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 algorithm guarantees optimal convergence rate for stochastic optimization.
Recurrent-DBN models dynamic relational data with interpretable latent structures.
In a recurrent setting, conventional approaches to neural architecture search find and fix a general model for all data samples and time steps. We propose a novel algorithm that can dynamically search for the structure of cells in a recurrent neural network model. Based on a combination of recurrent and recursive neura…
Transformers can outperform feedforward and recurrent networks due to dynamic sparsity.
Unrolled neural networks emerged recently as an effective model for learning inverse maps appearing in image restoration tasks. However, their generalization risk (i.e., test mean-squared-error) and its link to network design and train sample size remains mysterious. Leveraging the Stein's Unbiased Risk Estimator (SURE…
New algorithm for robust circular coordinates in recurrent time series data.
Recurrent models can produce infinite sequences, causing bias; new methods prevent this.
Develops a method for causal inference in recurrent event data with terminal failure.
Scalable verifier for recurrent neural networks using polyhedral abstractions.
Recurrent neural networks are nowadays successfully used in an abundance of applications, going from text, speech and image processing to recommender systems. Backpropagation through time is the algorithm that is commonly used to train these networks on specific tasks. Many deep learning frameworks have their own imple…
New financial volatility models capture dynamic volatility better.
The verification problem for neural networks is verifying whether a neural network will suffer from adversarial samples, or approximating the maximal allowed scale of adversarial perturbation that can be endured. While most prior work contributes to verifying feed-forward networks, little has been explored for verifyin…
Survey on learning models for irregularly sampled time series data.
We propose a formulation for nonlinear recurrent models that includes simple parametric models of recurrent neural networks as a special case. The proposed formulation leads to a natural estimator in the form of a convex program. We provide a sample complexity for this estimator in the case of stable dynamics, where th…
In this paper we propose a model that combines the strengths of RNNs and SGVB: the Variational Recurrent Auto-Encoder (VRAE). Such a model can be used for efficient, large scale unsupervised learning on time series data, mapping the time series data to a latent vector representation. The model is generative, such that …
Method generates joint posterior samples of source and foreground mass distributions for gravitational lensing.
Study shows exponential gap in sample complexity between noisy and non-noisy recurrent neural networks.
New methods improve Reservoir Computing for chaotic time series prediction.
A deep-learning-based surrogate model is developed and applied for predicting dynamic subsurface flow in channelized geological models. The surrogate model is based on deep convolutional and recurrent neural network architectures, specifically a residual U-Net and a convolutional long short term memory recurrent networ…
This project was motivated by a dialysis study in northern Taiwan. Dialysis patients, after shunt implantation, may experience two types ("acute" or "non-acute") of shunt thrombosis, both of which may recur. We formulate the problem under the framework of recurrent events data in the presence of competing risks. In par…
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…
This paper presents the recurrent estimation of distributions (RED) for modeling real-valued data in a semiparametric fashion. RED models make two novel uses of recurrent neural networks (RNNs) for density estimation of general real-valued data. First, RNNs are used to transform input covariates into a latent space to …
A semi-recurrent hybrid VAE-GAN model for generating sequential data is introduced. In order to consider the spatial correlation of the data in each frame of the generated sequence, CNNs are utilized in the encoder, generator, and discriminator. The subsequent frames are sampled from the latent distributions obtained b…
TriTPP models enable faster and more flexible event data modeling.
The Teacher Forcing algorithm trains recurrent networks by supplying observed sequence values as inputs during training and using the network's own one-step-ahead predictions to do multi-step sampling. We introduce the Professor Forcing algorithm, which uses adversarial domain adaptation to encourage the dynamics of th…
It is widely believed that the practical success of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) owes to the fact that CNNs and RNNs use a more compact parametric representation than their Fully-Connected Neural Network (FNN) counterparts, and consequently require fewer training examples to…
New RNN model handles long-term dependencies in irregularly-sampled time series.
This paper uses ODE to improve RNN models for time series data.
Generative Adversarial Networks (GANs) have shown remarkable success as a framework for training models to produce realistic-looking data. In this work, we propose a Recurrent GAN (RGAN) and Recurrent Conditional GAN (RCGAN) to produce realistic real-valued multi-dimensional time series, with an emphasis on their appli…
Recurrent Neural Networks (RNNs) are among the most popular models in sequential data analysis. Yet, in the foundational PAC learning language, what concept class can it learn? Moreover, how can the same recurrent unit simultaneously learn functions from different input tokens to different output tokens, without affect…
RTRL optimizes long sequences without truncation, converging to loss minima.
Being able to predict the occurrence of extreme returns is important in financial risk management. Using the distribution of recurrence intervals---the waiting time between consecutive extremes---we show that these extreme returns are predictable on the short term. Examining a range of different types of returns and th…
Develops a more flexible HDP-HMM for temporal data segmentation.
A new approach learns to represent context for nonstationary bandits.
This paper tackles data-efficient nonlinear control in Hamiltonian systems using symplectic geometry.
We analyze generalization in deep learning models using random matrix theory.
Generative model uses recurrent neural networks to predict graph edges.
Develops a deep generative model for radar target recognition using HRRP data.
Model predicts COVID-19 spread with better accuracy than existing methods.
Dual neural network architecture improves accuracy and interpretability.
Study evaluates CL methods in RNNs, highlighting differences from feedforward networks.
Gradient descent optimally trains RNNs without overparameterization.
Study compares LSTM, Transformer, and Mamba for bladder cancer recurrence analysis.
RAN model recognizes multiple activities from unlabeled sensor data.
Frequentist method estimates uncertainty in RNNs without altering architecture.
Boost-R uses gradient boosted trees for analyzing recurrence data.
Leveraging advances in variational inference, we propose to enhance recurrent neural networks with latent variables, resulting in Stochastic Recurrent Networks (STORNs). The model i) can be trained with stochastic gradient methods, ii) allows structured and multi-modal conditionals at each time step, iii) features a re…
Learning to predict solutions to real-valued combinatorial graph problems promises efficient approximations. As demonstrated based on the NP-hard edge clique cover number, recurrent neural networks (RNNs) are particularly suited for this task and can even outperform state-of-the-art heuristics. However, the theoretical…