arXiv research

Neural networks can separate non-separable data using feature maps.

DSI measures dataset separability for neural networks.

This paper investigates how data augmentation improves linear separation of manifold data.

A new measure DCSI quantifies separability for density-based clustering.

Improved clustering of extra-financial data using NMF with data separation.

The paper solves optimal bounds for separating data points in high dimensions.

Scattering networks maximize separation on low-dimensional data.

This work addresses the problem of learning sparse representations of tensor data using structured dictionary learning. It proposes learning a mixture of separable dictionaries to better capture the structure of tensor data by generalizing the separable dictionary learning model. Two different approaches for learning m…

Law explains how deep networks separate data for classification.

Constructs classifiers for neural networks with specific data configurations.

Despite substantial progress in signal source separation, results for richly structured data continue to contain perceptible artifacts. In contrast, recent deep generative models can produce authentic samples in a variety of domains that are indistinguishable from samples of the data distribution. This paper introduces…

Shallow nonlinear networks can separate classes linearly with polynomially scaling width.

Logistic regression is one of the most popular methods in binary classification, wherein estimation of model parameters is carried out by solving the maximum likelihood (ML) optimization problem, and the ML estimator is defined to be the optimal solution of this problem. It is well known that the ML estimator exists wh…

Neural networks use their hidden layers to transform input data into linearly separable data clusters, with a linear or a perceptron type output layer making the final projection on the line perpendicular to the discriminating hyperplane. For complex data with multimodal distributions this transformation is difficult t…

Adam optimizes linear classifiers with separable data.

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing of naturalistic audio streams. After incorporating deep learning techniques into…

Mixup reduces the sample complexity of finding optimal decision boundaries for more separable data.

Mirror flow optimizes separable data problems, converging to a maximum margin classifier.

We quantify the separation between the numbers of labeled examples required to learn in two settings: Settings with and without the knowledge of the distribution of the unlabeled data. More specifically, we prove a separation by $Θ(\log n)$ multiplicative factor for the class of projections over the Boolean hypercube o…

This work examines a semi-blind single-channel source separation problem. Our specific aim is to separate one source whose local structure is approximately known, from another a priori unspecified background source, given only a single linear combination of the two sources. We propose a separation technique based on lo…

Paper develops robust methods for panel data with latent groups, improving inference under group separation violations.

New indices for determining cluster compactness and separability.

New findings on robust learning with well-separated data.

We show linear XOR classification is possible and propose equality separation for anomaly detection.

Nonnegative matrix factorization (NMF) is a linear dimensionality technique for nonnegative data with applications such as image analysis, text mining, audio source separation and hyperspectral unmixing. Given a data matrix $M$ and a factorization rank $r$, NMF looks for a nonnegative matrix $W$ with $r$ columns and a …

This paper proposes RAS, a novel unsupervised loss function for speech separation.

Spatial blind source separation simplifies multivariate spatial prediction.

Gradient methods avoid overfitting on separable data.

SRTC model for background/foreground separation with missing pixels.

A new method for separating mixed signals in space and time.

DISCoVeR learns disentangled representations by separating shared and condition-specific factors.

Adversarial noises are linearly separable for random neural networks.

This paper presents an unsupervised method that trains neural source separation by using only multichannel mixture signals. Conventional neural separation methods require a lot of supervised data to achieve excellent performance. Although multichannel methods based on spatial information can work without such training …

New algorithms improve blind source separation for linear-quadratic mixtures.

A new NMF variant tackles underdetermined problems with sparse and separable assumptions.

Separable losses are inconsistent for structured prediction models.

The paper connects decision tree interpretability and robustness through separation.

New kernels allow learning from non-separable data.

A new NMF model for co-clustering and data approximation.

Graph convolution improves linear separability and generalizes to out-of-distribution data.

Sparse Blind Source Separation (sparse BSS) is a key method to analyze multichannel data in fields ranging from medical imaging to astrophysics. However, since it relies on seeking the solution of a non-convex penalized matrix factorization problem, its performances largely depend on the optimization strategy. In this …

This work investigates implicit bias in multiclass separable data using a novel geometry-aware optimizer.

Inverse Drum Machine separates drum mixes using transcription and synthesis.

Introduces Soft-SVM for binary classification bridging logistic and SVM.

We augment the nonnegative matrix factorization method for audio source separation with cues about directionality of sound propagation. This improves separation quality greatly and removes the need for training data, with only a twofold increase in run time. This is the first method which can exploit directional inform…

The task of clustering a set of objects based on multiple sources of data arises in several modern applications. We propose an integrative statistical model that permits a separate clustering of the objects for each data source. These separate clusterings adhere loosely to an overall consensus clustering, and hence the…

We propose a new framework for single-channel source separation that lies between the fully supervised and unsupervised setting. Instead of supervision, we provide input features for each source signal and use convex methods to estimate the correlations between these features and the unobserved signal decomposition. We…

Paper separates financial time series into fast and slow components.