arXiv research

New framework for neural networks converging to low loss without overparameterization.

Dynamic Sparse Training finds efficient sparse networks from scratch.

In this work, we leverage advances in sparse coding techniques to reduce the number of trainable parameters in a fully connected neural network. While most of the works in literature impose $\ell_1$ regularization, DropOut or DropConnect techniques to induce sparsity, our scheme considers feature importance as a criter…

Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered "black box" models whose internal structure and learned parameters are not interpretable. In this paper, we propose an interpretable RNN based on the sequential iterative soft-thresholding al…

New algorithms improve neural architecture search with faster convergence.

Paper connects neural network hyperparameter optimization and NAS to structured sparse recovery.

FiGS searches over a larger space of architectures for efficient mobile models.

One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training. It can be treated as a Network Compression problem on the architecture parameters from an over-parameterized network. However, there are two issues associated with most one-shot NAS methods…

Paper tackles NAS problem by modeling it as a sparse supernet.

This paper presents a novel deep learning architecture for short term load forecasting of building energy loads. The architecture is based on a simple base learner and multiple boosting systems that are modelled as a single deep neural network. The architecture transforms the original multivariate time series into mult…

New insights into the top-K sparse softmax gating function for deep learning.

Deep networks learn sparse hierarchical features without CoD.

Boosts share routing for multi-task learning with flexible sparse connections.

New method selects neural network architectures without needing data.

Recovering sparse conditional independence graphs from data is a fundamental problem in machine learning with wide applications. A popular formulation of the problem is an $\ell_1$ regularized maximum likelihood estimation. Many convex optimization algorithms have been designed to solve this formulation to recover the …

i-SpaSP prunes neural networks by identifying important groups of parameters, improving pruning efficiency.

Top-KAST maintains constant sparsity in large neural networks, improving performance and reducing resource usage.

Wide neural networks learn features under $μ$P, identifying weights and decomposing support.

Prototype model improves model auditing and understanding.

Parsimonious representations are ubiquitous in modeling and processing information. Motivated by the recent Multi-Layer Convolutional Sparse Coding (ML-CSC) model, we herein generalize the traditional Basis Pursuit problem to a multi-layer setting, introducing similar sparse enforcing penalties at different representat…

Hydra boosts efficiency for long-context reasoning in resource-constrained settings.

Kernelised flows improve density estimation and generation with fewer parameters.

EASIER-net uses sparse networks to improve prediction accuracy for high-dimensional data.

VINNAS uses variational inference to avoid mode collapse in neural architecture search.

In this paper, we propose a novel recurrent neural network architecture for speech separation. This architecture is constructed by unfolding the iterations of a sequential iterative soft-thresholding algorithm (ISTA) that solves the optimization problem for sparse nonnegative matrix factorization (NMF) of spectrograms.…

Sparse transformer architecture improves accuracy and speed in generative modeling and inverse problems.

Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time by leveraging proxy models, leading to architectures with competitive performance compared to those with hand-crafted designs. In this pape…

Neural models for NLP typically use large numbers of parameters to reach state-of-the-art performance, which can lead to excessive memory usage and increased runtime. We present a structure learning method for learning sparse, parameter-efficient NLP models. Our method applies group lasso to rational RNNs (Peng et al.,…

Consider the multivariate nonparametric regression model. It is shown that estimators based on sparsely connected deep neural networks with ReLU activation function and properly chosen network architecture achieve the minimax rates of convergence (up to $\log n$-factors) under a general composition assumption on the re…

A-DLISTA and VLISTA learn dictionaries and sparse representations under varying sensing matrices.

USN improves neural networks with uniform sparse connectivity.

MLP-Mixer achieves better performance through sparsity and wider architecture.

Sparse coding is a basic task in many fields including signal processing, neuroscience and machine learning where the goal is to learn a basis that enables a sparse representation of a given set of data, if one exists. Its standard formulation is as a non-convex optimization problem which is solved in practice by heuri…

We present a comprehensive framework for structured sparse coding and modeling extending the recent ideas of using learnable fast regressors to approximate exact sparse codes. For this purpose, we develop a novel block-coordinate proximal splitting method for the iterative solution of hierarchical sparse coding problem…

S$^2$GPT-PINNs solve PDEs with sparse, small models.

Proposes a new framework for predicting stock market movements using sparse neural architectures.

We present a general architecture of deep differentiable forest and its sparse attention mechanism. The differentiable forest has the advantages of both trees and neural networks. Its structure is a simple binary tree, easy to use and understand. It has full differentiability and all variables are learnable parameters.…

Deep learning models reconstruct volatility surfaces from noisy data under no-arbitrage constraints.

Capitalizing on the need for addressing the existing challenges associated with gesture recognition via sparse multichannel surface Electromyography (sEMG) signals, the paper proposes a novel deep learning model, referred to as the XceptionTime architecture. The proposed innovative XceptionTime is designed by integrati…

Study finds differences in LTs across tasks and architectures, proposing a consensus-based method for generating refined lottery tickets.

Bayesian KANs achieve near-minimax posterior contraction rates in anisotropic Besov spaces.

Given a convolutional dictionary underlying a set of observed signals, can a carefully designed auto-encoder recover the dictionary in the presence of noise? We introduce an auto-encoder architecture, termed constrained recurrent sparse auto-encoder (CRsAE), that answers this question in the affirmative. Given an input…

We propose Sparse Neural Network architectures that are based on random or structured bipartite graph topologies. Sparse architectures provide compression of the models learned and speed-ups of computations, they can also surpass their unstructured or fully connected counterparts. As we show, even more compact topologi…

Current deep learning architectures are growing larger in order to learn from complex datasets. These architectures require giant matrix multiplication operations to train millions of parameters. Conversely, there is another growing trend to bring deep learning to low-power, embedded devices. The matrix operations, ass…

We provide a series of results for unsupervised learning with autoencoders. Specifically, we study shallow two-layer autoencoder architectures with shared weights. We focus on three generative models for data that are common in statistical machine learning: (i) the mixture-of-gaussians model, (ii) the sparse coding mod…

Many transformations in deep learning architectures are sparsely connected. When such transformations cannot be designed by hand, they can be learned, even through plain backpropagation, for instance in attention mechanisms. However, during learning, such sparse structures are often represented in a dense form, as we d…

The paper analyzes dynamics of momentum in high dimensions with sparse updates.

This paper explores efficient neural networks by identifying sparse structures.