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.
New analysis explains pathology of deep Gaussian processes.
New DRGP models improve prediction accuracy for sequential data.
This paper improves speech synthesis using a DGP with SRU for naturalness.
Unified theory for deep and recurrent networks using Gaussian processes.
Modeling sequential data has become more and more important in practice. Some applications are autonomous driving, virtual sensors and weather forecasting. To model such systems so called recurrent models are used. In this article we introduce two new Deep Recurrent Gaussian Process (DRGP) models based on the Sparse Sp…
We define Recurrent Gaussian Processes (RGP) models, a general family of Bayesian nonparametric models with recurrent GP priors which are able to learn dynamical patterns from sequential data. Similar to Recurrent Neural Networks (RNNs), RGPs can have different formulations for their internal states, distinct inference…
Many applications in speech, robotics, finance, and biology deal with sequential data, where ordering matters and recurrent structures are common. However, this structure cannot be easily captured by standard kernel functions. To model such structure, we propose expressive closed-form kernel functions for Gaussian proc…
A new memory-efficient sign language translation model reduces weight usage.
Proposes a new model for time-to-event prediction with uncertainty quantification.
Gaussian processes are the leading class of distributions on random functions, but they suffer from well known issues including difficulty scaling and inflexibility with respect to certain shape constraints (such as nonnegativity). Here we propose Deep Random Splines, a flexible class of random functions obtained by tr…
A novel online GP model captures long-term memory in sequential data.
Time series analysis is a key component of machine learning, with applications in various fields.
We present a personalized and reliable prediction model for healthcare, which can provide individually tailored medical services such as diagnosis, disease treatment, and prevention. Our proposed framework targets at making personalized and reliable predictions from time-series data, such as Electronic Health Records (…
This work introduces a new model for complex stochastic processes.
Recursive KalmanNet combines neural networks with Kalman filters for precise state estimation.
In this paper, we show that the recent integration of statistical models with deep recurrent neural networks provides a new way of formulating volatility (the degree of variation of time series) models that have been widely used in time series analysis and prediction in finance. The model comprises a pair of complement…
Study Gaussian-process limits of neural networks using tensor programs.
Reliable 4D aircraft trajectory prediction, whether in a real-time setting or for analysis of counterfactuals, is important to the efficiency of the aviation system. Toward this end, we first propose a highly generalizable efficient tree-based matching algorithm to construct image-like feature maps from high-fidelity m…
SIS-RNN improves model flexibility for sequential data.
TransformerLSR models longitudinal, recurrent, and survival data jointly.
We propose stochastic, non-parametric activation functions that are fully learnable and individual to each neuron. Complexity and the risk of overfitting are controlled by placing a Gaussian process prior over these functions. The result is the Gaussian process neuron, a probabilistic unit that can be used as the basic…
Deep Gaussian Processes with polynomial kernels can collapse rapidly without proper hyperparameter tuning.
Left atrium shape has been shown to be an independent predictor of recurrence after atrial fibrillation (AF) ablation. Shape-based representation is imperative to such an estimation process, where correspondence-based representation offers the most flexibility and ease-of-computation for population-level shape statisti…
In recent years, China, the United States and other countries, Google and other high-tech companies have increased investment in artificial intelligence. Deep learning is one of the current artificial intelligence research's key areas. This paper analyzes and summarizes the latest progress and future research direction…
A new model uses attention and Gaussian processes for efficient time-series generation.
Deep models predict intraday electricity prices accurately.
We propose deep convolutional Gaussian processes, a deep Gaussian process architecture with convolutional structure. The model is a principled Bayesian framework for detecting hierarchical combinations of local features for image classification. We demonstrate greatly improved image classification performance compared …
Long-lead forecasting for spatio-temporal systems can often entail complex nonlinear dynamics that are difficult to specify it a priori. Current statistical methodologies for modeling these processes are often highly parameterized and thus, challenging to implement from a computational perspective. One potential parsim…
Develops a deep non-stationary kernel for non-stationary spatio-temporal point processes.
VSE estimates complex processes from noisy measurements without a model.
The extension of deep learning towards temporal data processing is gaining an increasing research interest. In this paper we investigate the properties of state dynamics developed in successive levels of deep recurrent neural networks (RNNs) in terms of short-term memory abilities. Our results reveal interesting insigh…
We extend Neural Processes (NPs) to sequential data through Recurrent NPs or RNPs, a family of conditional state space models. RNPs model the state space with Neural Processes. Given time series observed on fast real-world time scales but containing slow long-term variabilities, RNPs may derive appropriate slow latent …
Deep neural networks and Gaussian processes are shown to be equivalent through activation functions.
Predicting business process behaviour is an important aspect of business process management. Motivated by research in natural language processing, this paper describes an application of deep learning with recurrent neural networks to the problem of predicting the next event in a business process. This is both a novel m…
Deep-HGP uses Bayesian nonparametric approach for complex data regression.
Efficiently trains deep Gaussian processes with sparse approximations.
Survey on Gaussian processes and their deep variants.
Deep Transformed Gaussian Processes extend TGPs with variational inference for scalable multi-layer modeling.
Inter-domain Deep Gaussian Processes improve inference for non-stationary data.
Gaussian processes struggle with compositional functions, but deep Gaussian processes can outperform.
We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian processes is the warping of inputs through infinitely deep, but infinitesimal, diff…
The paper studies deep neural networks with Gaussian weights and finds their asymptotic behavior.
Bayesian time series forecasting improves by dynamically adapting to recent information.
Whilst deep neural networks have shown great empirical success, there is still much work to be done to understand their theoretical properties. In this paper, we study the relationship between random, wide, fully connected, feedforward networks with more than one hidden layer and Gaussian processes with a recursive ker…
dynoGP uses deep Gaussian processes for dynamic system identification.
Scalable machine learning with path signatures for time series and graphs.
Paper develops deep models for forecasting intermittent demand.
Latent dynamics discovery is challenging in extracting complex dynamics from high-dimensional noisy neural data. Many dimensionality reduction methods have been widely adopted to extract low-dimensional, smooth and time-evolving latent trajectories. However, simple state transition structures, linear embedding assumpti…