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.
ARCNPs improve CNPs by autoregressively modeling dependencies.
ARMA cell simplifies neural autoregressive modeling for time series.
Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers that the model uses internally when generating data. By constructing a stack of autoregressive models, each modelling th…
A new neural network for efficient density estimation.
We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task. We extensively evaluate the proposed model on machine…
Estimates causal effects using neural autoregressive density estimators.
Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based speech synthesis to 20x faster than real-time, via Inverse Autoregressive Flows (IAF). We unify a…
This work proposes an efficient autoregressive model for text generation.
We introduce Hyper-Conditioned Neural Autoregressive Flow (HCNAF); a powerful universal distribution approximator designed to model arbitrarily complex conditional probability density functions. HCNAF consists of a neural-net based conditional autoregressive flow (AF) and a hyper-network that can take large conditions …
New method estimates spin system mutual information using neural networks.
Normalising flows (NFS) map two density functions via a differentiable bijection whose Jacobian determinant can be computed efficiently. Recently, as an alternative to hand-crafted bijections, Huang et al. (2018) proposed neural autoregressive flow (NAF) which is a universal approximator for density functions. Their fl…
The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables. We propose a new type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast to earlier published flows, scales well to high-dimensional latent spaces. The proposed f…
Neural density estimators are flexible families of parametric models which have seen widespread use in unsupervised machine learning in recent years. Maximum-likelihood training typically dictates that these models be constrained to specify an explicit density. However, this limitation can be overcome by instead using …
NeLLoC improves image compression with parallel decoding.
Neural autoregressive models are explicit density estimators that achieve state-of-the-art likelihoods for generative modeling. The D-dimensional data distribution is factorized into an autoregressive product of one-dimensional conditional distributions according to the chain rule. Data completion is a more involved ta…
CTRNNs improve blood glucose forecasting in ICU, outperforming traditional models.
Paper proposes a neural network method for fast, interpretable AR model estimation.
BiGG model efficiently generates sparse graphs with reduced complexity.
Paper uses surprisal to dynamically allocate computation between fast and slow models.
Thermalizer stabilizes autoregressive models for long-term predictions in chaotic systems.
Efficiently combines autoregressive and set-based models for joint distributions.
Study reveals issues with neural autoregressive models and proposes mode recovery cost.
This work maps Boltzmann distributions to ARNNs for better physics-based model approximations.
This paper proposes CF-NADE, a neural autoregressive architecture for collaborative filtering (CF) tasks, which is inspired by the Restricted Boltzmann Machine (RBM) based CF model and the Neural Autoregressive Distribution Estimator (NADE). We first describe the basic CF-NADE model for CF tasks. Then we propose to imp…
EventFlow forecasts event sequences without autoregression, improving accuracy.
New method makes machine learning approximations unbiased and efficient.
Study finds optimal vocabulary size for neural machine translation.
In this paper, we consider a model called CHARME (Conditional Heteroscedastic Autoregressive Mixture of Experts), a class of generalized mixture of nonlinear nonparametric AR-ARCH time series. Under certain Lipschitz-type conditions on the autoregressive and volatility functions, we prove that this model is stationary,…
We present Sequential Neural Likelihood (SNL), a new method for Bayesian inference in simulator models, where the likelihood is intractable but simulating data from the model is possible. SNL trains an autoregressive flow on simulated data in order to learn a model of the likelihood in the region of high posterior dens…
Improved language generation with faster sampling speed.
Improved lattice field theory simulations with local-Autoregressive Conditional Normalizing Flow.
Identification of a groundwater contaminant source simultaneously with the hydraulic conductivity in highly-heterogeneous media often results in a high-dimensional inverse problem. In this study, a deep autoregressive neural network-based surrogate method is developed for the forward model to allow us to solve efficien…
Generative neural samplers estimate quantum spin system properties.
LMConv improves autoregressive models for image generation and completion.
A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the parameterization of an easily invertible elementwise transformation, whose choic…
PARNN improves ARNN with ARIMA feedback for accurate long-range forecasting.
Efficient methods for answering complex probabilistic queries in sequential data.
This review compares various deep generative models.
Improved simulation of phase transitions using hierarchical autoregressive networks.
Non-autoregressive translation (NAT) models remove the dependence on previous target tokens and generate all target tokens in parallel, resulting in significant inference speedup but at the cost of inferior translation accuracy compared to autoregressive translation (AT) models. Considering that AT models have higher a…
Vector autoregressive models characterize a variety of time series in which linear combinations of current and past observations can be used to accurately predict future observations. For instance, each element of an observation vector could correspond to a different node in a network, and the parameters of an autoregr…
We introduce the use of autoregressive normalizing flows for rapid likelihood-free inference of binary black hole system parameters from gravitational-wave data with deep neural networks. A normalizing flow is an invertible mapping on a sample space that can be used to induce a transformation from a simple probability …
ARTree uses deep learning to infer tree topologies efficiently.
Paper explores variable skipping to speed up range density estimation.
Single autoregressive model outperforms ensemble methods in offline reinforcement learning.
SALT models combine ARHMM and SLDS for efficient, interpretable time-series analysis.
Multivariate binary distributions can be decomposed into products of univariate conditional distributions. Recently popular approaches have modeled these conditionals through neural networks with sophisticated weight-sharing structures. It is shown that state-of-the-art performance on several standard benchmark dataset…
Graph neural networks improve volatility forecasts and portfolio performance.