New method corrects least-squares temporal difference for better lambda-return estimation.
problem Improving lambda-return estimation in reinforcement learning.
method Uncorrected least-squares temporal difference with a correction method.
result Enhanced accuracy in temporal difference learning.
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).
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.
Proposes a new method for off-policy learning in reinforcement learning.
problem Improving off-policy learning in reinforcement learning.
method Integrates current Q-function corrections with rewards instead of transition probabilities.
result Proves off-policy convergence for policy evaluation and control under certain conditions.
Paper proposes an efficient method for calibrating spatio-temporal forecasts.
problem Real-world spatio-temporal forecasting challenges like signal anomalies and distributional shifts.
method Learning with Calibration (ST-TTC) for real-time bias correction.
result ST-TTC improves spatio-temporal forecasting accuracy with reduced computational cost.
Temporal Functional Circuits explain KAN forecasts with interpretable edge functions.
problem Lack of mechanistic explanations in KAN forecasting.
method Transform KAN edge functions into faithful, temporally grounded explanations using a gated residual KAN.
result Gated KAN achieves lower MSE than linear-only models on regime-switching signals.
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.
Framework combines HMM and MTGCN for spatiotemporal causal inference in clinical data.
problem Challenges in observing direct treatment effects in clinical domains.
method Integrates Hidden Markov Model and Multi Task and Multi Graph Convolutional Network for spatiotemporal data.
result Advances predictive causal inference by structurally adapting to spatiotemporal complexities.
Improved incremental sequence classification with temporal consistency.
problem Updating predictions as new sequence elements are revealed.
method Temporal-difference learning and a temporal-consistency condition for successive predictions.
result Optimizing a novel loss function improves data efficiency and predictive accuracy.
New method tests independence in time series data.
problem Testing independence between time series data.
method Temporal dependence statistic with block permutation.
result Asymptotically valid and universally consistent test for independence.
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.
Quantum reservoir computing tackles noisy quantum computers for temporal tasks.
problem Efficiently process input sequences on noisy quantum computers.
method Quantum reservoir computing using dissipative quantum dynamics.
result Small and noisy quantum reservoirs can handle high-order nonlinear temporal tasks.
Transformers learn to predict temporal logic solutions from classical solver outputs.
problem Training neural networks on logic problem solutions for verification.
method Training a Transformer on generated training data from classical solvers, focusing on one solution per formula.
result Transformers can predict correct solutions to temporal logic problems, even to unseen benchmarks.
tempdisagg transforms low-frequency data into high-frequency estimates.
problem Transforming low-frequency data into high-frequency estimates.
method Uses econometric techniques including Chow-Lin, Denton, Litterman, Fernandez, and uniform interpolation.
result Transforms low-frequency aggregates into consistent, high-frequency estimates.
Sig-PCA integrates model outputs and observations to correct model biases.
problem Improving model accuracy and reliability by correcting biases and numerical approximations.
method Sig-PCA framework that combines summary statistics from model outputs with localized observations via a neural network.
result Corrects model outputs to align closely with observational data, preserving essential statistical information.
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.
The paper analyzes the sample complexities for policy evaluation with linear function approximation.
problem Policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes.
method Investigates sample complexities for two policy evaluation algorithms: TD and TDC.
result Establishes high-probability sample complexity bounds for policy evaluation algorithms.
New method corrects seasonal Arctic sea ice predictions with probabilistic models.
problem Systematic biases and errors in climate model forecasts of Arctic sea ice.
method Conditional Variational Autoencoder model to map observation distribution given biased model predictions.
result Probabilistic adjusted forecasts are better calibrated and have smaller errors.
This paper improves STL inference reliability under covariate shift.
problem Ensuring correct STL formulas in real-world settings with distribution shift.
method Proposes a conformalized STL inference framework that addresses covariate shift.
result Significantly improves symbolic learning reliability at deployment time.
New method preserves GCM spatial dependencies for better climate projections.
problem Systemic biases in GCM output and loss of spatial/temporal dependencies.
method SPECD approach using Vecchia approximation and semi-parametric quantile regression.
result SPECD preserves key marginal and joint distribution properties of precipitation and temperature.
RFN models urban mobility demand by separating temporal and spatial variability.
problem Aligning supply and demand in MoD systems for efficient transportation.
method Recurrent flow networks with latent variables and normalizing flows.
result RFN models explicitly disentangle temporal and spatial variability in urban mobility.
Algorithm learns stochastic system dynamics from data.
problem Recovering interpretable symbolic expressions for stochastic systems.
method Data-driven, trajectory averaging, drift-informed correction.
result Recover coefficients and densities to within 5% and 0.01 in total variation, respectively.
Improved TD learning for non-i.i.d. Markovian data.
problem Convergence analysis of two time-scale TD learning under Markovian samples.
method Non-asymptotic convergence analysis of two time-scale TD with gradient correction under Markovian data.
result Two time-scale TD can converge as fast as O(log t/(t^(2/3))) under diminishing stepsize.
Temporal Causal Prior-Data Fitted Networks (TCPFN) for industrial time series causal discovery
problem Estimating causal effects in industrial time series
method Temporal Causal Prior-Data Fitted Networks
result Zero-shot causal discovery with explicit reliability signals
Proposes Deep LTMLE for estimating dynamic treatment effects in longitudinal studies.
problem Estimating counterfactual mean outcomes under dynamic treatment policies in longitudinal settings.
method Uses a transformer architecture with temporal-difference learning for initial estimation, followed by TMLE correction and statistical inference.
result Demonstrates superior performance in complex, long-term scenarios compared to existing methods.
Deep neural networks predict earthquake locations with high accuracy.
problem Predicting the location of earthquakes with high precision.
method Recurrent Convolutional Neural Networks (R-CNN) model that accounts for spatio-temporal dependencies.
result Neural networks model outperforms baseline models in predicting earthquakes with ROC AUC 0.975 and PR AUC 0.0890.
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.
Algorithm mines environment assumptions for cyber-physical systems.
problem Modeling and verifying complex cyber-physical systems.
method Supervised learning to mine STL formulas for input signals.
result Algorithm learns both the structure and constants of STL formulas.
A fast spectral algorithm detects community structure in evolving graphs.
problem Detecting community structure in time-evolving sparse graphs.
method Extension of the Bethe-Hessian matrix for spectral community detection.
result The algorithm reaches the optimal detectability threshold and outperforms other methods.
Study compares geostatistical and machine learning models for PM2.5 prediction.
problem Improving accuracy of hourly PM2.5 maps across California.
method Traditional geostatistical methods (kriging, land use regression) and machine learning models (neural networks, random forests, support vector machines) were evaluated.
result Ensemble model enhanced predictive accuracy of PM2.5 concentration by correcting PurpleAir data bias.
Framework LiLY recovers latent causal variables from time-series data under distribution shifts.
problem Learning and correcting models under unknown distribution shifts in time-series data.
method LiLY framework that recovers latent causal variables and identifies their relations from temporal data under different distribution shifts.
result The framework reliably identifies time-delayed latent causal influences from observed variables under different distribution changes.
Novel flows generate molecules without post-processing.
problem Generating new molecules efficiently and without post-processing issues.
method Continuous normalizing E(3)-equivariant flows based on node ODEs coupled as a graph PDE.
result Generated samples achieve state-of-the-art performance on QM9 and ZINC250K benchmarks.
Develops a multi-resolution multi-task framework for integrating noisy, varying data.
problem Integrating evidence from multiple observation processes with varying resolutions and noise levels.
method Multi-resolution Multi-task Gaussian Processes (MRGP) framework, shallow and deep Gaussian Process mixtures.
result Generalizes and outperforms state-of-the-art GP compositions, offering efficient corrections and approximations.
New privacy method for eye tracking data reduces correlations and maintains accuracy.
problem Privacy concerns in eye tracking data from VR/AR glasses.
method Transform-coding based differential privacy mechanism for eye movement data.
result Significant reductions in sample correlations and query sensitivities, providing high privacy without loss in accuracy.
The paper tackles temporal coverage bias in financial panel data, proposing a structuring framework to correct for incomplete histories.
problem Incomplete histories of financial instruments lead to biased panel data.
method Formalizes the problem and proposes a coverage-aware structuring framework using structured metadata and an availability matrix.
result The framework reveals substantial distortions in return dynamics and volatility when naive temporal alignment is used.
Dynamic Vine Copulas detect and quantify time-varying higher-order interactions in multivariate systems.
problem Time-varying dependence in multivariate systems, including tail behavior, asymmetry, and conditional structure.
method Dynamic Vine Copulas (DVC) framework for estimating and diagnosing non-Gaussian dependence, using fixed-root-order C-vines and smooth parameter trajectories.
result DVC detects and quantifies time-varying higher-order interactions, distinguishing between pairwise and conditional dependence.
Paper tackles dynamic graph topology identification in time-varying graphs.
problem Dynamic graph topology identification in time-varying graphs.
method Proposes an online algorithm for time-varying optimization, with intrinsic temporal regularization.
result Demonstrates performance on Gaussian graphical model problem.
News sentiment in U.S. economic newspapers has become more persistent over 45 years.
problem Understanding the temporal dynamics of U.S. economic news sentiment over time.
method Daily economic news sentiment index from 1980-2025, analyzed using sentiment indexes.
result News sentiment states have become more persistent, with longer residence times in optimistic or pessimistic regimes.
Proposes log density gradient to improve reinforcement learning sample complexity.
problem Residual error in gradient estimation in policy gradient methods.
method Log density gradient method to correct residual error, using state-action discounted distributional formulation.
result Min-max optimization method to approximate log density gradient with on-policy samples, achieving sample complexity of m−1/2. SCAFFLSA reduces communication complexity for federated learning with heterogeneous clients.
problem Quantifying and reducing communication complexity in federated learning with heterogeneous clients.
method Proposes SCAFFLSA, a variant of FedLSA using control variates to correct for client drift.
result SCAFFLSA achieves logarithmic communication complexity for statistically heterogeneous agents, scaling with the inverse of the desired accuracy.
Study shows class imbalance and temporal coherence impact solar flare analysis.
problem Class imbalance and temporal coherence in rare-event analysis.
method Experiments on SWAN-SF dataset, including data and model manipulations.
result Temporal coherence invalidates randomness assumption, impacting sampling practices.
CREDIT learns to master pair trading with risk-aware RL, outperforming existing methods.
problem Challenges in applying RL to pair trading due to temporal correlations and risk considerations.
method Risk-aware recurrent reinforcement learning (RL) with bidirectional GRU and temporal attention.
result CREDIT achieves significant profit in pair trading over five years of U.S. stock data.
New TD algorithms stabilize RL tasks by reformulating updates into fixed point equations.
problem TD learning's sensitivity to step size specification.
method Implicit TD algorithms reformulate TD updates into fixed point equations.
result Implicit TD algorithms are more stable and less sensitive to step size.
The paper characterizes conditions for convergence of RL methods with linear approximations.
problem Characterizing non-uniqueness issues for reinforcement learning algorithms with linear function approximation.
method Proves a condition on features that determines convergence or non-uniqueness of natural algorithms.
result Natural algorithms converge to the correct solution if and only if value functions in the approximation space satisfy a certain shape.
A new property fixes look-ahead bias in backtesting and trading pipelines.
problem Fixing look-ahead bias in backtesting and trading pipelines.
method Developed a pipeline calculus separating availability from reference time, and a type-and-effect system for the value-independent fragment.
result The check scales linearly and catches all leaks, including those missed by differential and tiling detectors.
Deep learning model detects and corrects outliers in crowd-sourced weather data.
problem Data quality issues in crowd-sourced weather data.
method Bayesian deep learning approach with Gaussian-uniform mixture density network.
result Automated outlier detection in spatio-temporal environmental modeling.
CDA framework infers channel influence from aggregated data without user identifiers.
problem Lack of user-level path data due to privacy regulations and platform restrictions.
method CDA integrates PCMCI for causal discovery and Structural Causal Model for effect estimation.
result CDA achieves strong accuracy in estimating channel influence, even under structural uncertainty.
Extends utility maximization theory for infinite horizons without strong no-arbitrage assumptions.
problem Maximizing lifetime utility from wealth over an infinite horizon.
method Develops a duality theory using deflators and supermartingale properties, extending previous work.
result Establishes a strong duality theorem for infinite horizon utility maximization under minimal no-arbitrage assumptions.