Learning Theory and Algorithms for Forecasting Non-stationary Time Series

No abstract is available for this paper.

• Publication year

  2015

• Venue

  Neural Information Processing Systems

• Publication date

  2015-12-07

• Fields of study

  Mathematics, Computer Science

• Identifiers

  No identifiers available.

• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Online Time Series Prediction with Missing Data

  2015cited by this paper
• Sequential complexities and uniform martingale laws of large numbers

  2015cited by this paper
• Minimax Time Series Prediction

  2015cited by this paper
• Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path

  2015cited by this paper
• Domain adaptation and sample bias correction theory and algorithm for regression

  2014cited by this paper
• Generalization Bounds for Time Series Prediction with Non-stationary Processes

  2014cited by this paper
• Predictive PAC Learning and Process Decompositions

  2013cited by this paper
• Time Series: Theory and Methods

  2013cited by this paper
• Online Learning for Time Series Prediction

  2013cited by this paper
• New Analysis and Algorithm for Learning with Drifting Distributions

  2012cited by this paper
• Prediction of time series by statistical learning: general losses and fast rates

  2012cited by this paper
• The Generalization Ability of Online Algorithms for Dependent Data

  2011cited by this paper
• Online Learning: Stochastic, Constrained, and Smoothed Adversaries

  2011cited by this paper
• Predictive PAC Learnability: A Paradigm for Learning from Exchangeable Input Data

  2010cited by this paper
• Online Learning: Random Averages, Combinatorial Parameters, and Learnability

  2010influential reference
• Uniform convergence of Vapnik–Chervonenkis classes under ergodic sampling

  2010cited by this paper
• Chromatic PAC-Bayes Bounds for Non-IID Data

  2009cited by this paper
• Domain Adaptation: Learning Bounds and Algorithms

  2009cited by this paper
• Model selection for weakly dependent time series forecasting

  2009cited by this paper
• Fast Learning from Non-i.i.d. Observations

  2009cited by this paper
• Rademacher Complexity Bounds for Non-I.I.D. Processes

  2008cited by this paper
• Stability Bounds for Stationary φ-mixing and β-mixing Processes

  2008cited by this paper
• Competing with Stationary Prediction Strategies

  2006cited by this paper
• Analysis of Representations for Domain Adaptation

  2006cited by this paper
• Tracking the best hyperplane with a simple budget Perceptron

  2006cited by this paper
• Convergence and Consistency of Regularized Boosting Algorithms with Stationary B-Mixing Observations

  2005cited by this paper
• Tracking drifting concepts by minimizing disagreements

  2004cited by this paper
• Tracking a Small Set of Experts by Mixing Past Posteriors

  2003cited by this paper
• Time series analysis.

  2003cited by this paper
• Tracking the Best Linear Predictor

  2001cited by this paper
• On the generalization ability of on-line learning algorithms

  2001cited by this paper
• Nonparametric Time Series Prediction Through Adaptive Model Selection

  2000cited by this paper
• Decoupling, from Dependence to Independence, Randomly Stopped Processes, U-Statistics and Processes, Martingales and beyond

  2000cited by this paper
• A D.C. OPTIMIZATION ALGORITHM FOR SOLVING THE TRUST-REGION SUBPROBLEM∗

  1998cited by this paper
• Memory-Universal Prediction of Stationary Random Processes

  1998cited by this paper
• A D.C. Optimization Algorithm for Solving the Trust-Region Subproblem

  1998cited by this paper
• A Glivenko-Cantelli theorem for exchangeable random variables

  1997cited by this paper
• On the complexity of learning from drifting distributions

  1997cited by this paper
• A Theory of Learning and Generalization: With Applications to Neural Networks and Control Systems

  1997cited by this paper
• Long memory processes and fractional integration in econometrics

  1996influential reference
• Tracking the Best Expert

  1995cited by this paper
• RATES OF CONVERGENCE FOR EMPIRICAL PROCESSES OF STATIONARY MIXING SEQUENCES

  1994cited by this paper
• Learning with a slowly changing distribution

  1992cited by this paper
• Generalized autoregressive conditional heteroskedasticity

  1986cited by this paper
• First Order Autoregressive Processes and Strong Mixing

  1983cited by this paper
• Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation

  1982cited by this paper
• Time series analysis, forecasting and control

  1972cited by this paper

• How Patterns Dictate Learnability in Sequential Data

  2025cites this paper
• Beyond All-to-All: Causal-Aligned Transformer with Dynamic Structure Learning for Multivariate Time Series Forecasting

  2025cites this paper
• PAC-Bayesian Generalization Bounds for Graph Convolutional Networks on Inductive Node Classification

  2025influential citation
• Empirical PAC-Bayes bounds for Markov chains

  2025cites this paper
• A Closer Look at Curriculum Adversarial Training: From an Online Perspective

  2024cites this paper
• A Theoretical Framework for Zeroth-Order Budget Convex Optimization

  2024cites this paper
• Application of deep learning in cloud cover prediction using geostationary satellite images

  2024cites this paper
• DC-programming for neural network optimizations

  2024cites this paper
• Learning Rates of Deep Nets for Geometrically Strongly Mixing Sequence

  2024cites this paper
• Preparing for Black Swans: The Antifragility Imperative for Machine Learning

  2024cites this paper
• Learning under Temporal Label Noise

  2024cites this paper
• An adaptable fuzzy reinforcement learning method for non-stationary environments

  2024cites this paper
• SEAformer: frequency domain decomposition transformer with signal enhanced for long-term wind power forecasting

  2024cites this paper
• An Oracle Inequality for Multivariate Dynamic Quantile Forecasting

  2024cites this paper
• Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift

  2023cites this paper
• Online Forecasting Based Anomaly Detection For Monitoring Large Scale Streaming Data

  2023cites this paper
• Gradual Domain Adaptation: Theory and Algorithms

  2023cites this paper
• Deep Neural Newsvendor

  2023cites this paper
• Diversify: A General Framework for Time Series Out-of-Distribution Detection and Generalization

  2023cites this paper
• Theory and Algorithm for Batch Distribution Drift Problems

  2023cites this paper
• Principled Approaches for Private Adaptation from a Public Source

  2023cites this paper
• Uniform Risk Bounds for Learning with Dependent Data Sequences

  2023influential citation
• Veg-W2TCN: A parallel hybrid forecasting framework for non-stationary time series using wavelet and temporal convolution network model

  2023cites this paper
• Event Predictability: A Uniform Form for IoT-Based Nondeterministic Social Systems

  2023influential citation
• Time Series Forecasting with Hypernetworks Generating Parameters in Advance

  2022cites this paper
• Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond

  2022cites this paper
• Concentration inequalities for non-causal random fields

  2022cites this paper
• Benign overfitting in time-series linear models with over-parameterization

  2022cites this paper
• Mixture of Online and Offline Experts for Non-Stationary Time Series

  2022cites this paper
• Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series

  2022cites this paper
• Huber Additive Models for Non-stationary Time Series Analysis

  2022influential citation
• ETSformer: Exponential Smoothing Transformers for Time-series Forecasting

  2022cites this paper
• Statistical Estimation from Dependent Data

  2021cites this paper
• A High-order Tuner for Accelerated Learning and Control

  2021cites this paper
• Spatiotemporal information conversion machine for time-series forecasting

  2021cites this paper
• Learning Quantile Function without Quantile Crossing for Distribution-free Time Series Forecasting

  2021cites this paper
• ARISE: ApeRIodic SEmi-parametric Process for Efficient Markets without Periodogram and Gaussianity Assumptions

  2021cites this paper
• Learning to Learn the Future: Modeling Concept Drifts in Time Series Prediction

  2021cites this paper
• Cluster-and-Conquer: A Framework For Time-Series Forecasting

  2021cites this paper
• Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting

  2021cites this paper
• Possibilistic aggregation of inhomogeneous streams of data

  2021cites this paper
• Learning Ising models from one or multiple samples

  2020cites this paper
• Discrepancy-Based Theory and Algorithms for Forecasting Non-Stationary Time Series

  2020cites this paper
• Model adaptation and unsupervised learning with non-stationary batch data under smooth concept drift

  2020cites this paper
• Trendlets: A novel probabilistic representational structures for clustering the time series data

  2020cites this paper
• Harmonic Recurrent Process for Time Series Forecasting

  2020cites this paper
• On biased random walks, corrupted intervals, and learning under adversarial design

  2020cites this paper
• Accelerated Learning with Robustness to Adversarial Regressors

  2020cites this paper
• On Learnability under General Stochastic Processes

  2020cites this paper
• A Theory of Multiple-Source Adaptation with Limited Target Labeled Data

  2020cites this paper
• Deviation bound for non-causal machine learning

  2020cites this paper
• Adequacy of neural networks for wide-scale day-ahead load forecasts on buildings and distribution systems using smart meter data

  2020cites this paper
• Recurrent neural networks for time series prediction

  2020cites this paper
• Sparse Learning for Variable Selection with Structures and Nonlinearities

  2019cites this paper
• Learning from weakly dependent data under Dobrushin's condition

  2019cites this paper
• Identifying Malicious Players in GWAP-based Disaster Monitoring Crowdsourcing System*

  2019cites this paper
• Operator-theoretic framework for forecasting nonlinear time series with kernel analog techniques

  2019cites this paper
• High-dimensional VAR with low-rank transition

  2019cites this paper
• Provably Correct Learning Algorithms in the Presence of Time-Varying Features Using a Variational Perspective

  2019cites this paper
• Sample Complexity Bounds for the Linear Quadratic Regulator

  2019cites this paper
• Optimal Sampling of Parametric Families: Implications for Machine Learning

  2019cites this paper
• Online Time Series Prediction by ARX(∞) Approximation Algorithm

  2019cites this paper
• Learning GANs and Ensembles Using Discrepancy

  2019cites this paper
• Regularized Regression for Hierarchical Forecasting Without Unbiasedness Conditions

  2019cites this paper
• MACRO: A Meta-Algorithm for Conditional Risk Minimization

  2018cites this paper
• Online Learning Algorithms for Statistical Arbitrage

  2018cites this paper
• Foundations of Sequence-to-Sequence Modeling for Time Series

  2018cites this paper
• Exponential inequalities for nonstationary Markov chains

  2018cites this paper
• Theory and Algorithms for Forecasting Time Series

  2018cites this paper
• Towards Practical Conditional Risk Minimization

  2018cites this paper
• Random Projection Filter Bank for Time Series Data

  2017influential citation
• Final Team Report: A Novel GWAP Disaster Monitoring System

  2017cites this paper
• Non-Asymptotic Adaptive Control of Linear-Quadratic Systems

  2017cites this paper
• Multi-Armed Bandits with Non-Stationary Rewards

  2017cites this paper
• Finite Time Identification in Unstable Linear Systems

  2017cites this paper
• Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator

  2017cites this paper
• Learning Theory for Conditional Risk Minimization

  2017cites this paper
• Discriminative State Space Models

  2017cites this paper
• Discrepancy-Based Algorithms for Non-Stationary Rested Bandits

  2017influential citation
• Concentration inequalities for empirical processes of linear time series

  2017cites this paper
• Empirical risk minimization and complexity of dynamical models

  2016cites this paper
• Generalization bounds for non-stationary mixing processes

  2016influential citation
• Self-normalization techniques for streaming confident regression

  2016cites this paper
• SeDMiD for Confusion Detection: Uncovering Mind State from Time Series Brain Wave Data

  2016cites this paper
• Analysis of Nonstationary Time Series Using Locally Coupled Gaussian Processes

  2016cites this paper
• Conditional Risk Minimization for Stochastic Processes

  2015cites this paper