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.

168,742 papers · 148 categories

Trend · papers per month

50100149199 · Jun 202019922001200920172026
48 results for Bits-per-dimension metric

We propose a new way of constructing invertible neural networks by combining simple building blocks with a novel set of composition rules. This leads to a rich set of invertible architectures, including those similar to ResNets. Inversion is achieved with a locally convergent iterative procedure that is parallelizable …

2019-07-18abs ↗pdf ↗

Paper proves existence of a universal codebook for low-precision quantization.

problem Optimizing low-precision approximation of matrix products in machine learning.
method Develops a universal codebook that is near-optimal for all possible statistics of input data.
result Proves existence of a universal codebook with a 0.11 bit per dimension reduction in rate.

MsIGN tackles high-dimensional Bayesian inference using multiscale structure.

problem High-dimensional Bayesian inference challenges due to the curse of dimensionality.
method MsIGN generates samples from coarse to fine scale, minimizing Jeffreys divergence.
result MsIGN outperforms previous approaches in posterior approximation and mode capture.

This paper introduces methods to handle discrete data by dequantization.

problem Handling discrete data in deep learning models.
method Dequantization framework, including importance-weighted and Rényi dequantization objectives, and autoregressive dequantization.
result Improved performance on uniform dequantization distributions and state-of-the-art negative log-likelihood on CIFAR10.

i-DenseNets improve parameter efficiency and performance in density estimation.

problem Improving parameter efficiency and performance in density estimation models.
method Invertible Dense Networks (i-DenseNets) with learnable weighted concatenation and Concatenated LipSwish activation function.
result i-DenseNets outperform Residual Flows and other flow-based models in bits per dimension.

Improved autoregressive models generate higher quality images and are more robust to noise.

problem Generating high-quality images from autoregressive models.
method Noise conditional maximum likelihood estimation (MLE) with score-based sampling.
result Models trained with noise conditional MLE achieve better test likelihoods and generate higher quality images.

VFlow enhances generative flows by augmenting data dimensions for better expressiveness.

problem Tractable generative flows have limited expressiveness due to fixed intermediate dimensions.
method Augment data with extra dimensions and learn a generative flow for both original and augmented data using variational inference.
result VFlow achieves state-of-the-art performance on CIFAR-10 with improved compactness.

Simplified masked diffusion models improve discrete data generation.

problem Complex model formulations and unclear relationships hinder discrete data generative modeling.
method Developed a simple and general framework for masked diffusion models.
result Models trained on OpenWebText surpass prior diffusion language models and outperform autoregressive models.

NVAE improves VAE performance on large image datasets.

problem Improving variational autoencoder performance for large image datasets.
method Deep hierarchical VAE with depth-wise separable convolutions and batch normalization, residual parameterization of Normal distributions, and spectral regularization.
result NVAE achieves state-of-the-art results on MNIST, CIFAR-10, CelebA 64, and CelebA HQ datasets.

In this essay, we study the sufficient and necessary conditions for a Randers metrc to be of constant Ricci curvature without the restriction of strong convexity (regularity). The classification result for the case βα>1\|β\|_α>1 is provided, which is similar to the famous Bao-Robles-Shen's result for strongly convex Rand…

2017-05-31abs ↗pdf ↗

We prove the equivalences of several classical complete metrics on the Teichmüller and the moduli spaces of Riemann surfaces. We use as bridge two new Kähler metrics, the Ricci metric and the perturbed Ricci metric and prove that the perturbed Ricci metric is a complete Kähler metric with bounded negative holomorphic s…

2004-03-03abs ↗pdf ↗

Study on geodesics of Finsler metrics derived from Riemannian metrics.

problem Investigating geodesics in Finsler metrics derived from Riemannian metrics.
method Proved geodesic lemma for a family of Riemannian geodesic orbit metrics, analyzed geodesic graphs.
result Derived Finsler metrics have geodesic orbit property and belong to a new class of metrics.

New Kähler metrics generalize Calabi's and relate to Fano manifolds.

problem Existence of extremal Kähler metrics on Fano manifolds.
method Introducing σσ-extremal Kähler metrics and relating them to multiplier Hermitian-Einstein metrics.
result Existence of σσ-extremal Kähler metrics implies existence of multiplier Hermitian-Einstein metrics on Fano manifolds.

New Finsler metrics defined by Riemannian and 1-forms are studied.

problem Characterize and study properties of (α,β,γ)(α,β,γ)-metrics.
method Introduced and defined (α,β,γ)(α,β,γ)-metrics, analyzed their properties, and found conditions for local projective flatness and Douglas type.
result Necessary and sufficient conditions for (α,β,γ)(α,β,γ)-metrics to be locally projectively flat and Douglas type were found.

Study on special Finsler metrics with conditions for Riemannian and isotropic properties.

problem Characterizing Finsler metrics with specific geometric properties.
method Analyzing conditions for Riemannian and isotropic properties of AR-Finsler metrics.
result Conditions for isotropic SS-curvature and mean Landsberg curvature leading to vanishing curvature.

Survey of spectral, probabilistic, and deep metric learning methods.

problem Developing effective distance metrics for various machine learning tasks.
method Divided into spectral, probabilistic, and deep approaches, covering various techniques and their applications.
result Comprehensive overview of metric learning methods, including new developments and applications.

Study shows convergence of Lagrangian submanifolds under certain metrics.

problem Understanding convergence of Lagrangian submanifolds under specific metrics.
method Proves convergence to an embedded Lagrangian submanifold using a monotonicity lemma applied on a carefully-chosen metric ball.
result Convergence to an embedded Lagrangian submanifold implies convergence in the Hausdorff metric for a class of metrics.

In this paper, we study an important class of Finsler metrics--square metrics. We give two expressions of such metrics in terms of a Riemannian metric and a 1-form. We show that Einstein square metrics can be classified up to the classification of Einstein Riemannian metrics.

2012-09-18abs ↗pdf ↗

The current paper deals with some new classes of Finsler metrics with reversible geodesics. We construct weighted quasi-metrics associated with these metrics. Further, we investigate some important geometric properties of weighted quasi-metric space. Finally, we discuss the embedding of quasi-metric spaces with general…

2018-01-17abs ↗pdf ↗

Douglas metrics are metrics with vanishing Douglas curvature which is an important projective invariant in Finsler geometry. To find more Douglas metrics, in this paper we consider a class of Finsler metrics called general (α,β)(α,β)-metrics, which are defined by a Riemannian metric α=aij(x)yiyjα=\sqrt{a_{ij}(x)y^iy^j} and a 11-fo…

2016-06-26abs ↗pdf ↗

Proposes a method to select fair performance metrics through metric elicitation.

problem Choosing fair performance metrics in multiclass classification with multiple sensitive groups.
method Metric elicitation strategy that requires only relative preference feedback and is robust to noise.
result Elicits group-fair performance metrics for multiclass classification problems.

In this paper, we introduce the notion of Einstein-reversibility for Finsler met- rics. We study a class of p-power Finsler metrics determined by a Riemann metric and 1-form which are of Einstein-reversibility. It shows that such a class of Finsler metrics of Einstein-reversibility are always Einstein metrics. In parti…

2013-10-13abs ↗pdf ↗

In this paper, we give two classes of positive semi-definite metrics on 2-manifolds. The one is called a class of Kossowski metrics and the other is called a class of Whitney metrics: The pull-back metrics of wave fronts which admit only cuspidal edges and swallowtails in R3\boldsymbol{R}^3 are Kossowski metrics, and t…

2014-09-01abs ↗pdf ↗

Introduces new metric for Riemannian metrics, extending unbalanced optimal transport.

problem Extending unbalanced optimal transport to Riemannian metrics.
method Dynamic and static formulations of unbalanced optimal transport on Riemannian metrics.
result Wasserstein--Ebin metric provides a new Riemannian structure on the space of Riemannian metrics.

In this paper, we study generalized Douglas-Weyl (α,β)(α, β)-metrics. Suppose that an regular (α,β)(α, β)-metric FF is not of Randers type. We prove that FF is a generalized Douglas-Weyl metric with vanishing S-curvature if and only if it is a Berwald metric. Moreover by ignoring the regularity, if FF is not a Berwald met…

2015-10-26abs ↗pdf ↗

The paper introduces two new metrics on outer space and shows fixed points for their actions.

problem Analyzing metrics on outer space and their geometric group theory implications.
method Defined and analyzed entropy and pressure metrics on outer space, comparing to Weil-Petersson metric.
result For rank r4r \geq 4, the metrics have fixed points in their actions on outer space.

Given any two Einstein (pseudo-)metrics, with scalar curvatures suitably related, we give an explicit construction of a Poincaré-Einstein (pseudo-)metric with conformal infinity the conformal class of the product of the initial metrics. We show that these metrics are equivalent to ambient metrics for the given conforma…

2006-08-02abs ↗pdf ↗

Paper shows regions close to negatively curved metrics are minimal fillings and rigid.

problem Boundary rigidity and minimality of metrics near negatively curved ones.
method Generalizes previous work on filling volume minimality and boundary rigidity for almost hyperbolic metrics.
result Regions with metrics close to a negatively curved symmetric metric are strict minimal fillings and boundary rigid.

In this note, we consider two Riemannian metrics on a moduli space of metric graphs. Each of them could be thought of as an analogue of the Weil-Petersson metric on the moduli space of metric graphs. We discuss and compare geometric features of these two metrics with the "classic" Weil-Petersson metric in Teichmüller t…

2016-04-11abs ↗pdf ↗