Logarithmic regret for continuous-time reinforcement learning.
problem Continuous-time Markov decision processes with unknown transition probabilities and holding times.
method Upper confidence reinforcement learning, mean holding time estimation, stochastic comparison of point processes.
result Logarithmic regret bound achieved in finite time.
Continuous-time algorithms improve online learning performance.
problem Online learning with sequential data and minimizing overall regret.
method Extending discrete-time algorithms to continuous-time models for online linear optimization, adversarial bandit, and adversarial linear bandit.
result Optimal regret bounds are proven for continuous-time settings.
SoftCLT improves time series representation learning by soft contrastive loss.
problem Ignoring inherent correlations in time series leads to poor representation quality.
method SoftCLT introduces instance-wise and temporal contrastive loss with soft assignments.
result SoftCLT consistently improves various downstream tasks in time series learning.
ExpCLR uses expert features to improve time-series representation learning.
problem Current representation learning approaches fail to ensure useful properties for time-series data.
method ExpCLR employs expert features to replace data transformations in contrastive learning, ensuring two useful properties for time-series representations.
result ExpCLR outperforms state-of-the-art methods on three real-world time-series datasets.
Faster policy learning via continuous-time gradients.
problem Efficiently estimating policy gradients for continuous-time systems.
method Approximating continuous-time gradients directly, using adaptive discretization.
result More efficient policy gradient estimator leads to faster learning.
A new method uses sinusoidal functions to represent timestamps as dense vectors for improving irregularly sampled time series learning.
problem Challenges in supervised learning with irregularly sampled time series due to irregular time intervals.
method Proposes a novel method to represent timestamps as dense vectors using sinusoidal functions, called Time Embeddings.
result Improves LSTM-based and classical machine learning models, especially with very irregular data.
Study of discrete-time mean-variance model using reinforcement learning.
problem Discrete-time model with more general return distribution assumptions.
method Entropy-based exploration cost, reinforcement learning algorithm design.
result Optimal investment strategy with Gaussian density function.
Proposes a new approach to time series representation learning by embedding patches independently.
problem Capturing dependencies between time series patches is not optimal for representation learning.
method 1) Patch reconstruction task, 2) Patch-wise MLP, 3) Complementary contrastive learning.
result Improves time series forecasting and classification performance compared to state-of-the-art models.
Time-warping improves RNN transfer learning for diverse time scales.
problem Transfer learning for RNNs with varying time scales.
method Time-warping rescales time in LSTM models for better transfer.
result Time-warping maintains accuracy in transferring RNNs between different time scales.
Curriculum learning and imitation learning improve control over financial time-series data.
problem Improving control performance over complex financial time-series data.
method Data augmentation for curriculum learning and policy distillation for imitation learning.
result Curriculum learning shows significant improvement over time-series control tasks.
New neural net learns time-reversible symplectic dynamics.
problem Lack of time-reversibility in neural networks for symplectic systems.
method Proposes a new neural network architecture for time-reversible symplectic systems.
result Demonstrates learning of time-reversible symplectic dynamics from data.
Develops a reinforcement learning algorithm for learning deterministic equilibrium policies in time-inconsistent control problems.
problem Learning equilibrium policies in time-inconsistent control problems.
method Continuous-time model-free reinforcement learning algorithm using deterministic policy gradient approach.
result Learned equilibrium policies in general time-inconsistent control problems.
Time series analysis is a key component of machine learning, with applications in various fields.
problem Time series analysis in machine learning
method Basic concepts, classical statistical models, modern machine learning approaches
result Machine learning techniques for time series analysis
Logarithmic regret achieved in continuous-time linear-quadratic reinforcement learning.
problem Optimizing control actions in unknown continuous-time systems over a finite time horizon.
method Least-squares algorithm based on continuous-time observations and controls, with perturbation analysis and parameter estimation error analysis.
result Logarithmic regret bound of order O((lnM)(lnlnM)). Quantum model generates complex time series data with preserved temporal dynamics.
problem Generating synthetic time series data with temporal correlations.
method Quantum Hamiltonian learning to encode temporal dynamics.
result The proposed quantum model captures unique temporal features of the learned time series.
Survey of deep learning methods for time series forecasting.
problem Improving accuracy in time series predictions across various domains.
method Analysis of common encoder and decoder designs, hybrid models, and decision support.
result Advancements in deep learning for time series forecasting.
TRS-ODENs learn dynamics with time-reversal symmetry for more efficient learning.
problem Learning dynamics with time-reversal symmetry for more efficient learning.
method Proposed a loss function and a new framework (TRS-ODENs) to learn dynamics efficiently.
result TRS-ODENs can learn dynamics from noisy and complex trajectories efficiently.
Meta-learning for Koopman spectral analysis with short time-series data.
problem Lack of long time-series for training embedding functions in Koopman spectral analysis.
method Meta-learning approach using bidirectional LSTM and neural network to estimate embedding functions from short time-series.
result The proposed method achieves better performance in eigenvalue estimation and future prediction compared to existing methods.
Proposes a new method for time series classification and clustering.
problem Overfitting and information loss in dynamic time warping.
method Generalized time warping operator integrated with dictionary learning.
result Improves dictionary learning, classification, and clustering performance.
A new unsupervised contrastive learning framework improves time series representation learning.
problem Lack of labeled data in time series data.
method Proposes an unsupervised contrastive learning framework using a novel contrastive loss and data augmentation.
result Framework outperforms other approaches on univariate and multivariate time series, and benefits transfer learning.
Deep learning autoencoder model clusters unlabeled time series data.
problem Clustering unlabeled time series data.
method Two-stage approach: create labels from time series characteristics, then use autoencoder for clustering.
result 87.5% accuracy in clustering unseen time series data.
Develops DPG methods for continuous-time RL with deterministic policies.
problem High variance and slow convergence in stochastic policy RL methods.
method Derives continuous-time policy gradient formula and proposes CT-DDPG algorithm.
result CT-DDPG achieves superior stability and faster convergence in continuous-time RL.
Safe active learning for time-series models with Gaussian processes.
problem Learning time-series models while respecting safety constraints.
method Employing Gaussian processes with a nonlinear exogenous input structure, the approach dynamically explores the input space to generate data for model learning.
result The approach effectively learns time-series models under safety constraints, as demonstrated in a technical application.
Q(Δ)-Learning improves Q-Learning by separating action-value functions into different time scales.
problem Q-Learning struggles with bias-variance trade-off, especially in long-term rewards.
method Introduces Q(Δ)-Learning, extending TD(Δ) to decompose Q(Δ)-function into distinct discount factors. result Q(Δ)-Learning achieves better stability and scalability, especially for long-term tasks. POLA adapts learning rates for online time series prediction.
problem Adapting to changing data distributions in dynamic environments.
method Adaptive learning rate regulation for recurrent neural networks.
result POLA outperforms other online prediction methods in real-world datasets.
Paper introduces solving financial problems using time-stepped FBSDE and deep learning.
problem Quantitative finance problems under specific dynamics and instruments.
method Formulate as FBSDE, turn into control problems, time-step, solve with optimization and deep learning.
result Solves financial problems with new methods and deep learning.
TNC learns time series representations by leveraging temporal neighborhoods.
problem Complex, unlabeled time series data.
method Temporal Neighborhood Coding (TNC) with a debiased contrastive objective.
result TNC outperforms other unsupervised methods in time series clustering and classification.
POSL is an online learning algorithm for personalized predictions.
problem Real-time personalized predictions for streaming data.
method Online Super Learner algorithm that optimizes predictions with respect to baseline covariates.
result POSL provides reliable predictions and adapts to changing data environments.
A new ML method predicts long-time-step molecular dynamics, preserving symplectic and time-reversible properties.
problem Limited computational efficiency in long-time-step molecular dynamics simulations.
method Learning data-driven structure-preserving maps to generate long time-step classical dynamics.
result The method eliminates artifacts like lack of energy conservation and loss of equipartition.
Minimal assumptions analysis of Q-learning with time-varying policies.
problem Finite-time analysis of Q-learning with time-varying policies for discounted MDPs.
method Minimal assumptions, Poisson equation decomposition, sensitivity analysis.
result Established convergence rate and sample complexity for Q-learning.
Study shows using time-series privileged information improves model efficiency.
problem Efficiently predicting future outcomes using supervised models with privileged information.
method Developed an algorithm for learning with privileged time-series data and proved its efficiency for non-stationary Gaussian-linear systems.
result Learning with privileged information is more efficient than without it for non-stationary Gaussian-linear systems.
Continuous-time optimal stopping solved with deep reinforcement learning
problem Optimal stopping problems in continuous time
method CARLOS (Continuous-time Adaptive Reinforcement Learning for Optimal Stopping)
result Higher prices than existing Bermudan solvers, approaching American upper bound
New method uses Transformers for flu forecasting.
problem Forecasting influenza-like illness trends.
method Transformer-based machine learning models with self-attention.
result Forecasting results are competitive with state-of-the-art methods.
DeepLINK-T uses deep learning and knockoffs for time series data.
problem Interpreting and reproducible deep learning models for high-dimensional time series data.
method Combines deep learning with knockoffs for FDR control in feature selection for time series models.
result DeepLINK-T effectively controls FDR while demonstrating superior feature selection for high-dimensional longitudinal time series data.
Continuous-time Q-learning theory developed for reinforcement learning.
problem Continuous-time reinforcement learning challenges.
method Entropy-regularized, exploratory diffusion process formulation; first-order approximation of Q-function; martingale conditions.
result Developed a q-learning theory independent of time discretization.
Real-time policy distillation speeds up and improves reinforcement learning.
problem Slow and inefficient policy distillation in reinforcement learning.
method Simultaneous training and distillation of a teacher and student model.
result Significantly reduced distillation time and improved small model performance.
Proves and tests methods for learning time-series with breaks.
problem Learning time-series with structural breaks.
method Complete proofs and experimental validation of a regularized loss function.
result Experimental results support the validity of the techniques.
We present sktime -- a new scikit-learn compatible Python library with a unified interface for machine learning with time series. Time series data gives rise to various distinct but closely related learning tasks, such as forecasting and time series classification, many of which can be solved by reducing them to relate…
Paper introduces timing-based adversarial attacks on DRL-based navigation systems.
problem Vulnerability of DRL-based navigation systems to adversarial attacks.
method Timing-based adversarial strategies using physical noise patterns.
result Adversarial timing attacks significantly degrade DRL-based navigation performance.
Overview of high-dimensional time series regression methods.
problem Estimation and inference with high-dimensional time series data.
method Limit theory for high-dimensional dependent data, asymptotic theory for time series regression, statistical learning methods.
result Main limit theory results and asymptotic theory for high-dimensional time series regression.
Develops framework for understanding deep learning in time series data.
problem Understanding and explaining decisions made by deep learning models in time series data.
method Uses deep neural networks to capture and explain temporal dependencies in time series data.
result Framework successfully captures and explains temporal dependencies in various synthetic and real-world datasets.
Deep learning improves time series classification accuracy.
problem Classifying time series data efficiently.
method Developed deep neural networks for time series classification.
result Demonstrated superior performance of deep learning methods.
VSDN models sporadic time series with neural SDEs.
problem Modeling irregular and sparse time series data.
method Variational Bayesian method and neural SDEs.
result VSDNs outperform state-of-the-art models in prediction and interpolation.
Study optimizes reinforcement learning options under time constraints.
problem Learning useful options for diverse tasks with limited time.
method Directly searched for optimal option sets considering time budget.
result Discovered options outperform existing heuristics.
We study two time-scale linear stochastic approximation algorithms, which can be used to model well-known reinforcement learning algorithms such as GTD, GTD2, and TDC. We present finite-time performance bounds for the case where the learning rate is fixed. The key idea in obtaining these bounds is to use a Lyapunov fun…
New algorithm learns bridged diffusion processes without time-reversals.
problem Learning bridged diffusion processes efficiently and accurately.
method Score matching with Doob's h-transform, avoiding time-reversals.
result Outperforms existing methods in learning bridged diffusion processes.
Survey of data augmentation methods for improving deep learning on time series data.
problem Limited labeled data in real-world time series applications.
method Review and comparison of data augmentation methods for time series.
result Empirical comparison of data augmentation methods for various time series tasks.
By and large the process of learning concepts that are embedded in time is regarded as quite a mature research topic. Hidden Markov models, recurrent neural networks are, amongst others, successful approaches to learning from temporal data. In this paper, we claim that the dominant approach minimizing appropriate risk …