arXiv research

The bienergy of smooth maps between Riemannian manifolds, when restricted to unit vector fields, yields two different variational problems depending on whether one takes the full functional or just the vertical contribution. Their critical points, called biharmonic unit vector fields and biharmonic unit sections, form …

Characterizes magnetic unit vector fields on Lie groups.

In this paper we propose and investigate a novel nonlinear unit, called $L_p$ unit, for deep neural networks. The proposed $L_p$ unit receives signals from several projections of a subset of units in the layer below and computes a normalized $L_p$ norm. We notice two interesting interpretations of the $L_p$ unit. First…

Randomly chosen primary hidden units and derived secondary units reduce neural network complexity.

Study examines how business units can benefit from group cohesion under regulatory constraints.

Study examines dependence properties of Bayesian neural network units in finite-width networks.

Smooth groupoid algebras are H-unital, with implications for algebraic and homological properties.

Wasserstein t-SNE embeds hierarchical datasets considering within-unit distributions.

Most of the parameters in large vocabulary models are used in embedding layer to map categorical features to vectors and in softmax layer for classification weights. This is a bottle-neck in memory constraint on-device training applications like federated learning and on-device inference applications like automatic spe…

Study on hidden units in finite Bayesian neural networks and their tail properties.

We present a new equation with respect to a unit vector field on Riemannian manifold $M^n$ such that its solution defines a totally geodesic submanifold in the unit tangent bundle with Sasaki metric and apply it to some classes of unit vector fields. We introduce a class of covariantly normal unit vector fields and pro…

Bayesian units improve speech recognition with minimal parameters.

Let Σbe a k-dimensional minimal surface in the unit ball B^n which meets the unit sphere orthogonally. We show that the area of Σis bounded from below by the volume of the unit ball in R^k. This answers a question posed by R. Schoen.

Minimal vector fields on oscillator groups studied, with specific conditions for minimality.

Neural Power Unit (NPU) learns arbitrary power functions on real numbers.

Study calculates first $p$-widths of unit disk.

In a seminal paper Abadie, Diamond, and Hainmueller [2010] (ADH), see also Abadie and Gardeazabal [2003], Abadie et al. [2014], develop the synthetic control procedure for estimating the effect of a treatment, in the presence of a single treated unit and a number of control units, with pre-treatment outcomes observed f…

We investigate deep Bayesian neural networks with Gaussian weight priors and a class of ReLU-like nonlinearities. Bayesian neural networks with Gaussian priors are well known to induce an L2, "weight decay", regularization. Our results characterize a more intricate regularization effect at the level of the unit activat…

We construct homotopically non-trivial maps from the unit m-sphere to the unit (m-1)-sphere with arbitrarily small k-dilation for each k greater than (m + 1)/2. We prove that homotopically non-trivial maps from the unit m-sphere to the unit (m-1)-sphere cannot have arbitrarily small k-dilation for k less than or equal …

Can certain shapes be drawn with a pencil and eraser?

We present a probabilistic variant of the recently introduced maxout unit. The success of deep neural networks utilizing maxout can partly be attributed to favorable performance under dropout, when compared to rectified linear units. It however also depends on the fact that each maxout unit performs a pooling operation…

We study unit horizontal bundles associated with Riemannian submersions. First we investigate metric properties of an arbitrary unit horizontal bundle equipped with a Riemannian metric of the Cheeger-Gromoll type. Next we examine it from the Gromov-Hausdorff convergence theory point of view, and we state a collapse the…

Bayesian SHMM models speech units from unannotated speech.

Foreign exchange markets show that currency units (= accounting or nominal price units) are variables. Technical and economic progress evidence that the consumer baskets (= purchasing power units or real price units) are also variables. In contrast, all physical measurement units are constants and either defined in the…

Training data-driven approaches for complex industrial system health monitoring is challenging. When data on faulty conditions are rare or not available, the training has to be performed in a unsupervised manner. In addition, when the observation period, used for training, is kept short, to be able to monitor the syste…

New minimal surfaces found in ball with boundary constraints.

Researchers determine the Thurston unit ball for a family of $n$-chained links and find conditions for fibered faces.

Synthetic control method improves policy evaluation in high-dimensional settings.

In adversarial attacks to machine-learning classifiers, small perturbations are added to input that is correctly classified. The perturbations yield adversarial examples, which are virtually indistinguishable from the unperturbed input, and yet are misclassified. In standard neural networks used for deep learning, atta…

The paper addresses selection bias in conformal prediction for focal units.

Study shows how certain foliations in unit tangent bundles behave.

A method for making machine learning units-equivariant using dimensional analysis.

We give a full geometrical description of local totally geodesic unit vector field on Riemannian 2-manifold, considering the field as a local imbedding of the manifold into its unit tangent bundle with the Sasaki metric.

Study inverse curvature flows for capillary hypersurfaces in a unit ball.

The paper finds the Finsler structure of Apollonian weak metric on unit disc.

A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network's width is increased. Recent evidence suggests that developing compressible representations is key for adjusting the complexity of large networks to the learning task at hand. However, t…

We establish upper bounds for the minimal number of hidden units for which a binary stochastic feedforward network with sigmoid activation probabilities and a single hidden layer is a universal approximator of Markov kernels. We show that each possible probabilistic assignment of the states of $n$ output units, given t…

Study constructs disks with curved boundaries in a 3D ball.

Study $4$-dim hypersurfaces with constant mean curvature in unit spheres.

We give a complete list of those left invariant unit vector fields on three-dimensional Lie groups with the left-invariant metric that generate a totally geodesic submanifold in the unit tangent bundle of a group with the Sasaki metric. As a result, each class of three-dimensional Lie groups admits the totally geodesic…

Characterizes special curves on surface tangent bundles.

The unit ball is characterized by a Kähler-Einstein potential.

In this paper, we study the rigidity theorem of closed minimally immersed Legendrian submanifolds in the unit sphere. Utilizing the maximum principle, we obtain a new characterization of the Calabi torus in the unit sphere which is the minimal Calabi product Legendrian immersion of a point and the totally geodesic Lege…

A new method for online prediction uncertainty quantification in non-exchangeable panel data.

Volume of unit balls defined by quadratic differentials is not proper and has integrable volume.

Recently, neural networks in machine learning use rectified linear units (ReLUs) in early processing layers for better performance. Training these structures sometimes results in "dying ReLU units" with near-zero outputs. We first explore this condition via simulation using the CIFAR-10 dataset and variants of two popu…

Unit-free approach to Jacobi geometry and Hamiltonian mechanics.

This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages. Our approach may be described by the following two steps procedure: first the model learns the notion of acoustic units from the labelled data and …