arXiv research

New concept of regular separation for ODEs leads to improved Hardy field results.

Posterior regularization enhances Bayesian hierarchical mixture clustering by improving node separation.

In recent years, deep learning has surpassed traditional approaches to the problem of singing voice separation. The Wave-U-Net is a recent deep network architecture that operates directly on the time domain. The standard Wave-U-Net is trained with data augmentation and early stopping to prevent overfitting. Minimum hyp…

New method improves source separation using NMF and adversarial learning.

We discuss the $ζ-$regularized determinant of elliptic boundary value problems on a line segment. Our framework is applicable for separated and non-separated boundary conditions.

Study optimizes fairness in predictive models by balancing utility and separation.

We show that two uniform lattices of a regular right-angled Fuchsian building are commensurable, provided the chamber is a polygon with at least six edges. We show that in an arbitrary Gromov-hyperbolic regular right-angled building associated to a graph product of finite groups, a uniform lattice is commensurable with…

This work simplifies SVM parameter selection using S&S ratio.

We propose $\ell_1$ norm regularized quadratic surface support vector machine models for binary classification in supervised learning. We establish their desired theoretical properties, including the existence and uniqueness of the optimal solution, reduction to the standard SVMs over (almost) linearly separable data s…

The Douglas Rachford algorithm is an algorithm that converges to a minimizer of a sum of two convex functions. The algorithm consists in fixed point iterations involving computations of the proximity operators of the two functions separately. The paper investigates a stochastic version of the algorithm where both funct…

The Phi- relationship also known as Phi-factor appears in a number of lattice structures, mostly considering the lines within several separate circles or polygons. The paper considers a regular hexagonal tessellation as a lattice with the highest specific mechanical stiffness.

slimTrain simplifies DNN training by separating features and adapting hyperparameters.

New framework links fractal complexity to separation dimension.

A new method speeds up overlapping group lasso computations.

We study the asymptotic behaviour of regularized determinants of certain Laplace type operators with respect to singular deformations of the underlying manifold which are obtained by stretching a tubular neighborhood of an embedded separating hypersurface to a cylinder of infinite length. Using the asymptotic expansion…

New methods optimize personalized treatment assignment in trials with many arms.

The lack of interpretability remains a barrier to the adoption of deep neural networks. Recently, tree regularization has been proposed to encourage deep neural networks to resemble compact, axis-aligned decision trees without significant compromises in accuracy. However, it may be unreasonable to expect that a single …

New complex connects graph separability to group properties.

New method improves deep learning models robustness to label noise.

Turaev-Viro invariants match for certain surface bundles.

This paper presents a unified framework for smooth convex regularization of discrete optimal transport problems. In this context, the regularized optimal transport turns out to be equivalent to a matrix nearness problem with respect to Bregman divergences. Our framework thus naturally generalizes a previously proposed …

In a previous article, analytic 1-submanifolds had been classified w.r.t. their symmetry under a given regular and separately analytic Lie group action on an analytic manifold. It was shown that such an analytic 1-submanifold is either free or (via the exponential map) analytically diffeomorphic to the unit circle or a…

Gradient flow on softmax attention minimizes nuclear norm of weight matrices.

Paper proposes a new method to separate low rank and sparse matrices without bias.

Regularization is one of the crucial ingredients of deep learning, yet the term regularization has various definitions, and regularization methods are often studied separately from each other. In our work we present a systematic, unifying taxonomy to categorize existing methods. We distinguish methods that affect data,…

The paper extends optimal transport for linear separability of sheared distributions in supervised learning.

Deep clustering is the first method to handle general audio separation scenarios with multiple sources of the same type and an arbitrary number of sources, performing impressively in speaker-independent speech separation tasks. However, little is known about its effectiveness in other challenging situations such as mus…

New method improves source separation using adversarial NMF.

SRTC model for background/foreground separation with missing pixels.

For the problem of high-dimensional sparse linear regression, it is known that an $\ell_0$-based estimator can achieve a $1/n$ "fast" rate on the prediction error without any conditions on the design matrix, whereas in absence of restrictive conditions on the design matrix, popular polynomial-time methods only guarante…

We study the order of tangency between two manifolds of same dimension and give that notion three quite different geometric interpretations. Related aspects of the order of tangency, e.g., regular separation exponents, are also discussed.

Lowered regularity assumption for a phase-dependent Helfrich energy equation.

The paper discusses conditions for gluing multiple Alexandrov spaces into an Alexandrov space.

In magnetoencephalography (MEG) the conventional approach to source reconstruction is to solve the underdetermined inverse problem independently over time and space. Here we present how the conventional approach can be extended by regularizing the solution in space and time by a Gaussian process (Gaussian random field)…

The support vector machine (SVM) is a widely used machine learning tool for classification based on statistical learning theory. Given a set of training data, the SVM finds a hyperplane that separates two different classes of data points by the largest distance. While the standard form of SVM uses L2-norm regularizatio…

Large stepsizes can accelerate gradient descent for logistic regression.

We present a data dependent generalization bound for a large class of regularized algorithms which implement structured sparsity constraints. The bound can be applied to standard squared-norm regularization, the Lasso, the group Lasso, some versions of the group Lasso with overlapping groups, multiple kernel learning a…

The paper analyzes the risk of CV-tuned regularized estimators and connects it to SURE.

This work establishes universality for deep equivariant networks, overcoming limitations of previous approaches.

Let $M$ be a simple 3-manifold such that one component of $\partial M$, say $F$, has genus at least two. For a slope $α$ on $F$, we denote by $M(α)$ the manifold obtained by attaching a 2-handle to $M$ along a regular neighborhood of $α$ on $F$. If $M(α)$ is reducible, then $α$ is called a reducing slope. In this paper…

Hybrid model improves music source separation by 1.4 dB.

Recently, the principal component pursuit has received increasing attention in signal processing research ranging from source separation to video surveillance. So far, all existing formulations are real-valued and lack the concept of phase, which is inherent in inputs such as complex spectrograms or color images. Thus,…

Local regularization fails in transductive learning for some multiclass problems.

We present an alternating augmented Lagrangian method for convex optimization problems where the cost function is the sum of two terms, one that is separable in the variable blocks, and a second that is separable in the difference between consecutive variable blocks. Examples of such problems include Fused Lasso estima…

We formalize causal separation in portfolio theory, deriving a closed-form projected Markowitz solution.

We propose a novel SPARsity and Clustering (SPARC) regularizer, which is a modified version of the previous octagonal shrinkage and clustering algorithm for regression (OSCAR), where, the proposed regularizer consists of a $K$-sparse constraint and a pair-wise $\ell_{\infty}$ norm restricted on the $K$ largest componen…

We study incompressible surfaces constructed by Culler-Shalen theory in the context of twisted Alexander polynomials. For a $1$st cohomology class of a $3$-manifold the coefficients of twisted Alexander polynomials induce regular functions on the $SL_2(\mathbb{C})$-character variety. We prove that if an ideal point giv…

Optimizes two-sample tests for non-Euclidean domains using spectral regularization.