Unified formulation bridges adversarial and nonstationary bandits.
problem Handling time-varying reward distributions in multi-armed bandit problems.
method Unified oracle that switches between adversarial and nonstationary bandit oracles based on window size.
result Optimal regret achieved with matching lower bound.
New algorithm for nonstationary multi-armed bandits with optimal performance.
problem Nonstationary multi-armed bandits with changing model parameters over time.
method Adaptive Resetting Bandit (ADR-bandit) algorithm using adaptive windowing techniques.
result ADR-bandit achieves nearly optimal performance in both abrupt and gradual changes.
A new approach learns to represent context for nonstationary bandits.
problem Nonstationary contextual bandits where patterns change over time.
method Combines recurrent neural networks with contextual linear bandit algorithm.
result Consistently outperforms handcrafted historical contexts and other methods.
Bandit algorithms have been predominantly analyzed in the convex setting with function-value based stationary regret as the performance measure. In this paper, motivated by online reinforcement learning problems, we propose and analyze bandit algorithms for both general and structured nonconvex problems with nonstation…
Saddle-point optimization problems are an important class of optimization problems with applications to game theory, multi-agent reinforcement learning and machine learning. A majority of the rich literature available for saddle-point optimization has focused on the offline setting. In this paper, we study nonstationar…
Study shows nonstationary bandits require T-dependent regret even with minimal nonstationarity.
problem Understanding satisficing regret in nonstationary multi-armed bandits.
method Developed a novel Fano-based framework for nonstationary bandits with a post-interaction reference construction.
result Optimal regret scales with T even with minimal nonstationarity, contrasting with stationary case.
BerlinUCB learns from episodic rewards in nonstationary contexts.
problem Online learning with episodic rewards in nonstationary environments.
method BerlinUCB integrates clustering for self-supervision.
result BerlinUCB outperforms standard contextual bandits in various scenarios.
A new method optimizes in nonstationary environments with many arms efficiently.
problem Optimizing in nonstationary environments with a large number of arms.
method Gaussian interpolation to learn continuous Lipschitz reward functions in nonstationary environments.
result Efficiently learns continuous Lipschitz reward functions with O ∗ ( T ) \mathcal{O}^*(\sqrt{T}) O ∗ ( T ) cumulative regret. New algorithm tackles nonstationary linear bandits with latent dynamics.
problem Nonstationary bandit problem with latent states and unknown dynamics.
method Explore-then-commit algorithm with exploration and commitment phases.
result Achieves i l d e O ( T 2 / 3 ) ilde{\mathcal{O}}(T^{2/3}) i l d e O ( T 2/3 ) regret. DTS improves robustness of bandit algorithms in nonstationary environments.
problem Brittle behavior of multi-armed bandit algorithms in nonstationary exogenous factors.
method Deconfounded Thompson Sampling (DTS) that projects population-level performance while controlling for context.
result DTS provides resilience to exogenous variation and balances exploration and exploitation.
A contextual bandit method evaluates and improves inventory control policies.
problem Evaluating and improving periodic review inventory control policies with nonstationary demand.
method Contextual bandit-based algorithm to evaluate and tweak policies.
result The method achieves favorable guarantees in both theory and practice.
Proposes Genetic Thompson Sampling for multi-armed bandits, improving performance in nonstationary settings.
problem Improving sequential decision making tasks of online learning agents using multi-armed bandits.
method Integrates genetic principles into Thompson Sampling for multi-armed bandits.
result Significantly outperforms baselines in nonstationary settings.
New algorithm for nonstationary GLBs reduces computation and memory costs.
problem Nonstationary generalized linear bandits with unknown time-varying parameters.
method Discounted Online Mirror Descent (DOMD) for parameter estimation.
result Dynamic regret bounds of order O ( 1 ) O(1) O ( 1 ) per round in drifting and piecewise-stationary environments. We present and prove properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators. In particular, it simultaneously and correctly incorporates techniques from importance weighting, doubly robust evaluation, and nonstationary policy evaluation approaches. In a…
We consider a novel formulation of the multi-armed bandit model, which we call the contextual bandit with restricted context, where only a limited number of features can be accessed by the learner at every iteration. This novel formulation is motivated by different online problems arising in clinical trials, recommende…
New algorithm balances personalization and statistical validity in MRTs.
problem Optimizing decisions in nonstationary settings with habituation and recovery.
method ROGUE-TS Thompson Sampling with probability clipping.
result Achieves lower regret and maintains high statistical power.
Algorithm improves decision-making with partially observed contexts using pretrained models.
problem Improving decision-making with partially observed contexts in online linear contextual bandits.
method PULSE-UCB algorithm that uses pretrained models trained on auxiliary data to impute missing features.
result Achieves near-optimal performance in i.i.d. context case with Hölder-smooth missing features.
The paper provides bounds on the CDF of a variable under nonstationary conditions.
problem Estimating the complete distribution of a random variable under nonstationary conditions.
method Time-uniform and value-uniform bounds on the CDF of the running averaged conditional distribution.
result Presented computationally efficient bounds that are always valid and sometimes trivial.
Study adapts combinatorial semi-bandit for piecewise stationary, causally related rewards.
problem Nonstationary environment with changing base arms' distributions and causal relationships.
method Upper Confidence Bound (UCB) algorithm with change-point detector and group restart strategy.
result Regret upper bound reflecting effects of structural and distribution changes.
Flexible nonstationary Gaussian process with neural network parameters.
problem Limited expressiveness of stationary Gaussian processes.
method Nonstationary kernels with neural network parameters trained jointly.
result Better accuracy and log-score compared to stationary and hierarchical models.
The analysis of nonstationary time series is of great importance in many scientific fields such as physics and neuroscience. In recent years, Gaussian process regression has attracted substantial attention as a robust and powerful method for analyzing time series. In this paper, we introduce a new framework for analyzi…
Model nonstationary spatial processes using normalizing flows.
problem Difficult selection of spatial warping functions.
method Neural autoregressive flows (NAFs) for complex, high-dimensional warpings.
result NAFs model has greater representational capacity than other spatial process models.
Motivated by recommendation problems in music streaming platforms, we propose a nonstationary stochastic bandit model in which the expected reward of an arm depends on the number of rounds that have passed since the arm was last pulled. After proving that finding an optimal policy is NP-hard even when all model paramet…
ConvNets improve nonstationary covariance estimation for large-scale spatial data.
problem Estimating nonstationary spatial covariance functions on large scales.
method Convolutional Neural Networks (ConvNets) for subregion identification and selection.
result Enhanced accuracy in parameter estimation using ConvNet-based partitioning.
A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent problems. We study an episodic setting where the parameters of an MDP can differ across…
SORSCNs improve nonstationary data modeling by self-organizing and adjusting network parameters.
problem Nonstationary data challenges traditional models in continuous learning.
method SORSCNs autonomously adjust network parameters and structure in real-time using adaptive algorithms.
result SORSCNs outperform other models in generalizing to nonstationary data.
We propose a method to clean covariance matrices of nonstationary systems by using time-independent eigenvalues.
problem Noise in covariance matrices of nonstationary systems with time-independent eigenvalues.
method Data-driven approach to use independent eigenvalues encoding long-term influence of future on present.
result Our method outperforms optimal stationary methods for filtering covariance matrix and its inverse.
New method identifies nonstationary causal structures in time series data.
problem Identifying causal relationships in time series data that change over time.
method High-order Markov Switching Models for regime-dependent causal discovery.
result Scalable approach for estimating high-order regime-dependent causal structures.
New method for identifying causal relationships in financial time series data.
problem Identifying causal relationships in nonstationary financial time series data.
method Refined constraint-based causal discovery algorithm (CD-NOTS) for nonstationary time series data.
result CD-NOTS effectively identifies causal connections in financial applications.
SyMPLER improves time series forecasting in nonstationary environments with explainable models.
problem Nonstationary time series forecasting with limited interpretability.
method Dynamic piecewise-linear approximations based on Statistical Learning Theory generalization bounds.
result SyMPLER achieves comparable performance to black-box and explainable models while maintaining interpretability.
Markovian RNN adapts to nonstationary data using HMM for better time series prediction.
problem Nonstationary sequential data in real-life applications.
method Markovian RNN with HMM for regime switching and end-to-end optimization.
result Significant performance gains over vanilla RNN and Markov Switching ARIMA.
AREBA algorithm improves learning from imbalanced, nonstationary data.
problem Learning from imbalanced, nonstationary data in online settings.
method Adaptive REBAlancing (AREBA) algorithm that selectively includes examples to maintain class balance.
result AREBA significantly outperforms other algorithms in learning speed and quality.
A novel nonstationary permanental process relaxes kernel constraints and captures complex data patterns.
problem Limitations of existing permanental processes in terms of kernel types and stationarity.
method Sparse spectral representation of nonstationary kernels and hierarchical stacking of spectral feature mappings.
result Enhanced model expressiveness and reduced computational complexity.
Most real world phenomena such as sunlight distribution under a forest canopy, minerals concentration, stock valuation, exhibit nonstationary dynamics i.e. phenomenon variation changes depending on the locality. Nonstationary dynamics pose both theoretical and practical challenges to statistical machine learning algori…
New method infers causal relationships from nonstationary time series data.
problem Challenges in inferring causal relationships from nonstationary time series data.
method Proposes a new class of restricted SCM with time-varying filters and stationary noise, leveraging asymmetry from nonstationarity.
result Demonstrates effectiveness of the proposed methodology on various synthetic and real datasets.
Optimizes spectral density estimation for stationary and nonstationary processes.
problem Estimating spectral density of time series with complex structure.
method Optimally adaptive Bayesian spectral density estimation using smoothing spline covariance structure.
result Optimal eigendecomposition provides superior performance compared to alternative covariance functions.
Develops nonstationary MOGP kernels for better performance.
problem Limited applicability of existing MOGP kernels for nonstationary data.
method Harmonizable spectral mixture kernels for nonstationary MOGP.
result Automatic identification of nonstationary behavior in data.
New RL algorithm tackles nonstationary MDPs with linear approximations and varying rewards.
problem Nonstationary reinforcement learning with evolving reward and state transition functions.
method Developed a new algorithm LSVI-UCB-Restart with periodic restart, and parameter-free Ada-LSVI-UCB-Restart for unknown variation budgets.
result First minimax dynamic regret lower bound for nonstationary linear MDPs and linear MDPs lower bound.
New method tests independence with single nonstationary time series.
problem Testing independence in nonstationary nonlinear time series.
method Time-varying nonlinear regression, local long-run covariance estimation, strong Gaussian approximation.
result First framework for conditional independence testing with a single realization of a nonstationary nonlinear process.
A new method warps inputs to learn nonstationary kernels efficiently.
problem Learning nonstationary patterns in data with varying smoothness.
method Sparse spectrum Gaussian processes with input warping as conditional Gaussian measures.
result Efficient learning of nonstationary patterns with fewer parameters.
Most environmental phenomena, such as wind profiles, ozone concentration and sunlight distribution under a forest canopy, exhibit nonstationary dynamics i.e. phenomenon variation change depending on the location and time of occurrence. Non-stationary dynamics pose both theoretical and practical challenges to statistica…
In many scientific fields, such as economics and neuroscience, we are often faced with nonstationary time series, and concerned with both finding causal relations and forecasting the values of variables of interest, both of which are particularly challenging in such nonstationary environments. In this paper, we study c…
The paper provides bounds for regression schemes using nonstationary training samples.
problem Developing confidence intervals for nonparametric regression with nonstationary data.
method The approach involves Rademacher and Vapnik-Chervonenkis theories to analyze the cost and optimality of regression schemes.
result The paper establishes nonasymptotic bounds for regression schemes and optimality in L 2 L^{2} L 2 -distance. Develops a new method to discover causal relationships from nonstationary time series data.
problem Challenges in inferring causal relationships from observational data, especially for nonstationary time series.
method State-Dependent Causal Inference (SDCI) for conditionally stationary time series.
result SDCI can recover underlying causal dependencies with provable identifiability for state-dependent causal structures.
We present online prediction methods for time series that let us explicitly handle nonstationary artifacts (e.g. trend and seasonality) present in most real time series. Specifically, we show that applying appropriate transformations to such time series before prediction can lead to improved theoretical and empirical p…
A new method for nonstationary Gaussian processes using Fourier features.
problem Efficient simulation of nonstationary Gaussian processes with high-dimensional distributions.
method Discretizes the spectral representation of nonstationary processes, avoiding probability measure assumptions.
result An efficient low-rank approximation of nonstationary spectral densities, consistent and positive semi-definite.
AdaKoop efficiently models nonlinear dynamics from nonstationary data streams.
problem Capturing nonlinear dynamics in nonstationary data streams with computational efficiency.
method Koopman operator theory and probabilistic framework for streaming data.
result AdaKoop outperforms state-of-the-art methods in real-time forecasting accuracy and efficiency.
CtrlNS learns latent factors and distribution shifts from sparse transitions without prior knowledge.
problem Lack of prior knowledge of domain variables limits causal temporal representation learning.
method Sparse transition assumption and identifiability results from theoretical perspective.
result Effective in identifying distribution shifts and latent factors without prior knowledge.