Study on sparsity in CNNs trained with adaptive methods.
problem Understanding and optimizing sparsity in CNNs trained with adaptive methods.
method Experimental study of filter level sparsity in CNNs with BN and ReLU, using adaptive gradient descent and L2 regularization.
result Implicit sparsity can improve CNN performance and speedup without modifications.
Gradient descent on normalized networks reveals sparsity preferences.
problem Understanding the inductive bias of gradient descent on normalized neural nets.
method Analysis of gradient descent on weight-normalized smooth homogeneous neural nets, focusing on SWN and EWN.
result EWN causes weights to be updated in a way that prefers asymptotic relative sparsity.
New Bayesian method for sparse signal recovery using normal product priors.
problem Sparse signal recovery in compressive sensing.
method Developed a two-stage normal product-based hierarchical model using variational Bayesian inference.
result Demonstrated effectiveness through simulations compared to state-of-the-art algorithms.
New Bayesian model injects noise to improve neural network sparsity and acceleration.
problem Improving neural network sparsity and acceleration.
method Proposes a new Bayesian model that injects noise to neurons outputs while keeping weights unregularized, using log-normal multiplicative noise.
result Provides significant acceleration on deep neural architectures.
We find that CNNs with BN and ReLU exhibit feature sparsity through selective feature penalization.
problem Feature sparsity in CNNs trained with specific techniques.
method Empirical study and hypothesis testing on sparsification mechanisms.
result Selective feature penalization leads to feature sparsity in CNNs, comparable to explicit pruning.
Zero imputation leads to suboptimal neural network performance.
problem Suboptimal performance in neural networks due to missing data.
method Introduced Sparsity Normalization (SN) to handle missingness.
result Debiasing input-level sparsity improves neural network performance and stability.
A new filter design improves system identification accuracy.
problem Improving system identification accuracy for various system types.
method Generalized proportionate-type normalized subband adaptive filter (GPtNSAF) using least squares on subband errors with a sparsity penalty.
result GPtNSAF benefits from increasing subbands more than sparsity for quasi-sparse or dispersive systems, and both aspects are complementary for sparse systems.
PSiLON Net uses L1 weight normalization and 1-path-norm regularization for efficient learning and sparsity.
problem Efficient learning and sparsity in neural networks with limited data.
method PSiLON Net employs L1 weight normalization and 1-path-norm regularization to simplify the 1-path-norm and achieve efficient learning and near-sparse parameters. result PSiLON Net achieves reliable optimization and strong performance in the small data regime.
LNMC improves link prediction on social networks by considering log-normal degree distributions.
problem Link prediction in social networks with log-normal degree distributions.
method Log-Normal Matrix Completion (LNMC) using Alternating Direction Method of Multipliers.
result Up to 5% AUC increase over non-structured sparsity based methods.
New method computes affine normal directions efficiently for sparse polynomials.
problem Computing affine normal directions is computationally expensive in high dimensions.
method Reduces third-order tensor contraction to matrix-free formulation using log-determinant gradient.
result Scalable implementations with near-linear scaling in dimension and sparsity.
New method targets sparsity to prevent overfitting in deep nets.
problem Overfitting in deep neural networks with small datasets.
method Targeted sparsity regularization to visualize and counteract overfitting.
result Significant increase in image classification performance without overfitting.
We present sparse topical coding (STC), a non-probabilistic formulation of topic models for discovering latent representations of large collections of data. Unlike probabilistic topic models, STC relaxes the normalization constraint of admixture proportions and the constraint of defining a normalized likelihood functio…
The paper develops inference methods for high-dimensional multi-task regression with row-sparse coefficients.
problem Inference for high-dimensional multi-task regression with unknown coefficient matrix under row-sparsity.
method Proposes chi-square and normal inference methodologies using MT Lasso with de-biasing scheme and interaction matrix.
result Derives asymptotic normal and chi-square distribution results for valid confidence intervals and ellipsoids.
Two sparsity-aware NSAF algorithms improve sparse system identification with lower complexity.
problem Sparse system identification with improved performance and lower complexity.
method Gradient descent method to minimize combined cost function and l1-norm penalty on filter coefficients.
result Proposed algorithms achieve comparable performance with lower computational complexity.
Proposes MSN to improve DNN performance and speed.
problem Improving Deep Learning model regularization and performance.
method Empirical approach to study Spectral Normalization (SN) and Mean Spectral Normalization (MSN).
result MSN significantly improves DNN performance and speed.
Proposes a tail-adaptive shrinkage method for robust sparse estimation.
problem Robust Bayesian methods for high-dimensional regression under diverse sparse regimes.
method Global-local-tail (GLT) Gaussian mixture distribution with tail-adaptive shrinkage.
result GLT posterior contracts at minimax optimal rate for sparse normal mean models.
New algorithm identifies sparse dependencies in non-Gaussian data.
problem Learning sparse probabilistic graphical models in non-Gaussian settings.
method Algorithm based on transport maps and sparsity of graphs.
result Accurately estimates sparse Markov structure of non-Gaussian distributions.
Post-shifted BN prevents filter collapse in BN networks, improving model performance.
problem Filter collapse in BN networks reduces network capacity and harms model performance.
method Post-shifted BN (psBN) to prevent filter collapse by making BN parameters trainable again.
result psBN prevents filter collapse and increases model performance in various tasks.
Bayesian model improves sparsity in regression coefficients.
problem Sparsity in regression coefficients.
method Bayesian generalized fused lasso modeling using NEG distribution.
result The proposed method produces more sparse solutions than the ordinary fused lasso.
Proposes methods for constructing confidence sets in high-dimensional structured sparsity.
problem Building confidence regions for high-dimensional structured sparsity models.
method Desparsification of the estimator, structured matrix norm penalty, and asymptotic pivot construction.
result Developed methods for constructing asymptotic confidence regions in high-dimensional structured sparsity models.
A test for sparsity in Bayesian networks helps choose algorithms.
problem Selecting appropriate structure discovery algorithms for Bayesian networks.
method Developed a hypothesis test using the largest eigenvalue of the normalized inverse covariance matrix.
result The hypothesis test can determine if a BN has max in-degree greater than 1.
Enhances counterfactual explanations with more valid and informative saliency maps.
problem Lack of valid counterfactual explanations in existing models.
method Introduces a modified approach to CELS model by removing mask normalization.
result Demonstrates higher validity and more informative counterfactual explanations.
Study finds exact limits for sparse regression with fewer observations than usual.
problem Understanding sparse linear regression with sublinear sparsity.
method Adaptive interpolation method and modified AMP algorithm.
result Exact asymptotic expressions for mutual information and MMSE in sublinear sparsity.
Proposes HDBEN for heteroscedastic regression with improved sparsity and variance modeling.
problem Violation of constant error variance in high-dimensional regression.
method HDBEN framework using hierarchical Bayesian priors with ℓ1 and ℓ2 penalties. result Achieves posterior concentration, variable selection consistency, and asymptotic normality.
Develops a framework for interpretable two-level Boolean rules.
problem Improving interpretability in machine learning models.
method Optimization framework using LP relaxation, block coordinate descent, and alternating minimization.
result Provides good tradeoffs between accuracy and interpretability.
Develops a test for comparing linear models without assuming sparsity.
problem Testing equality of regression slopes in high-dimensional models.
method TIERS framework, self-normalization, ADDS estimator, plug-in approach.
result Robust test for equality of regression slopes under weak conditions.
Paper introduces structured sparsity estimators for Generalized Linear Models.
problem Estimating structured sparsity in GLMs with debiased estimators.
method Extends Stucky and van de Geer's results to GLMs with structured sparsity.
result Proves oracle inequalities for structured sparsity estimators in GLMs.
New algorithm detects tensor dependence structure alterations efficiently.
problem Detecting alterations in tensor dependence structures.
method Tensor-normal distributions, decorrelation, centralization, SERA (Sparsity-Exploited Reranking Algorithm).
result The proposed SERA algorithm controls false discovery rates effectively.
Unified framework for sparse alternatives to softmax with control over sparsity.
problem Lack of understanding and explicit control over sparsity in probability mapping functions.
method Unified framework encompassing softmax, sum-normalization, spherical softmax, and sparsemax. Two novel sparse formulations (sparsegen-lin and sparsehourglass) and convex loss functions developed.
result Improved performance in multilabel classification and seq2seq tasks like neural machine translation and abstractive summarization.
Paper tackles causal inference with partially labeled data, introducing robust methods.
problem Challenges in causal inference due to partially labeled datasets and potential bias.
method Decaying missing-at-random framework and BRSS estimator for doubly robust causal inference.
result Established asymptotic normality of BRSS estimator under decaying labeling propensity scores.
MOSAIC detects change points in dynamic networks with low-rank and sparse changes.
problem Detecting change points in dynamic networks with specific structural properties.
method Eigen-decomposition-based test with screened signals and residual-based adjustment.
result MOSAIC achieves minimax-optimal detection and testing rates.
We consider the problem of providing nonparametric confidence guarantees for undirected graphs under weak assumptions. In particular, we do not assume sparsity, incoherence or Normality. We allow the dimension D to increase with the sample size n. First, we prove lower bounds that show that if we want accurate infe…
A new method for embedding sparse high-order interactions.
problem Learning embeddings from sparse high-order interaction events.
method Hybridizing sparse hypergraph and matrix Gaussian processes.
result Strong asymptotic bounds on sparsity ratio.
A novel Bayesian method for dynamic sparsity in Gaussian dynamic linear regression.
problem Variable selection and shrinkage in time-varying regression models.
method Time-varying sparsity via Markov switching priors for coefficients' variances, extending spike-and-slab priors.
result Induces smoothness or shrinkage towards zero at each time point, leading to improved model performance.
Bayesian neural networks improve uncertainty estimates and sparsity.
problem Overfitting and lack of uncertainty estimates in neural networks.
method LBBNN with LRT and normalizing flows for more flexible variational posterior.
result Improved predictive power and more sparse networks.
Diagonal transformations preserve independence structures in non-Gaussian distributions.
problem Preserving independence structures in non-Gaussian distributions.
method Diagonal nonlinear transformations of multivariate normal variables.
result Independence structures are preserved in non-Gaussian distributions under diagonal transformations.
NMF with specific constraints is equivalent to LDA.
problem Dimensionality reduction of non-negative data.
method NMF with ℓ1 normalization constraints and Dirichlet prior. result NMF with these constraints is equivalent to LDA.
GRASP simplifies Bayesian regression with grouped predictors using an adaptive NBP prior.
problem Regression with grouped predictors and adaptive shrinkage.
method Normal Beta Prime (NBP) prior with tunable hyperparameters for flexible sparsity control.
result Empirical validation of robust and versatile GRASP across various sparsity and signal-to-noise ratios.
New method uses neural maps to efficiently sample lattice QCD distributions.
problem Challenges in sampling Boltzmann distributions of lattice field theories.
method Sparse triangular transport maps exploiting conditional independence structure of lattice graphs.
result Sparse triangular maps achieve efficient sampling with linear time complexity in lattice size.
Paper introduces ENZ to measure significant coefficients in sparse recovery, improving over classical methods.
problem Numerical noise creates long tails of negligible coefficients in sparse recovery.
method Entropy-based notion of effective sparsity (ENZ) to measure significant coefficients, proving stability under restricted isometry condition.
result ENZ decomposes into support cardinality and efficiency factor, providing a precise measure of sparsity.
Paper analyzes adaptive Lasso for high-dimensional diffusion processes, improving support recovery and bias.
problem Support recovery for high-dimensional diffusion processes under sparsity constraints.
method Adaptive Lasso estimator for d-dimensional ergodic diffusion process, focusing on linear models.
result Adaptive Lasso achieves support recovery and asymptotic normality for drift parameter under certain conditions.
A new framework uses matrix flows to unify frequentist and Bayesian approaches for sparse GGMs.
problem Challenges in studying conditional independence among many variables with few observations.
method General framework for variational inference with matrix-variate Normalizing Flow in Gaussian Graphical Models.
result Unified benefits of frequentist and Bayesian frameworks for sparse GGMs.
Consider a linear regression model where the design matrix X has n rows and p columns. We assume (a) p is much large than n, (b) the coefficient vector beta is sparse in the sense that only a small fraction of its coordinates is nonzero, and (c) the Gram matrix G = X'X is sparse in the sense that each row has relativel…
Undirected graphs can be used to describe matrix variate distributions. In this paper, we develop new methods for estimating the graphical structures and underlying parameters, namely, the row and column covariance and inverse covariance matrices from the matrix variate data. Under sparsity conditions, we show that one…
Study proposes efficient estimators for matrix-valued linear regression under sparsity assumptions.
problem Estimation of parameters in matrix-valued linear regression models.
method Explicit optimization-free estimators for matrix-valued linear regression models with sparsity assumptions.
result Established non-asymptotic convergence rates for the proposed estimators.
NARD extends ARD for linear models, promoting sparsity and correlation structure.
problem Sparse relationships between inputs and outputs, capturing correlation structure.
method Matrix normal prior with sparsity-inducing parameter, iterative updates, sequential evaluation, and surrogate function approximation.
result Significant computational efficiency improvements with comparable performance.
New algorithm improves learning in noisy networks with robust performance.
problem Improving learning in noisy, distributed networks.
method Diffusion normalized least mean M-estimate algorithm with sparse-aware variant.
result The proposed algorithms outperform existing diffusion algorithms in impulsive noise scenarios.
New layer sparsity concept improves neural networks.
problem Improving neural network efficiency and interpretability.
method Formulated layer sparsity, introduced regularization and refitting schemes.
result Generated more compact and accurate neural networks.