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.
Method improves clarity in forecasting spatio-temporal data.
Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensional domains. Regularization is a commonly used technique in machine learning to reduce variance, at the cost of introducing some bias. Most existing regularization techniques focus o…
DANR improves network regularization for spatio-temporal data.
Proposes tPARAFAC2 for tracking evolving patterns in time-evolving data.
TATD predicts missing entries in time-evolving tensors by exploiting temporal dependency and sparsity.
Rapidly growing product lines and services require a finer-granularity forecast that considers geographic locales. However the open question remains, how to assess the quality of a spatio-temporal forecast? In this manuscript we introduce a metric to evaluate spatio-temporal forecasts. This metric is based on an Opti- …
The paper extends NSGPs with -regularization for sparsity and solves the resulting R-NSGP regression problem.
Improved TD learning with neural nets reduces sample complexity and overparameterization.
A new tensor-based method for predicting temporal relationships in knowledge bases.
A simple regularization technique speeds up training of Neural ODEs.
Lower discount factors act as a regularizer in RL, improving performance.
A simple GI loss improves temporal generalization without complex methods.
TCR improves DNN robustness to noisy labels with minimal overhead.
Regularizes RNNs to be invariant to input order.
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…
SWoTTeD discovers hidden temporal patterns in EHR data.
Proves globally hyperbolic spacetimes via null distance completeness.
Improving the performance of click-through rate (CTR) prediction remains one of the core tasks in online advertising systems. With the rise of deep learning, CTR prediction models with deep networks remarkably enhance model capacities. In deep CTR models, exploiting users' historical data is essential for learning user…
Temporal VAE improves VaR estimation for financial portfolios.
Algorithm estimates parameters over time-varying graphs without special assumptions.
In reinforcement learning (RL), temporal abstraction still remains as an important and unsolved problem. The options framework provided clues to temporal abstraction in the RL, and the option-critic architecture elegantly solved the two problems of finding options and learning RL agents in an end-to-end manner. However…
A framework uses deep learning for spatio-temporal data prediction.
Multimodal ML models can process data in multiple modalities (e.g., video, images, audio, text) and are useful for video content analysis in a variety of problems (e.g., object detection, scene understanding). In this paper, we focus on the problem of video categorization by using a multimodal approach. We have develop…
The Temporal Group LASSO is an example of a multi-task, regularized regression approach for the prediction of response variables that vary over time. The aim of this work is to introduce the reader to the concepts behind the Temporal Group LASSO and its related methods, as well as to the type of potential applications …
Paper tackles estimating initial conditions of spatio-temporal processes from sparse data.
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 TD learning with tail averaging and regularization achieves optimal convergence rates.
We consider the problem of estimating the topology of spatial interactions in a discrete state, discrete time spatio-temporal graphical model where the interactions affect the temporal evolution of each agent in a network. Among other models, the susceptible, infected, recovered () model for interaction events fal…
High-dimensional time series prediction is needed in applications as diverse as demand forecasting and climatology. Often, such applications require methods that are both highly scalable, and deal with noisy data in terms of corruptions or missing values. Classical time series methods usually fall short of handling bot…
Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect spatial and temporal dependencies. In this paper, we propose a nove…
Scalable method for regionalizing and extracting temporal patterns from time series data.
New methods improve estimation of nonhomogeneous Poisson processes from limited data.
Comparing data defined over space and time is notoriously hard, because it involves quantifying both spatial and temporal variability, while at the same time taking into account the chronological structure of data. Dynamic Time Warping (DTW) computes an optimal alignment between time series in agreement with the chrono…
A cornerstone of human statistical learning is the ability to extract temporal regularities / patterns from random sequences. Here we present a method of computing pattern time statistics with generating functions for first-order Markov trials and independent Bernoulli trials. We show that the pattern time statistics c…
New framework IDOL identifies latent causal processes with instantaneous relations from time series data.
Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition. For spatial attention, we learn a saliency mask to allow the model to focus…
The paper analyzes how over-parameterization affects reinforcement learning performance.
Electronic records contain sequences of events, some of which take place all at once in a single visit, and others that are dispersed over multiple visits, each with a different timestamp. We postulate that fine temporal detail, e.g., whether a series of blood tests are completed at once or in rapid succession should n…
Study of convergence in Lorentzian spacetimes using temporal functions.
We present a confidence-based single-layer feed-forward learning algorithm SPIRAL (Spike Regularized Adaptive Learning) relying on an encoding of activation spikes. We adaptively update a weight vector relying on confidence estimates and activation offsets relative to previous activity. We regularize updates proportion…
Introduces TDRC to balance TD's ease and soundness.
A new method for filling in missing traffic data improves accuracy over existing techniques.
STAS selects optimal spatio-temporal scales for bias correction in precipitation forecasts.
Paper introduces an unsupervised tensor-based anomaly detection method for spatiotemporal data.
Accurate real time crime prediction is a fundamental issue for public safety, but remains a challenging problem for the scientific community. Crime occurrences depend on many complex factors. Compared to many predictable events, crime is sparse. At different spatio-temporal scales, crime distributions display dramatica…
Inserts proximal mapping into deep networks for better regularization.
A new framework for averaging spatio-temporal signals using optimal transport and soft alignments.
Temporal aggregation reveals latent default correlation from monthly data.