Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

3467101134 · Jun 202019922001200920182026
48 results for normality

Online Normalization normalizes neural network activations without batching for better accuracy.

problem Theoretical limitations of Batch Normalization and its inapplicability to certain network types.
method Introduces an unbiased gradient computation technique for normalized activations without using batches.
result Equivalent accuracy to Batch Normalization without batch usage.

This paper analyzes how normalization layers improve neural network training.

problem Improving generalization performance and training speed of neural networks.
method Global convergence analysis of two-layer neural networks with ReLU activations and Weight Normalization.
result Introduction of normalization layers changes the optimization landscape, enabling faster convergence.

Distance, normals, and double normals for real plane curves with singularities

problem Relation between normals and double normals and critical points of the squared distance function for real algebraic curves with singularities
method Investigate the topological discriminant of the distance function
result The topological discriminant consists of the evolute and distinguished normal lines at algebraic singular points

Optimized normalization layers improve domain generalization.

problem Improving model generalization across different domains.
method Learning separate normalization parameters per domain using multiple normalization methods (batch and instance).
result State-of-the-art accuracy on domain generalization benchmarks.

We consider the Laplace normal vector field of relatively normalized ruled surfaces with non-vanishing Gaussian curvature in the three-dimensional Euclidean space R3\mathbb{R}^{3}. We determine all ruled surfaces and all relative normalizations for which the Laplace normal image degenerates into a point or into a curve…

2015-10-28abs ↗pdf ↗

Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the distribution of the summed input to a neuron over a mini-batch of training cases to compute…

2016-07-21abs ↗pdf ↗

Proposes a flexible normalization method to handle multi-modal data.

problem Reduced effectiveness of batch normalization in multi-modal distributions.
method Extends normalization to multiple means and variances, detecting data modes on-the-fly.
result Outperforms batch normalization and other methods in various experiments.

Four improvements to Batch Normalization improve deep learning performance.

problem Improving Batch Normalization for better deep learning performance.
method Proposed improvements include reasoning about current examples, Ghost Batch Normalization, weight decay regularization, and a new normalization algorithm for small batch sizes.
result Performance gains across all batch sizes with no additional computation during training.

Developed criteria for selecting non-normalized models using NCE and score matching.

problem No information criteria for non-normalized models estimated by NCE or score matching.
method Developed information criteria based on discrepancy measures for non-normalized models estimated by NCE or score matching.
result The proposed criteria enable selection of the appropriate non-normalized model in a data-driven manner.

This paper investigates the impact of normalization on deep neural networks for click-through rate prediction.

problem The effect of normalization on deep neural network models for CTR estimation.
method Systematic study of various normalization approaches applied to feature embedding and MLP part of DNN models.
result Correct normalization significantly enhances model performance, as demonstrated by extensive experiments on real-world datasets.

The study finds abundant normal generators for mapping class groups.

problem Understanding normal generation in mapping class groups.
method Analyzing restrictions on invariant subsurfaces and Teichmüller spaces.
result Reducible mapping classes can normally generate mapping class groups based on their asymptotic translation lengths.

This paper deals with skew ruled surfaces in the Euclidean space E3\mathbb{E}^{3} which are equipped with polar normalizations, that is, relative normalizations such that the relative normal at each point of the ruled surface lies on the corresponding polar plane. We determine the invariants of a such normalized ruled …

2017-11-29abs ↗pdf ↗

We define a 2-normal surface to be one which intersects every 3-simplex of a triangulated 3-manifold in normal triangles and quadrilaterals, with one or two exceptions. The possible exceptions are a pair of octagons, a pair of unknotted tubes, an octagon and a tube, or a 12-gon. In this paper we use the theory of criti…

2003-09-26abs ↗pdf ↗

The paper updates Bayesian CMA-ES with normal Wishart and proves lower expected covariance.

problem Improving the Bayesian CMA-ES algorithm with normal Wishart prior.
method Revisits Bayesian CMA-ES, proves lower expected covariance in normal Wishart, and presents a generalized model.
result Proves that the expected covariance is lower in the normal Wishart prior model due to convexity of the inverse.

Layer normalization improves federated learning with skewed labels.

problem Label skewness in federated learning datasets.
method Identified feature normalization as key mechanism; applied to latent features before classifier.
result Normalization accelerates global training and improves convergence under extreme label shift.

Following Matveev, a k-normal surface in a triangulated 3-manifold is a generalization of both normal and (octagonal) almost normal surfaces. Using spines, complexity, and Turaev-Viro invariants of 3-manifolds, we prove the following results: 1) a minimal triangulation of a closed irreducible or a bounded hyperbolic 3-…

2006-06-05abs ↗pdf ↗

In this paper, we study normal homogeneous Finsler spaces. We first define the notion of a normal homogeneous Finsler space, using the method of isometric submersion of Finsler metrics. Then we study the geometric properties. In particular, we establish a technique to reduce the classification of normal homogeneous Fin…

2014-11-12abs ↗pdf ↗

Paper classifies rational 3-tangles using normal forms and minimal coordinates.

problem Classifying rational 3-tangles up to isotopy.
method Defined normal form and normal coordinate, investigated minimal coordinates, constructed contractible simplicial complex.
result Simplicial complex of normal forms is contractible, leading to classification of rational 3-tangles.

Channel normalization prevents vanishing gradients in convolutional neural networks.

problem Vanishing gradients in convolutional neural networks during optimization.
method Channel normalization, which centers and normalizes each channel individually.
result Channel normalization avoids vanishing gradients, enabling efficient optimization.

This study investigates global normalization in neural models, showing its effectiveness in search-aware training.

problem Theoretical equivalence of global and local normalization in high-capacity models, practical advantage unclear.
method Continuous relaxation of beam search for training globally normalized recurrent sequence models.
result Globally normalized models are more effective than locally normalized ones in inexact search.

PL-MCMC samples from normalizing flows' conditional distributions.

problem Sampling from complex conditional distributions learned by normalizing flows.
method Metropolis-Hastings implementation of PL-MCMC.
result PL-MCMC asymptotically samples from exact conditional distributions.

New normalization technique balances positive and negative weights for faster convergence.

problem Balancing positive and negative weights for faster convergence.
method Transformation of layer weights instead of outputs, balancing positive and negative contributions.
result Balanced normalization leads to faster convergence on standard benchmarks.

A virtual link diagram is called normal if the associated abstract link diagram is checkerboard colorable, and a virtual link is normal if it has a normal diagram as a representative.In this paper, we introduce a method of converting a virtual link diagram to a normal virtual link diagram by use of the double covering …

2016-06-02abs ↗pdf ↗

Calculation of the log-normalizer is a major computational obstacle in applications of log-linear models with large output spaces. The problem of fast normalizer computation has therefore attracted significant attention in the theoretical and applied machine learning literature. In this paper, we analyze a recently pro…

2015-06-12abs ↗pdf ↗

We study the normal holonomy group, i.e. the holonomy group of the normal connection, of a CR-submanifold of a complex space form. We complete the local classification of normal holonomies for complex submanifolds. We show that the normal holonomy group of a coisotropic submanifold acts as the holonomy representation o…

2013-11-22abs ↗pdf ↗

We say A is a quasi-normal subgroup of the group G if the commensurator of A in G is all of G. We develop geometric versions of commensurators in finitely generated groups. In particular, g is an element of the commensurator of A in G iff the Hausdorff distance between A and gA is finite. We show that a quasi-normal su…

2009-12-29abs ↗pdf ↗

Paper proves non-existence of certain hypersurfaces in complex quadric.

problem Non-existence of Hopf real hypersurfaces with parallel normal Jacobi operator.
method Introducing C\mathcal C-parallel and Reeb parallel normal Jacobi operators, proving non-existence theorems.
result Non-existence of Hopf real hypersurfaces with C\mathcal C-parallel normal Jacobi operator.

In this article, we first describe a normal form of real-analytic, Levi-nondegenerate submanifolds of CNC^N of codimension d \ge 1 under the action of formal biholomorphisms, that is, of perturbations of Levi-nondegenerate hyperquadrics. We give a sufficient condition on the formal normal form that ensures that the n…

2017-05-11abs ↗pdf ↗

Proposes a unified normalization method for multi-domain medical images.

problem Inadequate joint information across multiple datasets hinders image segmentation performance.
method Adversarial and task-driven normalization approach to learn a common normalizing function across multiple datasets.
result Jointly normalized images improve segmentation accuracy by up to 57.5%.

TaskNorm improves meta-learning performance by rethinking batch normalization.

problem Challenges in batch normalization for meta-learning with deep networks.
method Developed TaskNorm, a novel approach to batch normalization for meta-learning.
result TaskNorm consistently improves meta-learning performance across various datasets and meta-learning approaches.

Adaptive feature normalization improves model robustness to extraneous variables.

problem Degrading model performance due to extraneous variables in deep learning.
method Adaptive feature normalization using instance normalization instead of batch normalization.
result Adaptive normalization leads to significant performance gains across different datasets and architectures.

We introduce in this paper normal twistor equations for differential forms and study their solutions, the so-called normal conformal Killing forms. The twistor equations arise naturally from the canonical normal Cartan connection of conformal geometry. Reductions of its holonomy are related to solutions of the normal t…

2004-06-16abs ↗pdf ↗

A new proof shows almost every normal to a smooth convex body intersects at least 6 normals from different points.

problem The conjecture about normals to convex bodies in high dimensions.
method Short proof of Y. Martinez-Maure's result for n3n \geq 3.
result Almost every normal through a boundary point intersects at least 6 normals from different points.