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.
Embeds sparsity in deep neural networks, allowing exact zero parameters.
problem Learning sparse structures in deep networks.
method Embeds sparsity into neural network structure, allowing exact zero parameters during training.
result Can learn both structured and unstructured sparsity.
The paper studies how regularization parameters affect sparsity in deep neural networks.
problem Reducing the complexity of deep neural networks by promoting sparsity.
method Derives ℓ1-norm sparsity-promoting models, characterizes sparsity levels, and develops algorithms for selecting optimal regularization parameters. result Developed algorithms to select regularization parameters for desired sparsity levels in neural networks.
Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget. Existing methods rely on uniform or heuristic non-uniform sparsity budgets which have sub-optimal layer-wise parameter allocation resulting in a) lower prediction accuracy o…
SparseRT accelerates sparse computations on GPUs for deep learning inference.
problem Efficiently handling unstructured sparsity patterns on GPUs for deep learning.
method SparseRT, a code generator that leverages unstructured sparsity for accelerating sparse linear algebra operations.
result Geometric mean speedups of 3.4x at 90% sparsity and 5.4x at 95% sparsity for 1x1 convolutions and fully connected layers.
Improves robustness of information bottleneck framework with sparsity-inducing prior.
problem Fixed-dimensional priors restrict flexibility and restrict robustness.
method Sparsity-inducing spike-slab categorical prior that learns dimension distribution per data point.
result Improves accuracy and robustness compared to traditional priors and other methods.
Paper proposes a unified sparsity-based framework for evaluating algorithmic fairness.
problem Ensuring fairness in machine learning across diverse domains.
method Unified sparsity-based framework for evaluating fairness.
result Demonstrates broad applicability and effectiveness of the framework.
A new method for fast and robust sparsity learning over networks.
problem Efficiently learning sparse models in decentralized networks.
method Decentralized surrogate median regression (deSMR) method.
result Linear convergence rate with a simple implementation.
New Bayesian method for joint sparse parameter inference.
problem Inference of jointly sparse parameter vectors from multiple measurements.
method Hierarchical Bayesian learning with joint sparsity-promoting priors.
result New algorithms consistently outperform existing methods in numerical experiments.
Paper develops a method to learn optimal sparsity-promoting regularizers for linear inverse problems.
problem Solving linear inverse problems with sparse solutions.
method Bilevel optimization framework to select an optimal synthesis operator B. result Established well-posedness and theoretical guarantees for the learning process.
HALO learns to prune neural networks by adaptively shrinking weights.
problem Sparsity and model size in deep neural networks.
method Bayesian hierarchical models and trainable parameters for adaptive sparsification.
result HALO learns to create highly sparse networks with significant performance gains.
New Max-Plus neural network exploits subgradient sparsity for efficient training.
problem Training Max-Plus neural networks is challenging due to dense subgradients.
method Proposes a sparse subgradient algorithm tailored to Max-Plus models.
result Achieves more efficient updates while retaining theoretical guarantees.
Structured sparsity has recently emerged in statistics, machine learning and signal processing as a promising paradigm for learning in high-dimensional settings. All existing methods for learning under the assumption of structured sparsity rely on prior knowledge on how to weight (or how to penalize) individual subsets…
Overfitting is one of the most common problems when training deep neural networks on comparatively small datasets. Here, we demonstrate that neural network activation sparsity is a reliable indicator for overfitting which we utilize to propose novel targeted sparsity visualization and regularization strategies. Based o…
Federated Learning with L0 constraint improves sparsity and performance.
problem Inherent sparsity in data and models leads to dense models with poor generalizability.
method L0 constraint on model density achieved through probabilistic gates and federated stochastic gradient descent.
result Achieves target sparsity (rho) in FL with minimal loss in statistical performance.
Automated PDE discovery from multiple noisy experiments.
problem Inherent variability in experiments makes single experiment inference unreliable.
method Randomised adaptive group Lasso sparsity estimator in deep learning framework.
result More generalizable PDEs found from multiple datasets.
New measure SEV shows non-sparse models can still have low decision sparsity.
problem Non-sparse models can still make accurate decisions based on a few features.
method Introduced Sparse Explanation Value (SEV) to measure decision sparsity, not overall model sparsity.
result Many non-sparse models have low decision sparsity, as measured by SEV.
Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word relationships. However, with standard softmax attention, all attention heads are de…
Proposes a sparsity algorithm to improve corporate credit ratings.
problem Improving credit ratings of publicly traded companies.
method Formulates counterfactual explanation as an optimization problem and proposes a sparsity algorithm to maximize sparsity.
result The sparsity algorithm can capture features that improve credit ratings.
New sparsity attacks degrade DNN efficiency, raising concerns for resource-constrained systems.
problem Vulnerabilities in DNNs through energy and latency attacks.
method Proposed sparsity attacks that modify DNN inputs to reduce activation sparsity, increasing execution time and energy consumption.
result Adversarial sparsity attacks can degrade DNN efficiency by up to 1.82x in image recognition DNNs.
In this paper, we consider the block-sparse signals recovery problem in the context of multiple measurement vectors (MMV) with common row sparsity patterns. We develop a new method for recovery of common row sparsity MMV signals, where a pattern-coupled hierarchical Gaussian prior model is introduced to characterize bo…
Proposes a neural network for sparsity regularization in inverse problems using Gaussian mixture.
problem Sparsity in inverse problems with limited significant components.
method Probabilistic sparsity prior as a mixture of degenerate Gaussians, trained with neural network.
result Neural network yields lower mean square error than LASSO, group LASSO, and iterative hard thresholding.
2L-FUSE enhances feature sparsity through kernel learning.
problem Sparsity and feature selection in regression tasks.
method 2-Layered kernel machines for learning a shape matrix and feature direction identification.
result Minimal yet informative feature sets are identified without losing predictive performance.
New adaptive learning rate improves FTRL's adaptivity to sparsity, game-dependency, and best-of-both-worlds.
problem Improving adaptivity in sequential decision-making problems.
method Developed a stability-penalty-adaptive (SPA) learning rate for FTRL.
result First BOBW algorithm with sparsity-dependent bound.
Paper studies sparsity and DAG constraints for learning linear DAGs.
problem Learning DAGs from data is challenging due to the large search space.
method Formulates structure learning as a constrained optimization problem with soft sparsity and DAG constraints.
result Soft sparsity and DAG constraints lead to an easier optimization problem.
AGS-CL selectively updates penalties based on node importance for continual learning.
problem Catastrophic forgetting in continual learning.
method Adaptive Group Sparsity (AGS) with proximal gradient descent.
result Significantly outperforms baselines on various continual learning benchmarks.
New method enforces encoder sparsity in HPF for more interpretable feature selection.
problem Lack of encoder sparsity in HPF leads to lack of column-clustering property.
method Enforces encoder sparsity using a generalized additive model (GAM).
result Gains ability to perform feature selection and relates each representation to original features.
Dropout is commonly used to help reduce overfitting in deep neural networks. Sparsity is a potentially important property of neural networks, but is not explicitly controlled by Dropout-based regularization. In this work, we propose Sparseout a simple and efficient variant of Dropout that can be used to control the spa…
SCOPE iteratively optimizes sparsity-constrained problems without tuning hyperparameters.
problem Optimizing sparsity-constrained problems in signal processing, statistics, and machine learning.
method SCOPE (Sparsity-Constrained Optimization via sPlicing itEration) replaces gradient steps with a splicing operation guided by the objective value.
result SCOPE achieves linear convergence and superior support recovery performance.
Deep learning is finding its way into the embedded world with applications such as autonomous driving, smart sensors and aug- mented reality. However, the computation of deep neural networks is demanding in energy, compute power and memory. Various approaches have been investigated to reduce the necessary resources, on…
New algorithm learns from sparse data without knowing sparsity index.
problem Sparse bandit problem where only a subset of features affects reward.
method Sparsity-agnostic Lasso Bandit algorithm that doesn't require prior sparsity index knowledge.
result Established tight regret bounds and outperforms existing methods.
The mushroom body is the key network for the representation of learned olfactory stimuli in Drosophila and insects. The sparse activity of Kenyon cells, the principal neurons in the mushroom body, plays a key role in the learned classification of different odours. In the specific case of the fruit fly, the sparseness o…
Compressive sensing (CS) exploits sparsity to recover sparse or compressible signals from dimensionality reducing, non-adaptive sensing mechanisms. Sparsity is also used to enhance interpretability in machine learning and statistics applications: While the ambient dimension is vast in modern data analysis problems, the…
A new method solves l1-regularized optimization problems efficiently and sparsely.
problem l1-regularized optimization problems in machine learning.
method Orthant Based Proximal Stochastic Gradient Method (OBProx-SG)
result Promotes sparsity of solutions substantially and converges to global optimal solutions.
Sparsity learning with known grouping structure has received considerable attention due to wide modern applications in high-dimensional data analysis. Although advantages of using group information have been well-studied by shrinkage-based approaches, benefits of group sparsity have not been well-documented for greedy-…
This paper reviews Bayesian methods for sparsity-aware modeling.
problem Uncertainty evaluation and robustness in sparsity-aware models.
method Incorporates sparsity-promoting priors into deep neural networks, Gaussian processes, and tensor decomposition.
result Bayesian methods improve model robustness and uncertainty evaluation.
Stochastic optimization algorithms update models with cheap per-iteration costs sequentially, which makes them amenable for large-scale data analysis. Such algorithms have been widely studied for structured sparse models where the sparsity information is very specific, e.g., convex sparsity-inducing norms or ℓ0-n…
Sparse mapping has been a key methodology in many high-dimensional scientific problems. When multiple tasks share the set of relevant features, learning them jointly in a group drastically improves the quality of relevant feature selection. However, in practice this technique is used limitedly since such grouping infor…
A new method for differentiable structured sparsity improves neural network performance and sparsity.
problem Non-differentiability of structured sparsity penalties in neural networks.
method Introducing D-Gating, a differentiable approach to structured overparameterization. result The D-Gating objective converges to the L2,2/D-regularized loss and induces sparse learning dynamics. New algorithm recovers sparse signals from linearly sparse dictionaries efficiently.
problem Recovering sparse signals from linearly sparse dictionaries.
method Spectral method on reweighted covariance matrices.
result First polynomial-time algorithm for near-linear sparsity in overcomplete dictionaries.
The paper studies sparsity in EBF with hyperpriors and proposes a PALM algorithm.
problem Promoting sparsity in sparse learning problems.
method Empirical Bayes framework, hyperpriors, proximal alternating linearized minimization (PALM) algorithm.
result Appropriate hyperpriors can significantly enhance sparsity and restoration accuracy.
We study the emergence of sparse representations in neural networks. We show that in unsupervised models with regularization, the emergence of sparsity is the result of the input data samples being distributed along highly non-linear or discontinuous manifold. We also derive a similar argument for discriminatively trai…
Many natural signals exhibit a sparse representation, whenever a suitable describing model is given. Here, a linear generative model is considered, where many sparsity-based signal processing techniques rely on such a simplified model. As this model is often unknown for many classes of the signals, we need to select su…
Dynamic pricing learns demand model from sparse product networks.
problem Minimizing revenue loss in a large network of products with unknown demand parameters.
method Combines optimism-in-the-face-of-uncertainty and PAC-Bayesian approaches.
result Achieves asymptotically optimal performance in terms of network size and time horizon.
In dictionary selection, several atoms are selected from finite candidates that successfully approximate given data points in the sparse representation. We propose a novel efficient greedy algorithm for dictionary selection. Not only does our algorithm work much faster than the known methods, but it can also handle mor…
The paper analyzes the trade-off between smoothness and sparsity in GCN using lp-regularized learning.
problem Quantifying the trade-off between smoothness and sparsity in GCN.
method Proposes a novel SGD proximal algorithm for GCNs with an inexact operator to analyze the stability of the ℓp-regularized stochastic learning. result Establishes an explicit theoretical understanding of GCN with ℓp-regularized stochastic learning. Bayesian method improves dictionary learning for complex problems.
problem Efficiently identifying relevant dictionary entries for complex inverse problems.
method Bayesian group sparsity coding and deflation steps to compress and identify relevant subdictionaries.
result Significant computational complexity reduction and improved glitch detection in LIGO experiment.
This paper accelerates sparse CNN layers on GPUs by using unstructured sparsity.
problem Efficiency of sparse CNN layers on GPUs.
method Direct sparse operation and reduced precision.
result Achieving up to 90% sparsity in deep CNN models improves efficiency.