arXiv research

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

AlphaNet improves supernets training with alpha-divergence.

SuperNet speeds up neural network ensembling by training a single DNN for various phases.

To discover powerful yet compact models is an important goal of neural architecture search. Previous two-stage one-shot approaches are limited by search space with a fixed depth. It seems handy to include an additional skip connection in the search space to make depths variable. However, it creates a large range of per…

One-Shot Neural architecture search (NAS) attracts broad attention recently due to its capacity to reduce the computational hours through weight sharing. However, extensive experiments on several recent works show that there is no positive correlation between the validation accuracy with inherited weights from the supe…

This research improves multitask learning by creating task-specific pathways.

MixPath unifies multi-path neural architecture search with one-shot training.

One of the most critical problems in weight-sharing neural architecture search is the evaluation of candidate models within a predefined search space. In practice, a one-shot supernet is trained to serve as an evaluator. A faithful ranking certainly leads to more accurate searching results. However, current methods are…

S3NAS finds high-accuracy CNN architectures for NPUs in 3 hours.

BS-NAS broadens and shrinks search space for optimal neural architectures.

New method grows deep networks efficiently by dynamically pruning and growing layers.

A lightweight network and NAS method improve ASC tasks.

The ability to rank candidate architectures is the key to the performance of neural architecture search~(NAS). One-shot NAS is proposed to reduce the expense but shows inferior performance against conventional NAS and is not adequately stable. We investigate into this and find that the ranking correlation between archi…

Sparse Hopfield model improves memory retrieval with fewer connections.

New quantum code lacks sparse lift.

In this paper, a sparse Markov decision process (MDP) with novel causal sparse Tsallis entropy regularization is proposed.The proposed policy regularization induces a sparse and multi-modal optimal policy distribution of a sparse MDP. The full mathematical analysis of the proposed sparse MDP is provided.We first analyz…

This work introduces a method to compare sparse neural network topologies using graph theory.

Sparse-RS framework efficiently attacks models with sparse perturbations.

Using a Bayesian approach, we consider the problem of recovering sparse signals under additive sparse and dense noise. Typically, sparse noise models outliers, impulse bursts or data loss. To handle sparse noise, existing methods simultaneously estimate the sparse signal of interest and the sparse noise of no interest.…

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…

Sparse DNNs face scalability issues; MIT/IEEE/Amazon challenge analyzes best solutions.

In compressed sensing, we wish to reconstruct a sparse signal $x$ from observed data $y$. In sparse coding, on the other hand, we wish to find a representation of an observed signal $y$ as a sparse linear combination, with coefficients $x$, of elements from an overcomplete dictionary. While many algorithms are competit…

Sparse coding approximates the data sample as a sparse linear combination of some basic codewords and uses the sparse codes as new presentations. In this paper, we investigate learning discriminative sparse codes by sparse coding in a semi-supervised manner, where only a few training samples are labeled. By using the m…

Dynamic Sparse Training finds efficient sparse networks from scratch.

New method for hyperparameter tuning in sparse matrix factorization.

We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse momentum, an algorithm which uses exponentially smoothed gradients (momentum) to…

High dimensional sparse learning has imposed a great computational challenge to large scale data analysis. In this paper, we are interested in a broad class of sparse learning approaches formulated as linear programs parametrized by a {\em regularization factor}, and solve them by the parametric simplex method (PSM). O…

This paper explores loss landscapes of sparse neural networks, finding unique characteristics compared to dense networks.

Sparse APCA identifies sparse factors in financial returns over time.

Study confirms sparse coding in whole brain using MRI data.

A new method for sparse PCA using orthogonal rotations and soft-thresholding.

Develops sparse portfolio strategy for high-dimensional assets.

Picasso is a new library for sparse learning problems in R and Python.

The CUR decomposition provides an approximation of a matrix $X$ that has low reconstruction error and that is sparse in the sense that the resulting approximation lies in the span of only a few columns of $X$. In this regard, it appears to be similar to many sparse PCA methods. However, CUR takes a randomized algorithm…

DFR reduces the computational cost of sparse-group lasso and adaptive sparse-group lasso.

A variety of representation learning approaches have been investigated for reinforcement learning; much less attention, however, has been given to investigating the utility of sparse coding. Outside of reinforcement learning, sparse coding representations have been widely used, with non-convex objectives that result in…

Guarantees sparse recovery for neural networks with iterative hard thresholding.

New methods show sparse portfolios offer no advantage over mean-variance in diversification.

Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture of sparse experts to efficiently retrieve top-k classes. Different from most…

msPCA solves sparse PCA for multiple components efficiently.

We consider the scenario where one observes an outcome variable and sets of features from multiple assays, all measured on the same set of samples. One approach that has been proposed for dealing with this type of data is ``sparse multiple canonical correlation analysis'' (sparse mCCA). All of the current sparse mCCA t…

Predictive Sparse Manifold Transform learns dynamic video sequences.

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…

New method finds sparse networks without labels, improving performance.

Sparse curves on surfaces grow at a specific intermediate rate.

Is it possible to find the sparsest vector (direction) in a generic subspace $\mathcal{S} \subseteq \mathbb{R}^p$ with $\mathrm{dim}(\mathcal{S})= n < p$? This problem can be considered a homogeneous variant of the sparse recovery problem, and finds connections to sparse dictionary learning, sparse PCA, and many other …

This paper establishes conditions for sparse signal recovery with sparse measurements.

New method improves robust sparse association estimation.