Related papers: Dynamic Cumulative Residual Entropy Generating Fun…
We propose Deep Residual Mixture Models (DRMMs), a novel deep generative model architecture. Compared to other deep models, DRMMs allow more flexible conditional sampling: The model can be trained once with all variables, and then used for…
We provide a theoretical analysis for end-to-end training Discrete Flow Matching (DFM) generative models. DFM is a promising discrete generative modeling framework that learns the underlying generative dynamics by training a neural network…
Stimulated by the need of describing useful notions related to information measures, we introduce the `pdf-related distributions'. These are defined in terms of transformation of absolutely continuous random variables through their own…
The penetration of distributed renewable energy (DRE) greatly raises the risk of distribution network operation such as peak shaving and voltage stability. Battery energy storage (BES) has been widely accepted as the most potential…
A common objective in the analysis of tabular data is estimating the conditional distribution (in contrast to only producing predictions) of a set of "outcome" variables given a set of "covariates", which is sometimes referred to as the…
We train a generative diffusion model (DM) to simulate ultra-relativistic heavy-ion collisions from end to end. The model takes initial entropy density profiles as input and produces two-dimensional final particle spectra, successfully…
The one-dimensional (1D) $t-J$ model is investigated using the density matrix renormalization group (DMRG) method. We report for the first time a generalization of the DMRG method to the case of arbitrary band filling and prove a theorem…
Regenerative braking energy is the energy produced by a train during deceleration. When a train decelerates, the motors act as generators and produce electricity. This energy can be fed back to the third rail and consumed by other trains…
In recent years, deep discrete representation learning (DRL) has achieved significant success across various domains. Most DRL frameworks (e.g., the widely used VQ-VAE and its variants) have primarily focused on generative settings, where…
We propose a generative model termed Deciphering Autoencoders. In this model, we assign a unique random dropout pattern to each data point in the training dataset and then train an autoencoder to reconstruct the corresponding data point…
The yielding of concentrated cohesive suspensions can be deformation-rate dependent. One consquence of this is that a single suspension can present in one several different ways, depending upon how it is tested, or more generally, how it is…
Extracting appropriate features to represent a corpus is an important task for textual mining. Previous attention based work usually enhance feature at the lexical level, which lacks the exploration of feature augmentation at the sentence…
We consider the drift and diffusion properties of periodically driven renewal processes. These processes are defined by a periodically time dependent waiting time distribution, which governs the interval between subsequent events. We show…
In this paper, we explore the potential of generative machine learning models as an alternative to the computationally expensive Monte Carlo (MC) simulations commonly used by the Large Hadron Collider (LHC) experiments. Our objective is to…
This article aims to introduced a new distribution named as extended xgamma (EXg) distribution. This generalization is derived from xgamma distribution (Xg), a special finite mixture of exponential and gamma distributions [see, Sen et al.…
Increasing penetration of distribution generation (DG) and electric vehicles (EVs) calls for an effective way to estimate the achievable capacity connected to the distribution systems, but the exogenous uncertainties of DG outputs and EV…
Multi-energy microgrid (MEMG) offers an effective approach to deal with energy demand diversification and new energy consumption on the consumer side. In MEMG, it is critical to deploy an energy management system (EMS) for efficient…
We study the problem of detecting the structure of a complex dynamical system described by a set of deterministic differential equation that contains a Hamiltonian subsystem, without any information on the explicit form of evolution laws.…
Weighted extropy has recently emerged as a flexible information measure for quantifying uncertainty, with particular relevance to order statistics. In this paper, we introduce and study a weighted cumulative analogue of extropy, extending…
The recent empirical correlation for the surface tension is further investigated for universality. C5-C8 liquid hydrocarbons, for which accurate surface tension data over the complete liquid range are available, are used. Functional reduced…