SparseTrain uses dynamic sparsity in training deep neural networks on CPUs.
problem Training deep neural networks efficiently on general-purpose processors.
method Exploits dynamic zeros introduced by ReLU in feature maps and gradients.
result Significantly speeds up training on CPUs, up to 1.51x.
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.
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.
Sparsity-promoting priors have become increasingly popular over recent years due to an increased number of regression and classification applications involving a large number of predictors. In time series applications where observations are collected over time, it is often unrealistic to assume that the underlying spar…
To improve the execution speed and efficiency of neural networks in embedded systems, it is crucial to decrease the model size and computational complexity. In addition to conventional compression techniques, e.g., weight pruning and quantization, removing unimportant activations can reduce the amount of data communica…
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.
New algorithms extract Koopman invariant subspaces from large-scale data.
problem Difficulty in discerning the Koopman invariant subspace from many Koopman eigenmodes.
method Multi-task feature learning and pruning procedure to remove spurious modes.
result Effective in approximating Koopman operator for complex flows.
Model infers latent variables in sparse coding models using Langevin dynamics.
problem Sampling posterior distribution in sparse coding models.
method Langevin dynamics for inference and simultaneous learning of parameters.
result Langevin dynamics efficiently sample from 'L0 sparse' posterior distribution.
Dynamic risk factor model improves portfolio performance in high dimensions.
problem Dynamic portfolio allocation in high-dimensional financial markets.
method Time-varying sparsity on factor loadings, sequential learning of parameters and volatilities.
result Significant portfolio performance improvements and higher utility gains.
Sparsity-based approaches have been popular in many applications in image processing and imaging. Compressed sensing exploits the sparsity of images in a transform domain or dictionary to improve image recovery from undersampled measurements. In the context of inverse problems in dynamic imaging, recent research has de…
New learning algorithm mimics biological neural networks.
problem Biologically implausible backpropagation for directed neural networks.
method Introduces new neuronal dynamics and learning rule for arbitrary architectures, sparsity-inducing pruning method, and dynamical-systems characterization.
result Prunes irrelevant connections and improves learning efficiency.
The paper analyzes neural network dynamics after weights escape the origin.
problem Understanding gradient flow dynamics of neural networks after the origin.
method Analyzes gradient flow of homogeneous neural networks with locally Lipschitz gradients.
result Characterizes the first saddle point encountered after escaping the origin.
Gradient descent implicitly favors group sparsity in neural networks.
problem Understanding implicit regularization in neural networks for structured sparsity.
method Novel neural reparameterization for diagonally grouped linear networks.
result Gradient descent without explicit regularization biases towards group sparsity.
This paper investigates the role of sparsity in Reservoir Computing networks.
problem Designing efficient Recurrent Neural Networks (RNNs) with hidden recurrent layers.
method Empirical investigation of sparsity in input-reservoir connections and recurrent connections.
result Sparsity, particularly in input-reservoir connections, enhances the network's temporal memory and dimensionality.
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. Parsimonious Dynamic Mode Decomposition selects sparse modes robustly.
problem Manual tuning of sparsity parameters in traditional DMD.
method Time-delay embedding and Orthogonal Matching Pursuit.
result Autonomously determines optimally sparse subset of modes.
Develops a regression model for partially observed dynamic tensor data.
problem Characterizing the relationship between dynamic tensor data and external covariates when data is only partially observed.
method Introduces low-rank, sparsity, and fusion structures on the regression coefficient tensor, and uses a loss function projected over observed entries. Developed an efficient non-convex alternating updating algorithm.
result Derived finite-sample error bounds for the estimator.
This paper improves system identification by reducing sample complexity for high-dimensional linear dynamical systems.
problem High sample complexity for learning partially observed linear dynamical systems in high dimensions.
method Introduces an ℓ1-regularized estimation method that reduces sample complexity from linear to logarithmic with system dimension. result Markov parameters can be learned with logarithmic number of samples relative to system dimension, improving sample complexity.
The paper analyzes dynamics of momentum in high dimensions with sparse updates.
problem Theoretical analysis of momentum dynamics in high-dimensional sparse settings.
method Theoretical analysis of two models: least squares with sparse inputs and logistic regression with a rare class.
result Characterization of high-dimensional limits of momentum dynamics and phase structure.
Transformers can outperform feedforward and recurrent networks due to dynamic sparsity.
problem Understanding when and why Transformers outperform other neural network architectures.
method Analyzing a sequence-to-sequence data generating model with dynamic sparsity, proving sample complexity differences between feedforward, recurrent, and Transformers.
result Transformers can learn dynamic sparsity models with lower sample complexity than feedforward and recurrent networks.
Emerging resistive random-access memory (ReRAM) has recently been intensively investigated to accelerate the processing of deep neural networks (DNNs). Due to the in-situ computation capability, analog ReRAM crossbars yield significant throughput improvement and energy reduction compared to traditional digital methods.…
DNNs with L2 regularization reveal feature learning dynamics and sparsity.
problem Understanding feature learning in DNNs with L2 regularization. method Reformulating loss in terms of layerwise activations and covariances.
result Proving sparsity of local minima in L2-regularized DNNs. New method learns under latent group sparsity using network dynamics.
problem Sparse learning under latent group structure without prior group information.
method Heat-flow-based local network dynamics incorporating Laplacian geometry.
result Automatic interpolation between lasso and group lasso penalties.
Randomized feature models learn interaction kernels from agent paths.
problem Learning interaction kernels from noisy agent paths.
method Randomized feature algorithm and sparse regression.
result Pruned features reduce overfitting and lower simulation cost.
Dynamic tensor data are becoming prevalent in numerous applications. Existing tensor clustering methods either fail to account for the dynamic nature of the data, or are inapplicable to a general-order tensor. Also there is often a gap between statistical guarantee and computational efficiency for existing tensor clust…
The paper tackles reward-relevance in offline RL with sparse decision dynamics.
problem Offline reinforcement learning with sparse decision dynamics and estimation sparsity.
method Reward-filtered least-squares policy evaluation using thresholded lasso.
result The method provides theoretical guarantees with sample complexity dependent on sparse component size.
Understanding how housing values evolve over time is important to policy makers, consumers and real estate professionals. Existing methods for constructing housing indices are computed at a coarse spatial granularity, such as metropolitan regions, which can mask or distort price dynamics apparent in local markets, such…
LEWIS merges LLMs without training, improving performance on specific tasks.
problem Limited performance improvement of merged models on specific benchmarks.
method Guided model merging using layer-wise sparsity and task-vector pruning.
result Improved model performance by up to 11.3% on math-solving tasks.
Proposes a model for identifying edges in low-rank dynamical networks.
problem Inability of conventional methods to handle low-rank dynamical networks.
method Low rank dynamical network model with causal Wiener filtering.
result Consistent method for estimating all network edges.
Group-based sparsity models are proven instrumental in linear regression problems for recovering signals from much fewer measurements than standard compressive sensing. The main promise of these models is the recovery of "interpretable" signals through the identification of their constituent groups. In this paper, we e…
HierGP improves emulator efficiency for sparse, structured data.
problem Sparse, structured data in expensive simulations.
method Hierarchical shrinkage GP framework with cumulative shrinkage priors.
result HierGP identifies structured sparse features from limited data.
Sparse activations in neural networks are hard to exploit but lead to advantages in learning.
problem Sparse activations in neural networks are hard to exploit but lead to advantages in learning.
method Formal study of PAC learnability of MLP layers with activation sparsity.
result Classes of functions with activation sparsity lead to provable computational and statistical advantages over their non-sparse counterparts.
Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner. Such behavior can be well-captured by structured, nonparametric edge-exchangeable graphs. However, such exchangeable models necessarily ig…
Multi-cell cooperative processing with limited backhaul traffic is studied for cellular uplinks. Aiming at reduced backhaul overhead, a sparsity-regularized multi-cell receive-filter design problem is formulated. Both unstructured distributed cooperation as well as clustered cooperation, in which base station groups ar…
A nonparametric Bayesian sparse graph linear dynamical system (SGLDS) is proposed to model sequentially observed multivariate data. SGLDS uses the Bernoulli-Poisson link together with a gamma process to generate an infinite dimensional sparse random graph to model state transitions. Depending on the sparsity pattern of…
A model for POI recommendation using relation embedding.
problem Challenges in POI recommendation due to sparse user-POI matrix and varying context.
method Translation-based relation embedding using Knowledge Graph Embedding techniques, combined matrix factorization framework.
result Demonstrates effectiveness of the proposed model on real-world datasets.
Paper proposes a new dynamic pricing method with always-valid online statistical learning.
problem Designing dynamic pricing policies that adapt to online uncertainty and maintain validity.
method Regularized online statistical learning with theoretical guarantees and three major advantages.
result Proposed OORMLP pricing policy secures logarithmic regret in decision horizon.
We propose a dynamic edge exchangeable network model that can capture sparse connections observed in real temporal networks, in contrast to existing models which are dense. The model achieved superior link prediction accuracy on multiple data sets when compared to a dynamic variant of the blockmodel, and is able to ext…
A new distributed method speeds up sparse model training.
problem Efficiently training models with massive samples and high-dimensional features.
method Distributed Dynamic Safe Screening (DDSS) method for sparsity regularized models.
result Achieves linear convergence rate and eliminates almost all inactive features.
Novel regularization for Vision Transformers improves model generalization and sparsity.
problem Improving generalization and sparsity in Vision Transformers.
method Likelihood-guided variational Ising-based regularization.
result Improved generalization and sparsity in Vision Transformers.
New control theory shows neural networks can be sparsely active over time.
problem Optimizing neural networks for long-time control with sparsity constraints.
method Proving optimal controls vanish after a positive time and providing a stability estimate.
result Optimal controls for ℓ1-penalized neural ODEs are sparsely active over time. New method learns latent group structures without clustering, using heat flow dynamics.
problem Learning with latent group sparsity in machine learning problems.
method Heat flow dynamics on network structure to incorporate group structure.
result Effective performance and provable bounds on sample complexity.
Boosting as gradient descent algorithms is one popular method in machine learning. In this paper a novel Boosting-type algorithm is proposed based on restricted gradient descent with structural sparsity control whose underlying dynamics are governed by differential inclusions. In particular, we present an iterative reg…
A new method avoids overfitting in network reconstruction by using the minimum description length principle.
problem Determining the optimal model complexity in network reconstruction to prevent overfitting.
method Hierarchical Bayesian inference and weight quantization based on the minimum description length principle.
result The method yields increased accuracy in reconstructing both artificial and empirical networks.
As the availability and importance of temporal interaction data--such as email communication--increases, it becomes increasingly important to understand the underlying structure that underpins these interactions. Often these interactions form a multigraph, where we might have multiple interactions between two entities.…
Dynamic Mode Decomposition (DMD) yields a linear, approximate model of a system's dynamics that is built from data. We seek to reduce the order of this model by identifying a reduced set of modes that best fit the output. We adopt a model selection algorithm from statistics and machine learning known as Least Angle Reg…
With the rapid increase of available data for complex systems, there is great interest in the extraction of physically relevant information from massive datasets. Recently, a framework called Sparse Identification of Nonlinear Dynamics (SINDy) has been introduced to identify the governing equations of dynamical systems…
FedDST trains sparse sub-networks to improve efficiency in federated learning.
problem Efficiently train large models on resource-limited edge devices with limited network bandwidth.
method Dynamic sparse training to reduce model size and communication.
result FedDST outperforms existing methods in federated learning, especially in non-i.i.d. settings.