparse-graphs.txt
learning-continuous-control-policies-by-stochastic-value-gradients.txt
policy-evaluation-using-the-return.txt
exactness-of-approximate-map-inference-in-continuous-mrfs.txt
optimal-testing-for-properties-of-distributions.txt
fast-convergence-of-regularized-learning-in-games.txt
fast-lifted-map-inference-via-partitioning.txt
fast-provable-algorithms-for-isotonic-regression-in-all-l_p-norms.txt
sparse-pca-via-bipartite-matchings.txt
learning-stationary-time-series-using-gaussian-processes-with-nonparametric-kernels.txt