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.
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.
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. 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.
Although deep learning has shown great success in recent years, researchers have discovered a critical flaw where small, imperceptible changes in the input to the system can drastically change the output classification. These attacks are exploitable in nearly all of the existing deep learning classification frameworks.…
This work combines deep learning and sparse coding for CT image reconstruction.
problem Improving image quality in low-dose CT scans.
method Sparse signal representation using learned dictionaries, inspired by variational autoencoders and deep learning techniques.
result Regularization with learned dictionaries achieves competitive performance in CT reconstruction.
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.
Deep learning predicts dynamics from sparse data.
problem Predicting spatiotemporal dynamics from sparse data.
method Spatially dimension-independent deep learning framework.
result Predicts dynamics from sparse data sites.
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.
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.
We investigate the problem of factorizing a matrix into several sparse matrices and propose an algorithm for this under randomness and sparsity assumptions. This problem can be viewed as a simplification of the deep learning problem where finding a factorization corresponds to finding edges in different layers and valu…
Sparse VAE learns latent factors from high-dimensional data.
problem Unsupervised representation learning on high-dimensional data.
method Sparse VAE model that learns latent factors summarizing data associations.
result Sparse VAE can recover true model parameters with infinite data.
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.
Despite its nonconvex nature, ℓ0 sparse approximation is desirable in many theoretical and application cases. We study the ℓ0 sparse approximation problem with the tool of deep learning, by proposing Deep ℓ0 Encoders. Two typical forms, the ℓ0 regularized problem and the M-sparse problem, are …
Paper reveals hidden convexities in deep learning models using sparse signal processing.
problem Non-convex loss functions in deep learning models complicate optimization and theoretical understanding.
method Developed convex equivalences of ReLU NNs and their connections to sparse signal processing models.
result Recent research has uncovered hidden convexities in certain NN architectures, notably two-layer ReLU networks and other architectures.
We present a transductive deep learning-based formulation for the sparse representation-based classification (SRC) method. The proposed network consists of a convolutional autoencoder along with a fully-connected layer. The role of the autoencoder network is to learn robust deep features for classification. On the othe…
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.
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.
While sparse coding-based clustering methods have shown to be successful, their bottlenecks in both efficiency and scalability limit the practical usage. In recent years, deep learning has been proved to be a highly effective, efficient and scalable feature learning tool. In this paper, we propose to emulate the sparse…
BiSHop tackles tabular data challenges with sparse Hopfield layers.
problem Non-rotationally invariant data structure and feature sparsity in tabular data.
method Sequential column-wise and row-wise processing through interconnected directional learning modules with generalized sparse modern Hopfield layers.
result BiSHop surpasses current SOTA methods with significantly less hyperparameter tuning.
Bayesian approach improves uncertainty in deep learning models.
problem Uncertainty quantification in deep learning models.
method Bayesian point of view, Gaussian approximability, semi-parametric Bernstein-von Mises theorems.
result Bayesian credible regions have valid frequentist coverage, providing theoretical justification for deep learning.
sBayFDNN bridges deep learning and functional data analysis for complex, structured data.
problem Challenges in functional data analysis, especially for complex, continuously structured data.
method Sparse Bayesian functional deep neural network (sBayFDNN) that learns adaptive functional embeddings and interpretable region selection.
result First theoretical guarantees for a Bayesian deep functional model, ensuring reliability and statistical rigor.
Study analyzes feedback complexity for sparse feature retrieval in deep networks.
problem Learning sparse superposed features with feedback.
method Analysis of feedback complexity in sparse settings, including triplet comparisons.
result Establishes tight bounds and strong upper bounds for feature recovery.
Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in most deep models. Column Networks, a deep architecture, can succinctl…
Deep learning has gained great popularity due to its widespread success on many inference problems. We consider the application of deep learning to the sparse linear inverse problem encountered in compressive sensing, where one seeks to recover a sparse signal from a small number of noisy linear measurements. In this p…
Compressed sensing (CS) is a sampling theory that allows reconstruction of sparse (or compressible) signals from an incomplete number of measurements, using of a sensing mechanism implemented by an appropriate projection matrix. The CS theory is based on random Gaussian projection matrices, which satisfy recovery guara…
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 learning models reconstruct volatility surfaces from noisy data under no-arbitrage constraints.
problem Reconstructing implied volatility surfaces from sparse and noisy option quotes.
method Compared multiple neural architectures including Transformers, U-Nets, and variational autoencoders.
result Transformer and U-Net architectures achieve strong reconstruction accuracy, especially under sparse observation regimes.
Study improves theoretical understanding of Bayesian deep learning for classification tasks.
problem Theoretical gap in understanding Bayesian approaches in deep learning for classification.
method PAC-Bayes bounds techniques and Spike-and-Slab priors for sparse deep learning.
result Established non-asymptotic results for prediction error, achieving minimax optimal rates.
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.
uGLAD recovers sparse graphs from data using deep unrolled networks.
problem Sparse graph recovery from complex data.
method Optimizing deep unrolled networks to learn precision matrices.
result uGLAD outperforms existing algorithms in sparsity optimization and robustly handles missing data.
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…
New method learns sparse distributions by thresholding samples, improving performance and efficiency.
problem Sparse coding optimization in high-dimensional problems is computationally expensive and inefficient.
method Proposes a new variational sparse coding approach that learns sparse distributions by thresholding samples.
result Shows superior performance, statistical efficiency, and gradient estimation compared to other sparse distributions.
Sparse representations have been shown to be useful in deep reinforcement learning for mitigating catastrophic interference and improving the performance of agents in terms of cumulative reward. Previous results were based on a two step process were the representation was learned offline and the action-value function w…
SDAMI enhances interpretable high-dimensional regression with sparse deep learning and footprint principle.
problem Personalized models for small samples and high-dimensional features with interpretability.
method Sparse Deep Additive Model with Interactions (SDAMI) combining sparsity-driven feature selection and deep subnetworks.
result SDAMI successfully identifies pure interactions with near-zero false positive rates.
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.
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.
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.
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.
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.
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.
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…
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.
New method improves deep learning models robustness to label noise.
problem Improving deep learning models' robustness to corrupted labels.
method Sparse over-parameterization and implicit regularization.
result State-of-the-art test accuracy against label noise on various datasets.
The great success of deep learning poses urgent challenges for understanding its working mechanism and rationality. The depth, structure, and massive size of the data are recognized to be three key ingredients for deep learning. Most of the recent theoretical studies for deep learning focus on the necessity and advanta…
Proposes ℓ0-CCA for sparse CCA with improved representation learning.
problem CCA models break with too many variables, and sparsity is beneficial.
method Sparse CCA with stochastic gates and ℓ0-regularization. result Improves representation learning by gating nuisance variables.
X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using la…
A new deep learning model for tabular data improves accuracy over GBDT.
problem Improving accuracy in tabular data classification.
method Differentiable forest with sparse attention mechanism.
result The differentiable forest achieves higher accuracy than GBDT on tabular datasets.