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.

168,657 papers · 148 categories

Trend · papers per month

2585167731,031 · Jun 202019922001200920172026
48 results for recurrent mixture density networks

Gaining a better understanding of how and what machine learning systems learn is important to increase confidence in their decisions and catalyze further research. In this paper, we analyze the predictions made by a specific type of recurrent neural network, mixture density RNNs (MD-RNNs). These networks learn to model…

2019-01-23abs ↗pdf ↗

The study applies spatial density models to mobile node movements using Möbius distributions.

problem Modeling the steady-state density of mobile nodes on a 2D terrain.
method Used mixture density networks with Möbius distributions to describe node density over a disk.
result Möbius distributions are more suitable for capturing radial changes in node density compared to Gaussian distributions.

Although Recurrent Neural Network (RNN) has been a powerful tool for modeling sequential data, its performance is inadequate when processing sequences with multiple patterns. In this paper, we address this challenge by introducing a novel mixture layer and constructing an adaptive RNN. The mixture layer augmented RNN (…

2018-01-24abs ↗pdf ↗

Generalizes memory and forecasting capacities for nonlinear recurrent networks with dependent inputs.

problem Understanding memory and forecasting capabilities in networks with dependent inputs.
method Formulated bounds for memory and forecasting capacities in terms of network size and input properties.
result Proved that memory capacity for linear recurrent networks with independent inputs is given by the rank of the controllability matrix.

Paper improves speech separation by using deep neural networks for more accurate density priors.

problem Improving the accuracy of source priors for independent vector analysis in speech separation.
method Estimating the derivative of speech density using deep neural networks to optimize performance indices.
result Neural network density priors outperform previous ones in convergence speed and SIR.

Generative model prices basket options efficiently.

problem Real-time pricing of basket options with varying market inputs.
method Truncated path signatures and Mixture Density Networks (MDN) for learning the terminal density.
result The model produces small pricing errors and matches Monte Carlo simulations closely.

The paper introduces a new method for multivariate density estimation using deep neural mixture models.

problem Multivariate density estimation is a fundamental but underexplored task in machine learning.
method The paper extends Neural Mixture Densities (NMMs) to multivariate Deep Neural Mixture Models (DNMMs) using maximum-likelihood algorithm.
result The DNMMs can model any probability density function to any degree of precision and outperform traditional statistical estimation techniques.

Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem. Bayesian neural networks are one of the most popular approaches to uncertainty quantification. On the other hand, it was recently shown that ensembles of NNs, which belo…

2019-02-04abs ↗pdf ↗

Paper uses GMM and MAF for probabilistic classification, outperforming simpler models.

problem Classifying data with complex distributions.
method Density estimation using Gaussian Mixture Model and Masked Autoregressive Flow.
result Proposed classifiers outperform simpler models like linear discriminant analysis.

LSTM-MDNs improve risk forecasting during turbulent periods.

problem Forecasting Value-at-Risk (VaR) during volatile market conditions.
method Implemented Long Short-Term Memory mixture density networks (LSTM-MDNs) for VaR forecasting and compared them with established models.
result LSTM-MDNs outperformed benchmark models in turbulent periods but not in calm periods.

The two most extended density-based approaches to clustering are surely mixture model clustering and modal clustering. In the mixture model approach, the density is represented as a mixture and clusters are associated to the different mixture components. In modal clustering, clusters are understood as regions of high d…

2016-09-15abs ↗pdf ↗

Generative Adversarial Networks have surprising ability for generating sharp and realistic images, though they are known to suffer from the so-called mode collapse problem. In this paper, we propose a new GAN variant called Mixture Density GAN that while being capable of generating high-quality images, overcomes this p…

2018-10-31abs ↗pdf ↗

Bayesian geoacoustic inversion improved using MDN.

problem Efficiently solving Bayesian geoacoustic inversion problems.
method Deriving geoacoustic statistics from multidimensional posterior density using MDN, training the network on the whole parameter space.
result The network provides reliable predictions and good generalization performance, solving problems in seconds.

We introduce RNADE, a new model for joint density estimation of real-valued vectors. Our model calculates the density of a datapoint as the product of one-dimensional conditionals modeled using mixture density networks with shared parameters. RNADE learns a distributed representation of the data, while having a tractab…

2013-06-02abs ↗pdf ↗

Conditional diffusion models can approximate target distributions well with Gaussian-mixture reverse kernels.

problem Approximating target distributions in conditional diffusion models.
method Using finite Gaussian mixtures with ReLU-network logits as reverse kernels, reducing the problem to static conditional density approximation.
result The resulting neural reverse-kernel class is dense in conditional KL divergence under exact terminal matching.

Study compares MoE and RNN models for stock price prediction across volatility profiles.

problem Improving stock price prediction accuracy across different volatility levels.
method Dynamic Mixture of Experts model combining RNN and linear models, adjusting weights through a gating network.
result MoE model outperforms individual models in reducing prediction errors.

A neural network method estimates densities from characteristic functions.

problem Estimating fixed-horizon probability densities from empirical characteristic functions.
method Data-driven Fourier-mixture neural-network method trained in Fourier space.
result Competitive performance and clear gains on heavy-tailed targets.

Study improves stock price prediction using adaptive Mixture of Experts framework.

problem Tackles diverse volatility regimes in stock price prediction.
method Combines RNN for high-volatility stocks and linear regression for stable stocks with a gating mechanism.
result Achieves up to 33% improvement in MSE for volatile assets and 28% for stable assets.

RFN models urban mobility demand by separating temporal and spatial variability.

problem Aligning supply and demand in MoD systems for efficient transportation.
method Recurrent flow networks with latent variables and normalizing flows.
result RFN models explicitly disentangle temporal and spatial variability in urban mobility.

The paper proposes a method for interpretable mixture density estimation using a tree structure.

problem Complex probability distributions in machine learning models.
method Interpretable tree structure for mixture density estimation with fast inference.
result The method achieves both high speed and interpretability for mixture density estimation.

MD-CGAN models forecast time series with probabilistic posterior distributions.

problem Limited applications of GANs in time series forecasting, especially with probabilistic predictions.
method Mixture Density Conditional Generative Adversarial Model (MD-CGAN) using Gaussian mixture output.
result MD-CGAN outperforms benchmarks, especially in noisy time series.

A new model combines normalizing flows with mixture components for better density estimation.

problem Lack of explicit probability density functions in deep generative models.
method Variational mixture of normalizing flows, using variational inference and neural network parameters.
result The model can perform density estimation, semi-supervised learning, and clustering.

Proposes deep mixture models for probabilistic price movement forecasting in high-frequency trading.

problem Probabilistic forecasting of price movements in high-frequency trading.
method Deep recurrent neural networks with probabilistic mixture models.
result Outperforms benchmark models in both metric-based and simulated trading scenarios.

Stochastic recurrent neural networks with latent random variables of complex dependency structures have shown to be more successful in modeling sequential data than deterministic deep models. However, the majority of existing methods have limited expressive power due to the Gaussian assumption of latent variables. In t…

2019-10-28abs ↗pdf ↗

Regularized mixtures improve inflation and interest rate forecasts, especially correcting overconfidence.

problem Improving density forecasts of Eurozone inflation and real interest rates.
method Construct regularized mixtures of density forecasts with various objectives and penalties.
result Regularized mixtures outperform individual forecasters, especially correcting overconfidence.

The paper analyzes how a known density function can be deviated by a mixture distribution as more data is collected.

problem Modeling the deviation of a known density function when more data is collected.
method A novel distinguishability notion is used to establish rates of convergence for maximum likelihood estimates of the deviated proportion and latent mixing measure.
result Rates of convergence for the maximum likelihood estimates of the deviated proportion and latent mixing measure are established under the Wasserstein metric.

The Fisher information metric is an important foundation of information geometry, wherein it allows us to approximate the local geometry of a probability distribution. Recurrent neural networks such as the Sequence-to-Sequence (Seq2Seq) networks that have lately been used to yield state-of-the-art performance on speech…

2017-10-25abs ↗pdf ↗

New deep learning model estimates scattering timescale of FRBs efficiently.

problem Estimating scattering timescale of fast radio bursts (FRBs) is a bottleneck.
method Multimodal Transformer Based Generic Mixture Density Network (MT-GMDN) that ingests dynamic spectrum and timeseries profile.
result Achieves 94% R2R^2 on expected value of ττ for measurable scattering.

GGMPs improve non-Gaussian conditional density estimation.

problem Multimodality, heteroscedasticity, and strong non-Gaussianity in conditional density estimation.
method GGMP combines local Gaussian mixture fitting, cross-input component alignment, and per-component heteroscedastic GP training.
result GGMPs improve distributional approximation on synthetic and real-world datasets.

This paper studies sparse density estimation via 1\ell_1 penalization (SPADES). We focus on estimation in high-dimensional mixture models and nonparametric adaptive density estimation. We show, respectively, that SPADES can recover, with high probability, the unknown components of a mixture of probability densities an…

2009-01-14abs ↗pdf ↗