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.
A new neural network for efficient density estimation.
ARMA cell simplifies neural autoregressive modeling for time series.
New method estimates spin system mutual information using neural networks.
New method makes machine learning approximations unbiased and efficient.
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…
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 …
Paper uses surprisal to dynamically allocate computation between fast and slow models.
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 paper develops a learning theory for neural network-based CHARME models.
Paper proposes a neural network method for fast, interpretable AR model estimation.
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…
Improved simulation of phase transitions using hierarchical autoregressive networks.
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…
CTRNNs improve blood glucose forecasting in ICU, outperforming traditional models.
This work maps Boltzmann distributions to ARNNs for better physics-based model approximations.
Neural networks improve gravitational-wave parameter estimation.
PARNN improves ARNN with ARIMA feedback for accurate long-range forecasting.
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 …
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…
Proposes DCNAR for dynamic causal inference from neural time series.
Monotonic neural networks have recently been proposed as a way to define invertible transformations. These transformations can be combined into powerful autoregressive flows that have been shown to be universal approximators of continuous probability distributions. Architectures that ensure monotonicity typically enfor…
Long short-term memory network outperforms seasonal model in JSE Top 40 forecasting.
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.
Generative Adversarial Graph Neural Network (Sig-Graph GAN) models financial time series data.
This review compares various deep generative models.
LMConv improves autoregressive models for image generation and completion.
We propose a general framework for solving statistical mechanics of systems with finite size. The approach extends the celebrated variational mean-field approaches using autoregressive neural networks, which support direct sampling and exact calculation of normalized probability of configurations. It computes variation…
ARMA nets expand receptive fields for dense prediction tasks.
Tensor networks improve unsupervised learning performance.
Any discussion on exchange rate movements and forecasting should include explanatory variables from both the current account and the capital account of the balance of payments. In this paper, we include such factors to forecast the value of the Indian rupee vis a vis the US Dollar. Further, factors reflecting political…
Improved lattice field theory simulations with local-Autoregressive Conditional Normalizing Flow.
ARTree uses deep learning to infer tree topologies efficiently.
EventFlow forecasts event sequences without autoregression, improving accuracy.
Efficiently combines autoregressive and set-based models for joint distributions.
We introduce a deep, generative autoencoder capable of learning hierarchies of distributed representations from data. Successive deep stochastic hidden layers are equipped with autoregressive connections, which enable the model to be sampled from quickly and exactly via ancestral sampling. We derive an efficient approx…
We propose a method for solving statistical mechanics problems defined on sparse graphs. It extracts a small Feedback Vertex Set (FVS) from the sparse graph, converting the sparse system to a much smaller system with many-body and dense interactions with an effective energy on every configuration of the FVS, then learn…
CARRNN tackles deep learning for sporadic data, improving prediction errors in healthcare.
Transformers become faster by linearizing self-attention.
Estimates causal effects using neural autoregressive density estimators.
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our method masks the autoencoder's parameters to respect autoregressive constraints: ea…
SXL embeds spatial autocorrelation into neural networks for better geographic data learning.
ARCNPs improve CNPs by autoregressively modeling dependencies.
We present a method for feature interpretation that makes use of recent advances in autoregressive density estimation models to invert model representations. We train generative inversion models to express a distribution over input features conditioned on intermediate model representations. Insights into the invariance…
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…
Traffic flow forecasting is hot spot research of intelligent traffic system construction. The existing traffic flow prediction methods have problems such as poor stability, high data requirements, or poor adaptability. In this paper, we define the traffic data time singularity ratio in the dropout module and propose a …
Convolutional Neural Processes improve data efficiency in neural processes.
Study finds optimal vocabulary size for neural machine translation.