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.
Improves spatio-temporal forecasting by reducing errors between training and inference.
The extension of image generation to video generation turns out to be a very difficult task, since the temporal dimension of videos introduces an extra challenge during the generation process. Besides, due to the limitation of memory and training stability, the generation becomes increasingly challenging with the incre…
An algorithm solves optimization problems with large sample sets, improving worst-case complexity.
We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial networks (GANs) are known for their ability to simulate random high-quality images, bu…
Temporal Functional Circuits explain KAN forecasts with interpretable edge functions.
Neurons predict future scalar inputs by learning top modes of lag vectors.
Satellite imagery helps assess sustainable development with machine learning.
We introduce a probabilistic generative model for disentangling spatio-temporal disease trajectories from series of high-dimensional brain images. The model is based on spatio-temporal matrix factorization, where inference on the sources is constrained by anatomically plausible statistical priors. To model realistic tr…
Develops a machine learning model to predict ALS progression and assistive device use.
Learning rich representation from data is an important task for deep generative models such as variational auto-encoder (VAE). However, by extracting high-level abstractions in the bottom-up inference process, the goal of preserving all factors of variations for top-down generation is compromised. Motivated by the conc…
The spatio-temporal graph learning is becoming an increasingly important object of graph study. Many application domains involve highly dynamic graphs where temporal information is crucial, e.g. traffic networks and financial transaction graphs. Despite the constant progress made on learning structured data, there is s…
Improved NODEs for long-term time series forecasting.
Rolling Diffusion improves video prediction by progressively corrupting frames based on their temporal position.
LHM integrates expert ODEs with neural ODEs for disease progression prediction.
We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes i…
Develops a new method to create object models from medical images.
HRTPP improves TPP interpretability and accuracy in medical event modeling.
Recent advances in deep generative models have lead to remarkable progress in synthesizing high quality images. Following their successful application in image processing and representation learning, an important next step is to consider videos. Learning generative models of video is a much harder task, requiring a mod…
Proposes a new tensor decomposition method for functional temporal data with adaptive complexity.
Recent progress in recommender system research has shown the importance of including temporal representations to improve interpretability and performance. Here, we incorporate temporal representations in continuous time via recurrent point process for a dynamical model of reviews. Our goal is to characterize how change…
In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action spaces to accelerate learning. We assume the environment is out of our control, but that the agent …
PaGoDA reduces diffusion model training costs by 64x.
Improves disease progression prediction using auxiliary surrogate labels and health markers.
Early recognition of abnormal rhythms in ECG signals is crucial for monitoring and diagnosing patients' cardiac conditions, increasing the success rate of the treatment. Classifying abnormal rhythms into exact categories is very challenging due to the broad taxonomy of rhythms, noises and lack of large-scale real-world…
SPF uses a hierarchical approach to efficiently emulate climate changes.
We present a generative autoencoder that provides fast encoding, faithful reconstructions (eg. retaining the identity of a face), sharp generated/reconstructed samples in high resolutions, and a well-structured latent space that supports semantic manipulation of the inputs. There are no current autoencoder or GAN model…
Recent works demonstrated the usefulness of temporal coherence to regularize supervised training or to learn invariant features with deep architectures. In particular, enforcing smooth output changes while presenting temporally-closed frames from video sequences, proved to be an effective strategy. In this paper we pro…
CoI framework models clinical feature interactions, revealing temporal dependencies and enhancing transparency.
A new autoencoder architecture captures multiscale data.
New framework predicts urban traffic with high accuracy.
CryptoGAT improves cryptocurrency price prediction by treating it as a graph problem.
Event-based models (EBM) are a class of disease progression models that can be used to estimate temporal ordering of neuropathological changes from cross-sectional data. Current EBMs only handle scalar biomarkers, such as regional volumes, as inputs. However, regional aggregates are a crude summary of the underlying hi…
BOSH optimizes functions with stochastic evaluations more efficiently and precisely.
KBB algorithm reduces sample complexity for policy evaluation in general state spaces.
On many social networking web sites such as Facebook and Twitter, resharing or reposting functionality allows users to share others' content with their own friends or followers. As content is reshared from user to user, large cascades of reshares can form. While a growing body of research has focused on analyzing and c…
Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed architectures have mostly been developed manually by human experts, whi…
This work designs an active world model learning system with progress-based curiosity.
The contradiction between physical and economical sciences concerning the growth of the production/consumption mechanism is analyzed. It is then shown that if one wishes to keep the security level stable or to enhance it in a growing economy the cost of security grows faster than the gross wealth. The result is a typic…
Recent progress in using recurrent neural networks (RNNs) for image description has motivated the exploration of their application for video description. However, while images are static, working with videos requires modeling their dynamic temporal structure and then properly integrating that information into a natural…
Modeling glucose distribution changes over time using neural ODEs.
Prognostics or early detection of incipient faults is an important industrial challenge for condition-based and preventive maintenance. Physics-based approaches to modeling fault progression are infeasible due to multiple interacting components, uncontrolled environmental factors and observability constraints. Moreover…
CARRNN tackles deep learning for sporadic data, improving prediction errors in healthcare.
Study compares deep learning models for volatility prediction using multivariate data.
This paper tackles sampling issues in latent space EBMs by introducing diffusion-based amortization.
Survey on learning models for irregularly sampled time series data.
Generative model identifies temporal count data components with regime-dependent contributions.
Comorbid diseases co-occur and progress via complex temporal patterns that vary among individuals. In electronic health records we can observe the different diseases a patient has, but can only infer the temporal relationship between each co-morbid condition. Learning such temporal patterns from event data is crucial f…
Algorithm learns stochastic system dynamics from data.