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.
Derives time-averaged active inference from control principles.
Deep learning models outperform classical methods in forecasting neural activity.
New activation function BrownianReLU improves LSTM network performance on financial time series.
Generative model predicts daily activity sequences with duration-aware dynamics.
Safe active learning for time-series models with Gaussian processes.
In the work, a comparative correlation and fractal analysis of time series of Bitcoin crypto currency rate and community activities in social networks associated with Bitcoin was conducted. A significant correlation between the Bitcoin rate and the community activities was detected. Time series fractal analysis indicat…
Machine learning predicts COVID-19 activity in China.
GPRNs accurately model stellar activity affecting RV measurements of exoplanets.
Polynomial time algorithm learns depth-2 neural networks with ReLU activations.
Efficiently learns reward functions with fewer queries and shorter computation times.
A new uncertainty principle helps traders better understand market activity.
Enhances activity recognition in wearable computing with context awareness and uncertainty quantification.
Over the last few years, traffic data has been exploding and the transportation discipline has entered the era of big data. It brings out new opportunities for doing data-driven analysis, but it also challenges traditional analytic methods. This paper proposes a new Divide and Combine based approach to do K means clust…
Traditionally, the automatic recognition of human activities is performed with supervised learning algorithms on limited sets of specific activities. This work proposes to recognize recurrent activity patterns, called routines, instead of precisely defined activities. The modeling of routines is defined as a metric lea…
Sufficient physical activity and restful sleep play a major role in the prevention and cure of many chronic conditions. Being able to proactively screen and monitor such chronic conditions would be a big step forward for overall health. The rapid increase in the popularity of wearable devices provides a significant new…
Improved active output selection reduces calibration time by 10% or more.
Many online platforms have deployed anti-fraud systems to detect and prevent fraudulent activities. However, there is usually a gap between the time that a user commits a fraudulent action and the time that the user is suspended by the platform. How to detect fraudsters in time is a challenging problem. Most of the exi…
Researchers use operator learning to predict cardiac activation and repolarization times.
Active learning selects optimal measurement times for inferring continuous paths from sparse data.
CPATTA uses conformal prediction for efficient test-time adaptation.
Active subspace is a model reduction method widely used in the uncertainty quantification community. In this paper, we propose analyzing the internal structure and vulnerability and deep neural networks using active subspace. Firstly, we employ the active subspace to measure the number of "active neurons" at each inter…
This paper provides an overview of activation functions in neural networks.
A framework is introduced for actively and adaptively solving a sequence of machine learning problems, which are changing in bounded manner from one time step to the next. An algorithm is developed that actively queries the labels of the most informative samples from an unlabeled data pool, and that adapts to the chang…
New approach models computer network activity as mixtures of sources.
The problem of human activity recognition is central for understanding and predicting the human behavior, in particular in a prospective of assistive services to humans, such as health monitoring, well being, security, etc. There is therefore a growing need to build accurate models which can take into account the varia…
We study the activity, i.e., the number of transactions per unit time, of financial markets. Using the diffusion entropy technique we show that the autocorrelation of the activity is caused by the presence of peaks whose time distances are distributed following an asymptotic power law which ultimately recovers the Pois…
We define a Hidden Markov Model (HMM) in which each hidden state has time-dependent that drive transitions and emissions, and show how to estimate its parameters. Our construction is motivated by the problem of inferring human mobility on sub-daily time scales from, for example, mobile phone …
Human activity recognition plays an important role in people's daily life. However, it is often expensive and time-consuming to acquire sufficient labeled activity data. To solve this problem, transfer learning leverages the labeled samples from the source domain to annotate the target domain which has few or none labe…
Study reveals dynamic causal relationships between Ethereum transaction fees and economic subsystems.
Spark Transformer achieves high sparsity in FFN and attention without sacrificing model quality.
Develops a real-time exercise recommendation system using deep learning.
Automates detection of fast-ramped flexibility events for DSOs.
Active learning improves neutron spectroscopy experiments by automating measurement selection.
Using supervised machine learning approaches to recognize human activities from on-body wearable accelerometers generally requires a large amount of labelled data. When ground truth information is not available, too expensive, time consuming or difficult to collect, one has to rely on unsupervised approaches. This pape…
Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based learning is a concept that attempts to solve the latter by querying users with preference questions. In this paper, we will develop a new al…
DUNs improve active learning by dynamically adjusting model complexity.
With the rapid scaling up of deep neural networks (DNNs), extensive research studies on network model compression such as weight pruning have been performed for improving deployment efficiency. This work aims to advance the compression beyond the weights to neuron activations. We propose the joint regularization techni…
ESPRESSO segments time-series data for better human activity recognition.
Bayesian adaptive designs can be biased by active learning, especially with misspecified models.
Study proposes a stopping criterion for active learning based on error stability.
NAST generalizes scattering transform for non-stationary time series analysis.
Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The key idea is to drop nonlinear activation functions by setting them to be identity functions randomly during training time. During testing, …
Fink AGN classifier achieves high accuracy in classifying active galactic nuclei.
Study learns a neuron with non-monotonic activation functions.
Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear counterparts. However, selecting an appropriate activation function is a challenging probl…
Learning automatically the best activation function for the task is an active topic in neural network research. At the moment, despite promising results, it is still difficult to determine a method for learning an activation function that is at the same time theoretically simple and easy to implement. Moreover, most of…
New method reduces PDE surrogate model training costs by selectively acquiring time steps.
Automatic recognition of human activities from time-series sensor data (referred to as HAR) is a growing area of research in ubiquitous computing. Most recent research in the field adopts supervised deep learning paradigms to automate extraction of intrinsic features from raw signal inputs and addresses HAR as a multi-…