Temporal networks representing a stream of timestamped edges are seemingly ubiquitous in the real-world. However, the massive size and continuous nature of these networks make them fundamentally challenging to analyze and leverage for descriptive and predictive modeling tasks. In this work, we propose a general framewo…
On-device research index
arXiv research
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Temporal Sampling”
Dynamic sample pruning speeds up spatio-temporal forecasting models.
problem Training deep learning models on large, redundant datasets is computationally expensive.
method Dynamic sample pruning based on real-time learning state.
result Significant acceleration of training speed with improved performance.
Spatio-temporal data compression method reduces memory usage.
problem Efficiently storing and analyzing large spatio-temporal datasets.
method Adaptive sampling of tensor slices to compress and preserve structure.
result SkeTenSmooth outperforms other sampling methods in retaining patterns.
Temporal threat model defends against data poisoning with timestamps.
problem Adversaries can poison more samples than expected, rendering existing defenses ineffective.
method Leverage timestamps to define earliness and duration metrics for temporal robustness.
result Temporal aggregation provides provable temporal robustness against data poisoning.
Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under -Mixingstat.ML
Study shows DQN's performance degrades with temporal dependence in data.
problem Temporal dependence in replayed data affects DQN's performance.
method Modelled -mixing data, derived risk bounds, and empirical validation.
result Temporal dependence leads to a degradation in DQN's performance rate.
Regularized Adversarial Sampling and Deep Time-aware Attention for Click-Through Rate Predictioncs.LG
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…
odeN efficiently approximates multiple temporal motifs in large networks.
problem Efficiently counting multiple temporal motifs in large temporal networks.
method odeN is a sampling-based algorithm that provides accurate probabilistic approximations of motif counts.
result odeN provides accurate approximations of motif counts in a fraction of the time needed by state-of-the-art methods.
Improves spatio-temporal forecasting by reducing errors between training and inference.
problem Accumulation of small errors in Seq2Seq models during inference due to different distributions of training and inference phases.
method Curriculum learning based on Temporal Progressive Growing Sampling to replace some ground-truth context with generated predictions.
result Better models long-term dependencies and outperforms baseline approaches on two datasets.
New unsupervised deep learning method improves temporal resolution in tMRA.
problem Limited temporal resolution in tMRA due to fixed view-sharing scheme.
method Optimal transport driven cycle-consistent generative adversarial network (cycleGAN) without fully sampled k-space reference data.
result Can generate high quality reconstructions at various temporal resolutions.
A new method for embedding temporal relationships in graphs.
problem Limited performance of existing time-aware graph embedding methods.
method Integrates temporal smoothness and task-oriented negative sampling.
result Improves performance in various tasks, especially entity/relationship/temporal scoping prediction.
Inverse Models for Estimating the Initial Condition of Spatio-Temporal Advection-Diffusion Processesstat.ME
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.
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.
New method tackles video inverse problems using image diffusion models.
problem Spatio-temporal degradation in video inverse problems.
method Leverages image diffusion models to treat time dimension as batch dimension, introduces batch-consistent diffusion sampling.
result Achieves state-of-the-art reconstructions for various spatio-temporal degradations.
Temporal networks are ubiquitous and evolve over time by the addition, deletion, and changing of links, nodes, and attributes. Although many relational datasets contain temporal information, the majority of existing techniques in relational learning focus on static snapshots and ignore the temporal dynamics. We propose…
Paper introduces a new reinforcement learning method with improved performance.
problem Designing and analyzing efficient reinforcement learning algorithms.
method Proximal gradient temporal difference learning (GTD) with accelerated algorithm GTD2-MP.
result GTD algorithms have linear complexity and improved convergence rate.
Estimates spatio-temporal data with satellite NO2 concentrations using Yule-Walker equations.
problem Estimating large spatio-temporal autoregressions with unknown spatial interactions.
method Sparse generalized Yule-Walker estimation, penalized regression, spatial and temporal dependence.
result Strong forecast improvements and evidence of spatial interactions in NO2 satellite data.
This research tackles sample complexity in causal graph recovery with temporal heterogeneity.
problem Recovering a unique causal graph from observational data with temporal heterogeneity.
method Integrates time-series dynamics and multi-environment heterogeneity to constrain the problem, enabling a rigorous analysis of statistical limits.
result Unified necessary identifiability conditions and explicit information-theoretic bounds quantify the sample complexity under different noise distributions.
A new correction term improves sample efficiency in deep reinforcement learning.
problem Momentum accumulation in TD learning leads to doubly stale gradients.
method Proposed a correction term to address the issue of doubly stale gradients.
result Improves sample efficiency in policy evaluation.
CAWs learn temporal network dynamics without node identities or edge attributes.
problem Learning temporal network dynamics without node identities or edge attributes.
method Causal Anonymous Walks (CAWs) using temporal random walks and hitting counts.
result CAW-N outperforms previous methods in predicting links over 6 real temporal networks.
FPG uses fractional calculus for efficient reinforcement learning with long-term memory.
problem High variance and inefficient sampling in standard policy gradient methods for long-term temporal modeling.
method Fractional Policy Gradients (FPG) incorporating Caputo fractional derivatives for power-law temporal correlations.
result Achieves asymptotic variance reduction of order O(t^(-alpha)) and sample efficiency gains.
Improved CEM for fast real-time planning in high-dimensional control tasks.
problem Sampling inefficiency of CEM in real-time planning.
method Novel additions to CEM including temporally-correlated actions and memory.
result 2.7-22x less samples and 1.2-10x performance increase.
TG-GAN models dynamic graph evolution for continuous-time temporal graphs.
problem Challenges in modeling dynamic temporal graphs, especially in continuous time.
method Temporal Graph Generative Adversarial Network (TG-GAN) that models truncated edge sequences, time budgets, and node attributes.
result TG-GAN significantly outperforms existing methods in efficiency and effectiveness.
New neural networks model for spatio-temporal data.
problem Building a mapping from spatially encoded time series covariates to real-valued response data.
method Proposed two novel extensions of Functional Neural Network (FNN) for spatio-temporal regression.
result Demonstrated effectiveness in handling varying spatial correlations through comprehensive simulation studies.
Variant of mSSA improves time series prediction error.
problem Improve prediction error in multivariate time series.
method Introduce spatio-temporal factor model, establish prediction error scaling.
result Prediction error scales as 1 / √(min(N, T)T).
New loss function equivalence reveals PER's uniform sampling can be improved.
problem Improving Prioritized Experience Replay (PER) for better learning efficiency.
method Transforming non-uniformly sampled data loss functions into uniformly sampled ones.
result Some environments can replace PER with a new loss function without performance loss.
Improved TD learning reduces variance and bias errors.
problem Inefficient optimization variance in TD learning.
method Proposed a mathematically solid analysis of VRTD, showing linear convergence rate and reduced variance and bias errors.
result VRTD converges to a fixed-point solution with reduced variance and bias errors compared to vanilla TD.
A new video prediction model treats videos as continuous processes, reducing sampling steps and improving efficiency.
problem Efficiency and temporal coherence in video prediction models.
method Treats videos as a continuous multi-dimensional process, reducing sampling steps.
result Reduction of 75% sampling steps, state-of-the-art performance on benchmark datasets.
Paper improves TD learning algorithm bounds with linear approx.
problem Sharp bounds for TD method performance in MDPs.
method Polyak-Ruppert averaging, universal step size, refined error bounds, stability of random matrices.
result Near-optimal variance and bias terms achieved.
TCGPN improves stock forecasting by capturing temporal correlation patterns.
problem Stock forecasting with minimal periodicity and large node numbers.
method TCGPN uses Temporal-Correlation fusion encoder and pre-training methods to handle large datasets.
result TCGPN achieves state-of-the-art results on real stock market 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…
Accelerates TPP sampling with speculative decoding for faster sequence generation.
problem Efficiently sampling from complex temporal point processes.
method Adapting speculative decoding techniques from language models to TPPs.
result Achieves significant speedup (2-6x) while maintaining distributional accuracy.
Restricted Boltzmann Machines (RBMs) are generative models which can learn useful representations from samples of a dataset in an unsupervised fashion. They have been widely employed as an unsupervised pre-training method in machine learning. RBMs have been modified to model time series in two main ways: The Temporal R…
Time-variant value function transfer method for RL.
problem Transfer learning with time-variant task distributions.
method Variational approach leveraging temporal structure.
result The proposed method outperforms time-invariant approach in experiments.
TriTPP models enable faster and more flexible event data modeling.
problem Inflexibility and slow sampling in traditional TPP models.
method Triangular Maps and Normalizing Flows for parallel sampling and likelihood computation.
result TriTPP models achieve orders of magnitude faster sampling while maintaining flexibility.
New model recommends stocks considering individual preferences and diversification.
problem Inaccurate stock price predictions and ignoring investment theories.
method Portfolio Temporal Graph Network Recommender (PfoTGNRec) incorporating diversification-enhancing sampling.
result PfoTGNRec outperforms state-of-the-art models in real-world data.
Learning a good distance measure for distance-based classification in time series leads to significant performance improvement in many tasks. Specifically, it is critical to effectively deal with variations and temporal dependencies in time series. However, existing metric learning approaches focus on tackling variatio…
Improved TD learning reduces batch sampling error.
problem TD learning can be inaccurate in batch settings due to action weighting.
method Introduced PSEC-TD(0) to correct action weighting using importance sampling.
result PSEC-TD(0) produces more accurate value function estimates.
New algorithm improves causal discovery in biomedical data.
problem Stability and accuracy issues in causal discovery algorithms.
method Exploits temporal structure and tiered background knowledge.
result Increases accuracy in finite samples for causal structure estimation.
Develops methods to answer counterfactual questions in temporal point processes.
problem Lack of counterfactual analysis in temporal point process models.
method Causal model of thinning based on Gumbel-Max structural causal model, superposition theorem, and sampling algorithm.
result Simulation of counterfactual realizations provides valuable insights for targeted interventions.
Meta-learning adjusts TD learning's eligibility trace parameter for more efficient reinforcement learning.
problem Efficiently tuning the eligibility trace parameter for temporal difference learning.
method Meta-learning method to adjust eligibility trace parameter state-dependently.
result Improves overall quality of update targets, minimizing target error.
Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address a bias-variance trade off between reliance on current estimates, which could be …
A new kernel framework analyzes spatio-temporal data from dynamic equations.
problem Analyzing spatio-temporal data from dynamic equations with noisy measurements.
method Kernel-based framework with representer theorem for minimizing error with given samples.
result Minimizes error in solutions of dynamic equations with noisy spatio-temporal data.
FNOs improve spatio-temporal forecasting without needing PDE details.
problem Complex spatio-temporal dynamics in physical and biological phenomena.
method Fourier Neural Operators (FNOs) for dynamic spatio-temporal modeling.
result FNO forecasts are accurate and capture complex real-world dependencies.
Paper proposes a novel approach to improve temporal clustering of time series data.
problem Challenges in clustering temporal data with varying sampling rates and high dimensionality.
method Transform time series into Euclidean space using similarity measures, then use CNN-GRU autoencoder for latent representation.
result Approach outperforms existing methods by up to 32% on various time series datasets.
Paper tackles temporal overfitting in wind power curve modeling.
problem Temporal overfitting in wind power curve modeling.
method Proposes a Gaussian process-based method to partition and model time-invariant and time-varying components.
result Significant improvement in predicting responses for different time periods.
Paper improves generalization bounds for multi-kernel learning with mixed datasets.
problem Improving generalization for multi-kernel learning with mixed Markov chain datasets.
method Developed novel generalization bounds with and dependencies.
result Added terms compensate for dependency among samples in mixed datasets.
The paper shows how ignoring temporal context in recommender systems evaluation leads to false confidence, proposing a method to embed temporal context.
problem The discrepancy between offline and online recommender system performance evaluation.
method Proposes a training procedure to embed temporal context into recommender systems and validates its advantage using multi-objective optimization.
result Including temporal context in recommender systems evaluation can improve recall@20 by up to 20%.
In this work we consider the problem of detecting anomalous spatio-temporal behavior in videos. Our approach is to learn the normative multiframe pixel joint distribution and detect deviations from it using a likelihood based approach. Due to the extreme lack of available training samples relative to the dimension of t…