New method uses sparse deep neural networks for high-dimensional regression with improved parameter estimation.
problem Improving parameter estimation in high-dimensional sparse regression models.
method Proposes nonparametric estimation of partial derivatives in sparse deep neural networks.
result Established convergence rate of nonparametric estimation of partial derivatives as O(n−1/4). Sparse-penalized deep neural networks improve performance in weakly dependent processes.
problem Nonparametric regression and classification under weak dependence.
method Sparse-penalized deep neural networks with oracle inequalities and convergence rates established.
result The proposed estimators outperform non-penalized ones in simulations.
New framework tackles deep learning issues like local traps and miscalibration.
problem Local traps and miscalibration in deep neural networks.
method Sparse deep learning framework with prior annealing algorithms.
result Proposed method successfully addresses local traps and miscalibration.
Sparse linear models improve neural network debuggability.
problem Improving neural network interpretability and debugging.
method Using sparse linear models over learned deep feature representations.
result The approach leads to more debuggable and accurate neural networks.
New method finds sparse networks without labels, improving performance.
problem Sparse connectivity in neural networks to reduce memory and energy demands.
method Neural Tangent Transfer method to find sparse networks without labels.
result Sparse networks achieve higher classification performance and faster convergence.
Sparse Meta Networks adapt deep neural networks incrementally for fast learning.
problem Training deep neural networks is slow and impractical for complex, changing environments.
method Sparse Meta Networks use a memory layer to learn online sequential adaptation, accumulating fast-weights incrementally.
result Sparse Meta Networks achieve strong performance in various sequential adaptation scenarios.
Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods exist for pruning connections of a neural network after it was trained without conne…
USN improves neural networks with uniform sparse connectivity.
problem Overfitting and limited scalability in classical neural networks.
method Uniform sparse network (USN) with even and sparse connectivity.
result USN outperforms state-of-the-art sparse network models in accuracy, speed, and robustness.
Paper develops efficient variational inference for sparse deep learning with theoretical guarantees.
problem Sparse deep learning's challenge of huge storage consumption and sparse structure recovery.
method Bayesian treatment with spike-and-slab priors and continuous relaxation of Bernoulli distribution for computationally efficient variational inferences.
result Provides variational posterior contraction rate, justifying consistency of the proposed method.
New framework explains deep learning using signal processing techniques.
problem Lack of a rigorous mathematical theory explaining deep learning performance.
method Transform-domain sparse regularization, Radon transform, and approximation theory.
result Explains neural network properties and performance.
Deep networks are shown to be equivalent to a new type of kernel chain.
problem Identifying an appropriate function space for deep neural networks.
method Extending Reproducing Kernel Banach Spaces (RKBS) to chain RKBS (cRKBS), which composes kernels rather than functions.
result Any deep neural network function is a neural cRKBS function, and conversely, any neural cRKBS function corresponds to a deep neural network.
The paper provides statistical guarantees for sparse deep learning.
problem Understanding the potential and limitations of sparse deep learning.
method Develops statistical guarantees for different types of sparsity in sparse deep learning.
result Statistical guarantees for sparse deep learning with mild dependence on network widths and depths.
Proposes a method to learn sparse deep neural networks with theoretical guarantees.
problem Over-parameterized deep neural networks cause training, prediction, and interpretation difficulties.
method Frequentist-like method for sparse DNNs under Bayesian framework.
result Consistent sparse DNNs with at most O(n/log(n)) connections. Paper proposes a new method to optimize deep neural networks with sparse regularization.
problem Difficulty in achieving optimal convergence rates for deep neural networks due to sparsity constraints.
method Introduces a novel penalized estimation method for sparse DNNs, resolving computational and theoretical issues.
result Establishes an oracle inequality for the excess risk of the proposed sparse-penalized DNN estimator and derives convergence rates.
A new estimator learns sparse linear models with context-dependent coefficients.
problem Sparse linear models lack flexibility compared to deep neural networks for handling feature groups.
method Contextual lasso estimator using a deep neural network with lasso regularization.
result Learned models can be sparser than standard lasso without sacrificing predictive power.
Deep networks learn sparse hierarchical features without CoD.
problem Overparameterized deep networks struggle with the curse of dimensionality.
method Norm-constrained neural networks for sparse compositional functions.
result Deep networks can learn sparse hierarchical features efficiently.
Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts. Orthogonal to pruning literature, deep neural networks are known to be susceptible to adversarial…
Paper proposes new Bayesian neural network models for efficient learning.
problem Efficient learning and model compression in deep neural networks.
method Proposes Spike-and-Slab Group Lasso (SS-GL) and Spike-and-Slab Group Horseshoe (SS-GHS) priors for structured sparsity in Bayesian neural networks.
result Establishes competitive performance in prediction accuracy, model compression, and inference latency compared to baseline models.
New defense method reduces adversarial attacks on neural networks.
problem Vulnerability of deep neural networks to adversarial attacks.
method Sparse coding frontend trained on clean images.
result Significantly attenuates adversarial attacks before reaching classifier.
Deep weight factorization improves neural network training through smooth optimization of sparse penalties.
problem Challenges in applying sparse regularization in neural networks due to non-differentiability of penalties.
method Introduces deep weight factorization, decomposing weights into multiple factors for smooth optimization of L1-penalized networks. result Deep weight factorization outperforms shallow factorization and pruning methods consistently across various architectures and datasets.
The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sparsifying DNNs before, during, and after training by pruning edges from the underlying topology. The resulting neural network is known as a …
The paper develops a deep neural network estimator for weakly dependent processes with various loss functions.
problem Learning weakly dependent processes with a broad class of loss functions.
method Sparse-penalized deep neural networks with ψ-weak dependence structure and θ∞-coefficients. result Oracle inequalities for the excess risk of the sparse-penalized deep neural networks estimators.
We consider the classical sparse regression problem of recovering a sparse signal x0 given a measurement vector y=Φx0+w. We propose a tree search algorithm driven by the deep neural network for sparse regression (TSN). TSN improves the signal reconstruction performance of the deep neural network designed for sp…
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.
Sparse deep learning improves prediction uncertainty for time series data.
problem Uncertainty quantification for dependent data like time series.
method Sparse recurrent neural networks (RNNs) for time series data.
result Sparse deep learning can consistently estimate and predict time series data with correct uncertainty quantification.
This work introduces a method to compare sparse neural network topologies using graph theory.
problem Comparing and understanding sparse neural network topologies, especially during training.
method Introducing Neural Network Sparse Topology Distance (NNSTD) to measure distances between different sparse neural networks.
result Sparse neural networks can outperform over-parameterized models without further structure optimization.
New theory for BNNs with Gaussian priors achieves optimal posterior concentration rates.
problem Lack of theoretical results for BNNs with Gaussian priors.
method New approximation theory for non-sparse DNNs with bounded parameters.
result BNNs with non-sparse general priors can achieve near-minimax optimal posterior concentration rates.
SIAN bridges simple models to neural networks by identifying necessary feature combinations.
problem The gap between simple models and powerful neural networks in performance.
method Feature interaction detection and sparse selection algorithm.
result Competitive performance across multiple tabular datasets with optimal tradeoff.
Sparse deep neural networks(DNNs) are efficient in both memory and compute when compared to dense DNNs. But due to irregularity in computation of sparse DNNs, their efficiencies are much lower than that of dense DNNs on regular parallel hardware such as TPU. This inefficiency leads to poor/no performance benefits for s…
This paper considers the growth in the length of one-dimensional trajectories as they are passed through deep ReLU neural networks, which, among other things, is one measure of the expressivity of deep networks. We generalise existing results, providing an alternative, simpler method for lower bounding expected traject…
New GPU kernels boost deep learning speed and memory efficiency.
problem Sparse deep learning matrices are not well-suited for existing sparse kernels.
method Identified favorable properties of sparse matrices from deep learning, developed high-performance GPU kernels for sparse matrix operations.
result 27% of single-precision peak performance on Nvidia V100 GPUs achieved with new kernels.
This paper extends the Gaussian process interpretation of deep networks to more varied weight distributions.
problem Understanding the impact of different weight initialization schemes on deep learning dynamics.
method Extending the Gaussian process interpretation to PSEUDO-IID weight distributions, including sparse and low-rank networks.
result PSEUDO-IID initialized networks are effectively equivalent up to variance, enabling tractable posterior distributions.
Algorithm learns latent variables for thermodynamically-consistent deep neural networks.
problem Predicting time evolution of large-scale physical systems with thermodynamic consistency.
method Sparse autoencoders and structure-preserving neural networks.
result Method conserves total energy and entropy inequality for both conservative and dissipative systems.
Post-processes deep networks with StoNet to quantify uncertainty.
problem Uncertainty quantification in predictions from large-scale deep neural networks.
method Feeds DNN output into StoNet, trains StoNet with sparse penalty, constructs prediction intervals.
result Proposed approach constructs honest confidence intervals with shorter lengths and better calibration.
A new framework compresses neural networks using sparse optimization.
problem Efficiently reducing the size of deep neural networks for practical deployment.
method Sparse optimization for model compression, tailored for stochastic learning.
result Up to 7.2 and 2.9 times FLOPs reduction with comparable accuracy.
Deep neural network with l_1-regularization achieves nearly optimal risk bounds.
problem Achieving optimal risk bounds in deep learning.
method Empirical risk minimization with l_1-regularization.
result Adaptively nearly-minimax risk bound across various function classes.
Dynamic model pruning improves performance on deep neural networks without retraining.
problem High memory and latency requirements for deep neural networks on low-end devices.
method Dynamic allocation of sparsity pattern and feedback signal to reactivate pruned weights.
result Sparse models achieve state-of-the-art performance with no additional retraining.
Improvements in the performance of deep neural networks have often come through the design of larger and more complex networks. As a result, fast memory is a significant limiting factor in our ability to improve network performance. One approach to overcoming this limit is the design of sparse neural networks, which ca…
Oracle inequality for sparse neural nets adapts to unknown structure.
problem Sparse deep neural nets in nonparametric regression.
method Gibbs posterior distribution with Metropolis-adjusted Langevin algorithms and mixture of uniform priors.
result Oracle inequality showing adaptation to unknown regularity and structure, achieving minimax-optimal rate of convergence.
NeuroFabric proposes a method to optimize sparse network training topologies.
problem Long training times in deep neural networks due to high memory and compute requirements.
method Developed a new sparse neural network initialization scheme and evaluated various topologies.
result Identified a single optimal topology that maximizes accuracy across different datasets.
Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs. Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more…
This paper shows neural networks can learn non-linear sparse parities.
problem The challenge of learning non-linear models with neural networks.
method Gradient descent on depth-two neural networks.
result Sparse parities are learnable by neural networks but not by linear methods.
The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sparsifying DNNs before, during, and after training by pruning edges from the underlying topology. The resulting neural network is known as a …
Unified analysis of neural networks for sparse signal recovery.
problem Sparse signal recovery from few linear measurements.
method Introduces a general class of neural networks with weight-sharing, analyzes their Rademacher complexity, and derives generalization bounds.
result Derives generalization bounds that depend linearly on the number of parameters and depth, applicable to various neural network types.
Improves key instance detection in MIL models by using neural network inversion with sparseness constraint.
problem Limited key instance detection performance in attention-based deep MIL models due to skewed attention scores.
method Sparse network inversion with a sparseness constraint incorporated into neural network inversion, solved by proximal gradient method.
result Significantly improved key instance detection performance while maintaining bag-level prediction performance.
Proposes a non-parametric method for deep discrete latent variable models.
problem Learning sparse discrete latent representations in deep models.
method Iterative algorithm with Beta-Bernoulli process prior and local data scaling.
result Improves sparsity and scalability of deep discrete latent variable models.
A promising paradigm for achieving highly efficient deep neural networks is the idea of evolutionary deep intelligence, which mimics biological evolution processes to progressively synthesize more efficient networks. A crucial design factor in evolutionary deep intelligence is the genetic encoding scheme used to simula…
Paper improves DOA estimation in sparse arrays using Siamese neural networks.
problem Challenges in DOA estimation with limited snapshots in sparse linear arrays.
method Introduces a Siamese neural network with a sparse augmentation layer for enhanced signal feature embedding.
result Demonstrates improved DOA estimation accuracy in sparse arrays.