SANs use sparse activation functions to compress data representations.
problem Learning meaningful features without considering compression.
method Introduce φ metric, define activation functions, and present SANs.
result SANs achieve small description length and interpretable kernels.
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.
Previous literature on unsupervised learning focused on designing structural priors with the aim of learning meaningful features. However, this was done without considering the description length of the learned representations which is a direct and unbiased measure of the model complexity. In this paper, first we intro…
Novel active learning framework using sparse approximation for efficient model training.
problem Efficient model training with limited labeled data.
method Formulates batch active learning as sparsity-constrained discontinuous optimization problems, using greedy or proximal iterative hard thresholding algorithms.
result Achieves competitive performance with lower computational complexity across different settings.
BatchTopK SAEs improve GPT-2 and Gemma activations with adjustable sparsity.
problem Interpreting language model activations using sparse autoencoders.
method Adapting the TopK constraint to the batch-level, allowing variable number of active latents per sample.
result BatchTopK SAEs consistently outperform TopK SAEs in reconstructing GPT-2 and Gemma activations.
REALITrees uses a Rashomon ensemble approach for active learning in sparse decision trees.
problem Active learning reduces labeling costs by selecting informative samples, but current methods often sacrifice model diversity and direct characterization of the hypothesis space.
method REALITrees constructs a committee of all near-optimal sparse decision tree models using a Rashomon Set and a Gibbs posterior to weight them by empirical risk.
result REALITrees outperforms randomized ensembles, especially in noisy environments, by leveraging expanded model multiplicity.
Paper hypothesizes MLP layers in LLMs can be approximated by sparse Mixture of Experts.
problem Understanding dense MLP layers in LLMs.
method Theoretical connection between MoE models and SAE structure in activation space.
result MLP layers in LLMs can be well approximated by sparse Mixture of Experts.
Picasso is a new library for sparse learning problems in R and Python.
problem Sparse learning problems in high-dimensional data analysis.
method Unified framework of pathwise coordinate optimization with efficient active set selection strategies.
result picasso can efficiently handle large-scale problems.
SWAT reduces training efficiency and speed for CNNs.
problem Efficient training of neural networks on sparse hardware.
method SWAT modifies backpropagation to eliminate small weights and activations.
result SWAT reduces FLOPS by 80% on ResNet-50 for ImageNet, improving training speed by 3.3x.
This research improves neural network performance with adaptive activation functions in sparse data settings.
problem Limited data availability in scientific and engineering problems.
method Investigation of two types of adaptive activation functions with individual trainable parameters.
result Adaptive activation functions, especially with individual trainable parameters, enhance prediction accuracy and confidence in sparse data settings.
New method uses temperature to control sparse MoE convergence rates.
problem Sparse MoE convergence rates are slow due to temperature interactions.
method Proposes a novel activation gate to improve convergence rates.
result Improved convergence rates to polynomial rates via novel gate.
New RL agent learns sparse rewards efficiently.
problem Sparse-reward environments and computational expense.
method Active inference with novel free energy minimization.
result High sample efficiency and online operation.
Study confirms sparse coding in whole brain using MRI data.
problem Sparse coding in the whole brain's neural activities.
method Applied various matrix factorization methods to fMRI data.
result Sparse coding hypothesis in information representation in the whole human brain is confirmed.
Regularization improves stability and consistency of sparse autoencoders.
problem Varying features across random seeds and training choices in SAEs.
method Added L1 or L2 penalties on encoder and decoder weights.
result L2 regularization increases cross-seed feature consistency.
Sparse neural networks can match dense models on Lipschitz functions.
problem Sparse networks are more efficient but lack theoretical guarantees.
method Formal model of sparse networks, LSH-based routing function, Lipschitz function approximation.
result Sparse networks can approximate dense networks on Lipschitz functions.
Model shows loss curve with two distinct exponents due to sparse activations.
problem Sparse activations impact neural network scaling laws.
method Introduced a model for neural scaling laws under sparse activations, derived asymptotic population loss, and analyzed gradient-descent dynamics.
result Loss curve exhibits double-descent peak near interpolation threshold with two distinct scaling exponents.
Concerns about interpretability, computational resources, and principled inductive priors have motivated efforts to engineer sparse neural models for NLP tasks. If sparsity is important for NLP, might well-trained neural models naturally become roughly sparse? Using the Taxi-Euclidean norm to measure sparsity, we find …
Batteryless or so called passive wearables are providing new and innovative methods for human activity recognition (HAR), especially in healthcare applications for older people. Passive sensors are low cost, lightweight, unobtrusive and desirably disposable; attractive attributes for healthcare applications in hospital…
Sparse Transformers degrade semantic information first, with early layers encoding more.
problem Understanding how sparse Transformers affect learned representations and semantic information.
method Probed Transformers with progressively pruned weights to observe changes in semantic information and model behavior.
result Complex semantic information is first to degrade in sparse Transformers, with early layers encoding more.
Unified framework for clustering with sparse convex combinations.
problem Challenges in subspace clustering with limited labelled data.
method Spectral-based sparse subspace representation with extensions to constrained and active learning.
result Effective and competitive clustering results on simulated and real data.
Binary autoencoder with sparse hidden layer preserves information and zero reconstruction error.
problem Preserving information and zero reconstruction error in binary neural networks.
method Binary autoencoder with random binary weights, sparse hidden layer, and varying neuron thresholds.
result Zero reconstruction error for any input with a large hidden layer and varying neuron thresholds.
Transformers exhibit sparse activation maps, reducing computational load and improving robustness.
problem Sparse activation in Transformer models.
method Extensive experiments on various Transformer architectures and tasks.
result Sparsity in Transformers is a prevalent phenomenon, reducing FLOP count and improving model robustness.
We investigate sparse representations for control in reinforcement learning. While these representations are widely used in computer vision, their prevalence in reinforcement learning is limited to sparse coding where extracting representations for new data can be computationally intensive. Here, we begin by demonstrat…
In this paper, we consider the problem of recovering a sparse signal based on penalized least squares formulations. We develop a novel algorithm of primal-dual active set type for a class of nonconvex sparsity-promoting penalties, including ℓ0, bridge, smoothly clipped absolute deviation, capped ℓ1 and mini…
SAEs struggle with curved activation manifolds, revealing layer-dependent scaling laws.
problem Sparse autoencoders' reconstruction error varies across layers, not fitting existing scaling laws.
method Cross-layer study of 844 SAE checkpoints, fitting and regressing on manifold geometry.
result Manifold geometry predicts layer-dependent width exponents in SAEs, with transferable coefficients.
A method to improve sequential learning by keeping past data errors in check.
problem Challenges in sequential learning with Gaussian processes due to accumulating errors.
method Memory-based dual sparse variational Gaussian processes.
result Improves accuracy in inference and learning for various applications.
We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches. (i) It automatically derives a compact, sparse and meaningful feature representation of sensor data that does not rely on prior expert know…
Efficiently learns sparse halfspaces with noisy labels.
problem Learning sparse halfspaces with arbitrary bounded noise.
method Polynomial time algorithm for active learning with improved label complexity.
result First efficient algorithm with label complexity polynomial in 1−2η1. Deep Convolutional Sparse Coding (D-CSC) is a framework reminiscent of deep convolutional neural networks (DCNNs), but by omitting the learning of the dictionaries one can more transparently analyse the role of the activation function and its ability to recover activation paths through the layers. Papyan, Romano, and E…
Sparse Canonical Correlation Analysis (CCA) has received considerable attention in high-dimensional data analysis to study the relationship between two sets of random variables. However, there has been remarkably little theoretical statistical foundation on sparse CCA in high-dimensional settings despite active methodo…
DiAL uses Bayesian Dirichlet random fields for active learning with sparse labels.
problem Active learning with limited labeled data.
method Bayesian Dirichlet random field for feature-conditional class probabilities, calibrating with graph Laplacian.
result Competitive performance in low-label rate graph learning tasks.
New framework tackles high-dimensional reliability analysis using surrogate models and active subspaces.
problem High computational cost and curse of dimensionality in reliability analysis of high-dimensional systems.
method Sparse Active Subspace (SAS) algorithm for identifying low-dimensional manifolds and constructing efficient surrogate models.
result Proposed framework significantly improves accuracy and efficiency of reliability analysis compared to existing methods.
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.
The paper improves Gaussian process models for efficient batch optimization.
problem Poor scaling and optimization loop issues in Gaussian process models.
method Dual GP parameterization for linear scaling and non-Gaussian likelihood updates.
result Extends sparse models to greedy batch fantasizing acquisition functions.
Sparse Subspace Clustering (SSC) is a state-of-the-art method for clustering high-dimensional data points lying in a union of low-dimensional subspaces. However, while ℓ1 optimization-based SSC algorithms suffer from high computational complexity, other variants of SSC, such as Orthogonal Matching Pursuit-based S…
Active learning selects optimal measurement times for inferring continuous paths from sparse data.
problem Inferring continuous probability paths from sparse snapshots in high-fidelity domains like single-cell biology.
method Extends active experimentation to the space of measures using Linearized Optimal Transport (LOT) for probabilistic surrogate modeling.
result Empirical results show that the proposed strategy outperforms uncertainty-agnostic baselines.
We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference. The great success of DNNs motivates the pursuing of lightweight models for the deployment onto embedded devices. However, most of the prev…
We propose a novel general algorithm LHAC that efficiently uses second-order information to train a class of large-scale l1-regularized problems. Our method executes cheap iterations while achieving fast local convergence rate by exploiting the special structure of a low-rank matrix, constructed via quasi-Newton approx…
New proof shows neural networks can memorize training data with high accuracy.
problem Proving neural networks can memorize training data with high accuracy.
method Probabilistic construction exploiting sparsity.
result Proves neural networks with threshold or mixed threshold-ReLU activations can memorize training data.
We study the problem of efficient PAC active learning of homogeneous linear classifiers (halfspaces) in Rd, where the goal is to learn a halfspace with low error using as few label queries as possible. Under the extra assumption that there is a t-sparse halfspace that performs well on the data (t≪d)…
The digital revolution of the banking system with evolving European regulations have pushed the major banking actors to innovate by a newly use of their clients' digital information. Given highly sparse client activities, we propose CPOPT-Net, an algorithm that combines the CP canonical tensor decomposition, a multidim…
Brain networks in fMRI are typically identified using spatial independent component analysis (ICA), yet mathematical constraints such as sparse coding and positivity both provide alternate biologically-plausible frameworks for generating brain networks. Non-negative Matrix Factorization (NMF) would suppress negative BO…
New K-SVD framework speeds up image denoising with active set algorithm.
problem Efficiently denoise images with high noise levels.
method Proposes K-SVDP using Primal-dual active set (PDAS) algorithm. result Demonstrates comparable performance to state-of-the-art methods.
We study sparse group Lasso for high-dimensional double sparse linear regression, where the parameter of interest is simultaneously element-wise and group-wise sparse. This problem is an important instance of the simultaneously structured model -- an actively studied topic in statistics and machine learning. In the noi…
A new method for the unsupervised learning of sparse representations using autoencoders is proposed and implemented by ordering the output of the hidden units by their activation value and progressively reconstructing the input in this order. This can be done efficiently in parallel with the use of cumulative sums and …
Finding sparse solutions of underdetermined systems of linear equations is a fundamental problem in signal processing and statistics which has become a subject of interest in recent years. In general, these systems have infinitely many solutions. However, it may be shown that sufficiently sparse solutions may be identi…
New CSC model extracts EEG signals with low noise sensitivity.
problem Analyzing noisy EEG signals during anesthesia.
method Kruskal CSC model using Kruskal decomposition for low-rank tensor activations.
result TC-FISTA efficiently extracts robust, sparse, and interpretable EEG encodings.
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.