arXiv research

A new test detects differences between two distributions without flow.

In a previous analysis the problem of "zero-inflated" time data (caused by high frequency trading in the electronic order book) was handled by left-truncating the inter-arrival times. We demonstrated, using rigorous statistical methods, that the Weibull distribution describes the corresponding stochastic dynamics for a…

Gradient descent struggles to achieve zero loss in deep learning models due to non-generic data distributions.

The paper addresses score-mismatched diffusion models and zero-shot conditional samplers.

Deep model tackles zero-inflated multi-species abundance estimation.

In finance, durations between successive transactions are usually modeled by the autoregressive conditional duration model based on a continuous distribution omitting zero values. Zero or close-to-zero durations can be caused by either split transactions or independent transactions. We propose a discrete model allowing…

Study on convergence of Langevin dynamics for zero-sum games in probability distributions.

New bandit algorithms improve sparse reward learning.

Proposes a method to handle sparse multiway count data with false zeros using zero-truncated Poisson regression.

Paper proposes copula-based models for analyzing multivariate zero-inflated continuous data.

We present a domain adaptation based generative framework for zero-shot learning. Our framework addresses the problem of domain shift between the seen and unseen class distributions in zero-shot learning and minimizes the shift by developing a generative model trained via adversarial domain adaptation. Our approach is …

We consider the problem of selecting non-zero entries of a matrix $A$ in order to produce a sparse sketch of it, $B$, that minimizes $\|A-B\|_2$. For large $m \times n$ matrices, such that $n \gg m$ (for example, representing $n$ observations over $m$ attributes) we give sampling distributions that exhibit four importa…

Zero-shot anomaly detection method using batch normalization.

Gradient descent learns ReLU functions with non-zero bias efficiently.

Study Bergman kernels and zero distributions of random sections on Kähler manifolds.

Proposes a new model to predict travel demand with zero-inflated and long-tail characteristics.

The paper studies Fubini-Study metrics and zero distributions on CR manifolds.

We review a simple model of closed economy, where the economic agents make money transactions and a saving criterion is present. We observe the Gibbs distribution for zero saving propensity, and non-Gibbs distributions otherwise. While the exact solution in the case of zero saving propensity is already known to be give…

New ZIPLN model accounts for zero-inflation in multivariate count data.

KSG mutual information estimator, which is based on the distances of each sample to its k-th nearest neighbor, is widely used to estimate mutual information between two continuous random variables. Existing work has analyzed the convergence rate of this estimator for random variables whose densities are bounded away fr…

We study the shapes of the implied volatility when the underlying distribution has an atom at zero and analyse the impact of a mass at zero on at-the-money implied volatility and the overall level of the smile. We further show that the behaviour at small strikes is uniquely determined by the mass of the atom up to high…

This thesis predicts the distribution of smoothed zeros of random sections on line bundles.

The study reveals a persistent bias in the distribution of holonomy on compact hyperbolic 3-manifolds.

Study of Alexander polynomials of torus knots and links, showing zeros equidistribute on unit circle.

Paper introduces zero-space memory protection for CNNs without ECC overhead.

We analyze the data on personal income distribution from the Australian Bureau of Statistics. We compare fits of the data to the exponential, log-normal, and gamma distributions. The exponential function gives a good (albeit not perfect) description of 98% of the population in the lower part of the distribution. The lo…

We present a rigorous homogenization theorem for distributed dislocations. We construct a sequence of locally-flat Riemannian manifolds with dislocation-type singularities. We show that this sequence converges, as the dislocations become denser, to a flat non-singular Weitzenböck manifold, i.e. a flat manifold endowed …

In this paper, we study distribution of the zeros of the Alexander polynomials of knots and links in S^3. We call a knot or link "real stable" (resp. "circular stable") if all the zeros of its Alexander polynomial are real (resp. unit complex). We give a general construction of real stable and circular stable knots and…

Bayesian method improves extreme quantile estimation with zero coverage error.

We estimate generic statistical properties of a structural credit risk model by considering an ensemble of correlation matrices. This ensemble is set up by Random Matrix Theory. We demonstrate analytically that the presence of correlations severely limits the effect of diversification in a credit portfolio if the corre…

Adversarial training achieves optimal test error for shallow networks.

Paper introduces a flow-based framework for representation learning.

New method uncovers zero entropy in dependent observations after finite samples.

The study connects projective codes to the distribution of zeros of odd maps.

The M5 competition tackles overdispersed retail sales forecasting with GAMLSS.

In this work we prove an universality result regarding the equidistribution of zeros of random holomorphic sections associated to a sequence of singular Hermitian holomorphic line bundles on a compact Kähler complex space $X$. Namely, under mild moment assumptions, we show that the asymptotic distribution of zeros of r…

We present a simple generative framework for learning to predict previously unseen classes, based on estimating class-attribute-gated class-conditional distributions. We model each class-conditional distribution as an exponential family distribution and the parameters of the distribution of each seen/unseen class are d…

New connections found on zero-mean multivariate normal distributions.

A new algorithm optimizes softmax units in large language models.

A new method for distributed optimization with noisy function evaluations.

A new model synthesizes population with fewer structural and sampling zeros.

Modular neural causal models outperform other models in generalization and adaptation.

Bayesian model for discrete data with conditional transformations.

Non-parallel many-to-many voice conversion, as well as zero-shot voice conversion, remain under-explored areas. Deep style transfer algorithms, such as generative adversarial networks (GAN) and conditional variational autoencoder (CVAE), are being applied as new solutions in this field. However, GAN training is sophist…

It is well known that the distribution of returns from various financial instruments are leptokurtic, meaning that the distributions have "fatter tails" than a Normal distribution, and have skew toward zero. This paper presents a graceful micro-level explanation for such fat-tailed outcomes, using agents whose private …

Alternative model predicts health insurance reimbursement based on contract limitations.

Study finds a limiting distribution for free path lengths on flat surfaces with circular obstacles.

MixFT re-partitions data into sub-domains for better TSFM fine-tuning.