New taxonomy and improved solvers for discrete energy minimization.
problem Maximum-a-posteriori inference in discrete graphical models.
method Dual block-coordinate ascent rule, theoretical analysis, new solver variants.
result Improved state-of-the-art solver outperforming existing methods on all test instances.
New model allows some connections to be zero, improving network analysis.
problem Networks with block structure and sparsity.
method Sparse Popularity Adjusted Stochastic Block Model (PABM).
result Allows some probabilities of connections to be zero.
ROIreg refines CNN's classification ability by focusing on pixel blocks.
problem Improving CNN's performance in semi-supervised and supervised learning.
method ROIreg divides pixel blocks, replaces them with random images, and trains CNN to maintain the maximum probability.
result ROIreg and VAT have complementary training effects, improving overall performance.
Residual flows are shown to approximate MMD well.
problem Lack of theoretical understanding of normalizing flows' expressiveness.
method Proved residual flows are universal approximators in MMD.
result Residual flows can approximate MMD with a bounded number of blocks.
The paper improves volatility estimation in high-frequency data with reduced variance.
problem Estimating volatility in high-frequency data with stochastic volatility and microstructure noise.
method Chop data into blocks, compute RK or QMLE on each block, and aggregate estimates.
result The ratio of asymptotic variance to efficiency converges to 1.0025 for the fastest RK and 1 for QMLE as block size increases.
Study the maximum genus of Jenga-like configurations.
problem Determine the maximum genus of Jenga-like structures.
method Treat Jenga blocks as a polyhedral surface and calculate its genus.
result Determine the maximum genus of generalized Jenga games.
REM improves recommender systems by integrating multi-mode tensor data.
problem Cold-start problem in recommender systems.
method Multilayer tensor factorization with a maximum block improvement strategy.
result REM outperforms existing methods in product sales predictions.
A new method for efficient inference and model selection in SBMs using OT.
problem Efficient inference and model selection in stochastic block models.
method Interpreting MLVI as srGW with entropic regularization, then unregularizing for sparse solutions, and adding a sparsity-promoting regularizer.
result The method consistently recovers SBM parameters and selects the number of clusters in finite samples.
Spectral clustering for directed graphs using likelihood estimation.
problem Clustering directed graphs with edge directions.
method Maximum likelihood estimation on stochastic block models.
result Significant performance gains over existing methods.
Stochastic block model shows universal applicability to network inference problems.
problem Finding partitions in complex networks that maximize objective functions.
method Showed equivalence of popular algorithms to maximum likelihood formulation of SBM.
result SBM is nearly universal for solving MPE problems.
Study how noisy labels affect semi-supervised learning.
problem Effect of noisy labels on semi-supervised learning performance.
method Proposed an algorithm derived from a continuous relaxation of the Maximum A Posteriori (MAP) estimator for a Degree Corrected Stochastic Block Model (DC-SBM).
result Our approach achieves promising performance even with very noisy labeled data.
Paper shows SBMs are like surface tension problems, aiding network clustering.
problem Cluster network nodes into communities with dense internal connections.
method Used maximum likelihood estimation and network analogs of surface-tension algorithms.
result Successfully recovered planted community structure in synthetic networks.
Estimates social network structure from random walk subgraphs.
problem Recovering population structure from random walk subgraphs in stochastic block models.
method Maximum likelihood estimation, SAEM algorithm, de-biasing techniques.
result New de-biased estimator provides more accurate recovery of network structure.
Model counts interactions in dynamic networks using Poisson processes and clusters.
problem Counting interactions in dynamic networks with unknown cluster structure.
method Developed a model using non-homogeneous Poisson processes and block modeling. Truncated to discrete time for tractability. Used an exact integrated classification likelihood criterion for estimation.
result Estimates cluster memberships and number of clusters simultaneously.
Simplified explanation of ML for mixtures and OT.
problem Maximum likelihood estimation for mixture models.
method Optimal transport with entropic regularization.
result EM algorithm is a block-coordinate descent on OT loss.
Residual Flows improve flow-based models for density estimation.
problem Density estimation using flow-based models with biased log-density estimates.
method Proposed a Russian roulette estimator for unbiased log-density estimation and used an alternative infinite series for gradient calculation. Improved invertible residual blocks with activation functions avoiding derivative saturation and generalized Lipschitz condition to induced mixed norms.
result Residual Flows achieve state-of-the-art performance on density estimation and outperform coupling block networks in joint generative and discriminative modeling.
We analyze the performance of spectral clustering for community extraction in stochastic block models. We show that, under mild conditions, spectral clustering applied to the adjacency matrix of the network can consistently recover hidden communities even when the order of the maximum expected degree is as small as $\l…
Graph clustering involves the task of dividing nodes into clusters, so that the edge density is higher within clusters as opposed to across clusters. A natural, classic and popular statistical setting for evaluating solutions to this problem is the stochastic block model, also referred to as the planted partition model…
Paper proposes an algorithm for robust estimation using Huber's criterion.
problem Non-convexity and non-robustness of joint maximum likelihood estimation.
method Block-wise minimization majorization framework with data-adaptive step sizes.
result Improved convergence and robustness in sparse learning.
MVTV improves interpretability in low-dimensional regression.
problem Estimating regression functions with few features and high interpretability needs.
method MVTV divides space into blocks, fits values jointly, and optimizes automatically.
result MVTV outperforms CART and CRISP in both complexity and human interpretability studies.
Efficient RNNs on FPGA using structured matrices improve energy efficiency 35.7x.
problem Irregular network structure after pruning degrades RNN performance and energy efficiency.
method Use block-circulant matrices to compress and accelerate RNNs in FPGA.
result Achieved maximum energy efficiency improvement of 35.7x compared to ESE.
New method optimizes MAP inference for structured problems.
problem Structured energy minimization problems
method Proximal bundle method with block-coordinate Frank-Wolfe
result Empirically outperforms state-of-the-art algorithms
The performance of spectral clustering can be considerably improved via regularization, as demonstrated empirically in Amini et. al (2012). Here, we provide an attempt at quantifying this improvement through theoretical analysis. Under the stochastic block model (SBM), and its extensions, previous results on spectral c…
Paper tackles joint community detection and phase synchronization in stochastic block models.
problem Jointly recover cluster structure and phase angles in stochastic block models.
method Proposes two algorithms: a spectral method based on multi-frequency QR factorization and an iterative multi-frequency generalized power method.
result Proposed algorithms significantly improve recovery of cluster structure and phase angles compared to existing methods.
New defense method inspired by encryption improves visual classification accuracy.
problem Conventional defenses reduce accuracy and are defeated by obfuscated gradients.
method Block-wise pixel shuffling with secret key for training and test images.
result Achieves high accuracy (91.55%) on clean images and (89.66%) on adversarial examples.
We examine the recovery of block sparse signals and extend the framework in two important directions; one by exploiting signals' intra-block correlation and the other by generalizing signals' block structure. We propose two families of algorithms based on the framework of block sparse Bayesian learning (BSBL). One fami…
Resolving a conjecture of Abbe, Bandeira and Hall, the authors have recently shown that the semidefinite programming (SDP) relaxation of the maximum likelihood estimator achieves the sharp threshold for exactly recovering the community structure under the binary stochastic block model of two equal-sized clusters. The s…
Large-scale L1-regularized loss minimization problems arise in high-dimensional applications such as compressed sensing and high-dimensional supervised learning, including classification and regression problems. High-performance algorithms and implementations are critical to efficiently solving these problems. Building…
We investigate the detectability of modules in large networks when the number of modules is not known in advance. We employ the minimum description length (MDL) principle which seeks to minimize the total amount of information required to describe the network, and avoid overfitting. According to this criterion, we obta…
Study information limits for community detection in sub-hypergraphs.
problem Identify limits for exact community detection in sub-hypergraphs.
method Use Fano's inequality to define model parameters and identify success and failure regions.
result Identify regions where algorithms succeed or fail in exact recovery.
New model handles complex non-linear relationships with hidden graph structures.
problem Modeling non-linear relationships with hidden graph-structured interactions.
method Block-diagonal localized mixture of polynomial experts (BLoMPE) regression model with penalized maximum likelihood selection criterion.
result Strong theoretical guarantee for finite-sample oracle inequality.
Invertible ResNets enable classification, density estimation, and generation.
problem Enforcing invertibility in ResNets without architectural changes.
method Simple normalization during training to make ResNets invertible.
result Invertible ResNets achieve competitive performance with single architecture.
Study on inferring dynamic communities and links in networks with memory.
problem Inferring communities and links in dynamic networks with memory.
method Maximum likelihood inference from single snapshot observations, analytical and numerical analysis.
result Link persistence makes community detection harder, while community persistence makes it easier.
A family of maximum mean discrepancy (MMD) kernel two-sample tests is introduced. Members of the test family are called Block-tests or B-tests, since the test statistic is an average over MMDs computed on subsets of the samples. The choice of block size allows control over the tradeoff between test power and computatio…
A new channel locality block improves CNN performance.
problem Improving the performance of convolutional neural networks.
method Proposed a variant of Squeeze-and-Excitation block using convolutional layers to learn nearby channel correlation.
result Our C-Local block achieved higher accuracy than the standard SE block on the cifar-10 dataset.
Randomized block-diagonal preconditioning improves parallel learning convergence.
problem Improving convergence of gradient-based optimization methods in parallel settings.
method Randomization of coordinates during optimization to repartition tasks.
result Randomization significantly improves convergence of block-diagonal preconditioned methods.
An algorithm finds a compact Hankel submatrix for spectral learning.
problem Efficiently computing SVD for large Hankel matrices in spectral learning.
method Maximal bipartite matching algorithm to select rows and columns of Hankel matrix.
result Compact Hankel submatrix with full structural rank.
Paper models graph edge dependencies using latent variables for community detection.
problem Graphs' edge dependencies not fully explained by community membership.
method Introduces auxiliary latent variables to model edge dependencies and analyzes conditions for exact recovery.
result Exact recovery possible by semidefinite programming down to maximum likelihood threshold.
The paper proposes a method to estimate joint probability from unpaired data using entropic transport kernels.
problem Estimating joint probability from unpaired data with unknown internal ordering.
method Maximum-likelihood inference, entropic optimal transport kernels, EMML algorithm.
result The method can recover true density from empirical approximations as the number of blocks increases.
This research explains how Batch Normalization improves neural networks through theoretical analysis.
problem Understanding the impact of Batch Normalization on neural network training and generalization.
method Using a basic neural network block, the study analyzes Batch Normalization by decomposing it into population normalization and gamma decay.
result Batch Normalization acts as an implicit regularizer, decomposable into explicit components that affect learning dynamics and generalization.
Regularization improves spectral embedding by focusing on the largest blocks.
problem Improving the quality of spectral embedding for graph data.
method Explained the impact of complete graph regularization on spectral embedding of a block model.
result Regularization forces spectral embedding to focus on the largest blocks, making it less sensitive to noise or outliers.
A new method improves Bayesian filtering in nonlinear systems.
problem Bayesian filtering in nonlinear dynamical systems with non-Gaussian posteriors.
method Transport maps with block-triangular structure and gradient flows for MMD minimization.
result Accurate approximation of non-Gaussian posteriors without particle collapse.
A new model adjusts for covariates in community detection.
problem Community detection in networks with covariate information.
method Pairwise covariates-adjusted stochastic block model (PCABM) with spectral clustering.
result Consistent community detection and coefficient estimates under sparsity conditions.
This paper studies the partial estimation of Gaussian graphical models from high-dimensional empirical observations. We derive a convex formulation for this problem using ℓ1-regularized maximum-likelihood estimation, which can be solved via a block coordinate descent algorithm. Statistical estimation performance …
Paper proposes a new method for estimating conditional densities using logistic regressions.
problem Estimating conditional densities for complex distributions.
method Parametric conditional density estimation via weighted logistic regressions.
result Maximum likelihood estimates can be obtained efficiently via a block-wise alternating maximization scheme and local case-control sampling.
Develops a multichannel deep network for faster, artifact-free image CS.
problem Block-wise sampling artifacts in image CS with multiple sampling rates.
method Multichannel deep network for block-based image CS, removing blocking artifacts.
result Significantly outperforms state-of-the-art CS methods in objective and subjective metrics.
Regularization improves logistic regression performance in high-dimensional settings.
problem Improving logistic regression in scenarios with many parameters and observations.
method Introducing a convex regularizer to the negative log-likelihood function to encourage desired structures.
result Explicit expressions for various performance metrics of regularized logistic regression are derived.
New model considers edge correlations in multilayer networks for better predictions.
problem Inferring community structure in multilayer networks with edge correlations.
method Developed a maximum-likelihood estimate for parameters and a measure of layer correlation.
result Improved prediction accuracy in multilayer networks, including a grocery shopping network.