Temporal regularization improves stability in reinforcement learning.
problem High variance in reinforcement learning, especially in high-dimensional domains.
method Temporal regularization based on smoothness in value estimates over trajectories.
result Temporal regularization provides improvement even in high-dimensional Atari games.
Method improves clarity in forecasting spatio-temporal data.
problem Forecasting spatio-temporal data with clarity and interpretability.
method Supervised semi-nonnegative matrix factorization with frequency regularization.
result Method offers clearer interpretability in forecasting spatio-temporal data.
A new metric assesses spatio-temporal forecast quality using Gini regularized Optimal Transport.
problem Evaluating the quality of spatio-temporal forecasts.
method Gini-regularized Optimal Transport (OT) problem, using Gini impurity function as a regularizer.
result The Gini regularized OT problem converges to the classical OT problem, offering a numerically more stable algorithm.
DANR improves network regularization for spatio-temporal data.
problem Inadequate edge weights compromise network regularization.
method Discrepancy-aware network regularization (DANR) with ADMM.
result DANR achieves improved performance on various tasks.
Proposes tPARAFAC2 for tracking evolving patterns in time-evolving data.
problem Lack of temporal regularization in tensor factorizations for capturing evolving patterns.
method Temporal PARAFAC2 (tPARAFAC2) with temporal regularization.
result tPARAFAC2 accurately captures evolving patterns better than existing methods.
TATD predicts missing entries in time-evolving tensors by exploiting temporal dependency and sparsity.
problem Predict missing entries in time-evolving tensors with temporal dependency and sparsity issues.
method TATD (Time-Aware Tensor Decomposition) integrates temporal dependency and time-varying sparsity through a smoothing regularization with Gaussian kernel and alternating optimization.
result TATD achieves state-of-the-art accuracy for decomposing temporal tensors.
Paper improves video categorization using temporal coherence.
problem Video categorization in multiple modalities.
method Temporal coherence-based regularization for multimodal models.
result Models with temporal coherence outperform state-of-the-art.
The paper extends NSGPs with L1-regularization for sparsity and solves the resulting R-NSGP regression problem.
problem Sparsity in non-stationary temporal data.
method Developed an ADMM-based method for solving the regularized NSGP regression problem.
result The proposed methods induce sparsity in the parameters of NSGPs.
Improved TD learning with neural nets reduces sample complexity and overparameterization.
problem Temporal difference learning with neural networks in large state spaces.
method Projection-free and max-norm regularized Neural TD learning, with Lyapunov drift analysis.
result Max-norm regularization significantly improves TD learning's sample complexity and overparameterization.
Paper proposes a Hellinger distance regularizer to disentangle options in reinforcement learning.
problem Temporal abstraction in reinforcement learning, specifically the mutual exclusivity of learned options.
method Introduces a Hellinger distance regularizer to disentangle options.
result Demonstrates the effectiveness of the Hellinger distance regularizer in disentangling options.
A new method aligns spatial and temporal data, improving on Dynamic Time Warping.
problem Comparing data over space and time, accounting for both spatial and temporal variability.
method Spatio-Temporal Alignments (STA) using regularized optimal transport (OT) and soft-DTW.
result Soft-DTW increases quadratically with time shifts, effectively handling spatio-temporal data.
Method computes pattern time statistics from random sequences.
problem Extracting temporal regularities from random sequences.
method Using generating functions for Markov and Bernoulli trials.
result Pattern time statistics cover various measurements in learning.
A new tensor-based method for predicting temporal relationships in knowledge bases.
problem Predicting temporal relationships in evolving knowledge bases.
method Tensor decomposition of order 4 with new regularization schemes.
result Achieves state-of-the-art performance in temporal link prediction.
A simple regularization technique speeds up training of Neural ODEs.
problem Training Neural ODEs is computationally expensive.
method Randomly sampling the end time of the ODE during training.
result Significantly decreases training time and improves performance.
Lower discount factors act as a regularizer in RL, improving performance.
problem Improving RL performance with limited data.
method Explicitly equating reduced discount factors to regularization terms.
result Regularization effectiveness depends on data properties.
A simple GI loss improves temporal generalization without complex methods.
problem Temporal drift between train and test distributions in evolving data.
method Gradient Interpolation (GI) loss to regularize temporal complexity.
result GI loss outperforms complex methods on real-world datasets.
TCR improves DNN robustness to noisy labels with minimal overhead.
problem Training on noisy labeled datasets degrades DNN generalization.
method TCR combines original labels and previous epoch predictions for regularization.
result TCR consistently enhances DNN robustness to label noise.
Regularizes RNNs to be invariant to input order.
problem Making RNNs invariant to input order.
method Stochastic regularization to enforce permutation invariance.
result Improves model performance on permutation invariant tasks.
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…
This paper tackles efficient learning for factorial marked temporal point processes.
problem Efficient learning for factorial marked temporal point processes.
method Decoupled learning method with two procedures: ADM-M and Fast ISTA, and a reformulated Logistic Regression model.
result Empirical results show the efficiency of the decoupled and reformulated method.
SWoTTeD discovers hidden temporal patterns in EHR data.
problem Complex temporal patterns in EHR data.
method Sliding Window for Temporal Tensor Decomposition (SWoTTeD) with constraints and regularizations.
result SWoTTeD achieves at least as accurate reconstruction as state-of-the-art models and extracts meaningful temporal phenotypes.
Proves globally hyperbolic spacetimes via null distance completeness.
problem No Hopf-Rinow Theorem in Lorentzian Geometry.
method Observation of null distances and their behavior with time functions.
result Proves globally hyperbolic spacetimes via null distance completeness.
Temporal VAE improves VaR estimation for financial portfolios.
problem Estimating VaR for large asset portfolios in finance.
method Temporal VAE with annealing regularization to avoid posterior collapse.
result Temporal VAE outperforms classical VaR estimation methods on real data.
Algorithm estimates parameters over time-varying graphs without special assumptions.
problem Estimating parameters over time-varying graphs without assuming independence.
method Decentralized online regularized learning with innovation, consensus, and regularization terms.
result Estimations converge almost surely under certain conditions.
A framework uses deep learning for spatio-temporal data prediction.
problem Interpolation of continuous spatio-temporal fields on irregular points.
method Decomposes spatio-temporal processes into products of basis functions and spatial coefficients.
result Effectiveness in reconstructing coherent spatio-temporal fields.
Paper tackles estimating initial conditions of spatio-temporal processes from sparse data.
problem Estimating initial conditions of spatio-temporal advection-diffusion processes from sparse data.
method Regularized convex optimization problem with Alternating Direction Method of Multipliers.
result Efficient solutions for non-uniform and shifted uniform sampling schemes.
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 …
STGCN uses deep learning to forecast traffic, capturing spatial and temporal dependencies.
problem Accurate traffic forecasting for urban control and guidance.
method Spatio-Temporal Graph Convolutional Networks (STGCN) on graphs with complete convolutional structures.
result STGCN outperforms state-of-the-art baselines on various real-world traffic datasets.
Proposes a time-aware attention model for CTR prediction.
problem Lack of temporal signals in existing CTR prediction models.
method Time-aware attention model with absolute and relative temporal signals, regularized adversarial sampling.
result Significantly improves CTR prediction performance.
Improves stability of actor-critic methods by penalizing TD error.
problem Instability in actor-critic methods during learning.
method Regularize actor's learning objective by penalizing critic's TD error.
result Improves stability and overall performance of actor-critic methods.
ST-UNet models spatio-temporal graphs by pooling and unpooling operations.
problem Lack of effective means to extract dynamic features from spatio-temporal graphs.
method Designing a multi-scale architecture, Spatio-Temporal U-Net (ST-UNet), with paired sampling operations.
result Achieves substantial improvements in spatio-temporal prediction tasks.
Improved TD learning with tail averaging and regularization achieves optimal convergence rates.
problem Convergence analysis of TD learning with linear function approximation.
method Tail-averaging and regularization applied to TD learning algorithm.
result Achieves optimal O(1/t) convergence rate in expectation and with high probability. 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…
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 (SIR) model for interaction events fal…
Enhanced LSTM model learns complex temporal dependencies.
problem Modeling long-term dependencies in sequential data.
method Gamma-LSTM with hierarchical memory units and gates.
result Gamma-LSTM outperforms regular and stacked LSTMs in sequence prediction.
Scalable method for regionalizing and extracting temporal patterns from time series data.
problem Static spatial snapshots and ad hoc regularization limit effective spatial analysis and resource management.
method Minimum description length principle for fully nonparametric spatial partitioning and time series archetypes.
result Accurately recovers planted regional structure and drivers in synthetic and empirical data.
New methods improve estimation of nonhomogeneous Poisson processes from limited data.
problem Estimating nonhomogeneous Poisson processes from limited data.
method Formulated as a learning generalization problem, proposed adaptive and data-driven binning methods.
result Improved estimation of nonhomogeneous Poisson processes with limited data.
New framework IDOL identifies latent causal processes with instantaneous relations from time series data.
problem Identifying latent causal processes with instantaneous relations from time series data.
method Sparse influence constraint and variational inference architecture with sparsity regularization.
result Our method can identify latent causal processes with instantaneous relations.
The paper analyzes how over-parameterization affects reinforcement learning performance.
problem Understanding the impact of over-parameterization in reinforcement learning.
method Theoretical analysis of Least-Square Temporal Difference (LSTD) algorithm with random features and asymptotic regime.
result Identification of a double descent phenomenon in reinforcement learning performance.
Introduces TDRC to balance TD's ease and soundness.
problem TD learning's instability and divergence issues.
method Gradient Temporal-Difference Learning with Regularized Corrections (TDRC).
result TDRC performs as well as TD when TD works, but is sound in divergent cases.
Study of convergence in Lorentzian spacetimes using temporal functions.
problem Non-compactness of spacetime isometries and convergence in semi-Riemannian settings.
method Introduced anchored convergence and used Cauchy temporal functions to define convergence for spacetimes.
result Established local and global regularity of Cauchy temporal functions and their properties.
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…
A new method for filling in missing traffic data improves accuracy over existing techniques.
problem Incomplete spatiotemporal traffic data.
method Low-rank autoregressive tensor completion (LATC) framework.
result LATC framework better captures spatiotemporal consistency and local consistency.
STAS selects optimal spatio-temporal scales for bias correction in precipitation forecasts.
problem Limited prior data and fixed ST scale in existing BCoPs lead to biases in numerical weather predictions.
method End-to-end deep-learning BCoP model STAS with SFM/TFM to automatically adjust spatial and temporal scales.
result STAS outperforms 8 published BCoP methods on threat scores (TS).
Proposes deep learning for joint mean and quantile spatio-temporal modeling.
problem Typical spatio-temporal modeling focuses on conditional expectations, ignoring quantiles.
method Multi-output multi-quantile deep learning approach.
result Joint modeling of mean and quantiles improves predictive density and conditional expectation.
Proposes interpretable attention for video action recognition.
problem Efficient video action recognition with attention mechanisms.
method Spatial-temporal attention mechanism with saliency masks and convolutional LSTM.
result Improves video action recognition accuracy and spatial-temporal localization.
Paper introduces an unsupervised tensor-based anomaly detection method for spatiotemporal data.
problem Challenges in detecting anomalies in spatiotemporal data, especially in urban traffic monitoring and medical imaging.
method Formulates anomaly detection as a regularized robust low-rank + sparse tensor decomposition, incorporating spatiotemporal smoothness and local dependencies.
result Demonstrates improved anomaly detection performance on both synthetic and real data.
Paper presents a new algorithm for predicting crop yield across fields.
problem Predicting within-field spatial variability of crop yield in complex environments.
method Spatial-temporal Multi-Task Learning algorithm integrating multiple data sources.
result Algorithm outperforms conventional methods in predicting crop yield.