Algorithm adapts to non-stationary rewards without prior knowledge.
problem Optimizing decisions in non-stationary environments without prior knowledge of changes.
method Optimization-based algorithm that restarts when non-stationarity is detected.
result Achieves tighter dynamic regret bound and is nearly minimax optimal.
We use diffusion models to sample from complex GP priors in climate data.
problem Sampling from non-stationary Gaussian process priors is computationally hard.
method Replace GP prior with a diffusion model surrogate and use training-free guidance algorithms.
result Generated distributions are close to GP priors and can be fine-tuned.
DS-TS adapts to abrupt and smooth changes in bandit problems.
problem Non-stationary multi-armed bandit problems with abrupt and smooth changes.
method Discounted Thompson Sampling with Gaussian priors.
result Achieves nearly optimal regret bound for both abrupt and smooth changes.
New approach turns optimal stationary RL into non-stationary RL without prior knowledge.
problem Optimal RL in non-stationary environments without prior knowledge of non-stationarity.
method Black-box reduction of optimal stationary RL algorithms to non-stationary RL.
result Achieves optimal dynamic regret bounds in various RL settings.
Generative models improve inverse problems by providing tailored priors.
problem Analyzing the error in inverse problems solved with generative priors.
method Quantitative error bounds for minimum Wasserstein-2 generative models.
result The error in the posterior due to the generative prior is bounded by the prior's error in Wasserstein-1 distance.
New algorithm reduces dynamic regret without prior function change knowledge.
problem Non-stationary stochastic optimization with bandit feedback.
method Fixed step sizes combined with multi-scale sampling framework.
result Achieves optimal dynamic regret without prior function change knowledge.
New definition resolves ambiguity in non-stationary bandit classification.
problem Ambiguity in classifying non-stationary bandits using existing definitions.
method Introducing a formal definition that resolves ambiguity and provides a unified approach.
result Unified approach applicable to both Bayesian and frequentist formulations, resolves classification issues.
This paper distills financial indicators into neural networks to reduce noise and improve accuracy.
problem Reduction of non-stationary noise in financial time series data.
method Co-distillation of smaller networks trained on indicators to transfer prior knowledge and reduce overfitting.
result The proposed method outperforms traditional methods in terms of speed and accuracy on real financial datasets.
New method reduces dynamic regret for non-stationary bandits.
problem Non-stationary stochastic multi-armed bandit problem with changing optimal arm.
method Proposes a method achieving near-optimal dynamic regret without prior knowledge of changes.
result Achieves O ~ ( K N ( S + 1 ) ) \widetilde O(\sqrt{K N(S+1)}) O ( K N ( S + 1 ) ) dynamic regret. Master algorithm fails to detect non-stationarity in practical settings.
problem Non-Stationary Reinforcement Learning without prior knowledge.
method Master algorithm tested under various conditions, including piecewise stationary multi-armed bandits.
result Master's non-stationarity detection is ineffective for practical horizons, leading to performance similar to random restarting.
MetaCURL tackles non-stationary MDPs with optimal dynamic regret.
problem Online learning in non-stationary Markov decision processes.
method MetaCURL uses a meta-algorithm with multiple black-box algorithms and a sleeping expert framework.
result Achieves optimal dynamic regret without prior knowledge of MDP changes.
Vroom optimizes in unpredictable conditions without derivatives.
problem Optimizing in non-stationary, adversarial environments.
method Zeroth-order online learning with vanishing regret.
result Achieves favorable rates in stochastic settings.
DAL enhances black-box bandit algorithms for non-stationary environments.
problem Non-stationary environments in bandit problems.
method DAL combines any stationary bandit algorithm with a change detector.
result DAL consistently outperforms state-of-the-art methods in various non-stationary scenarios.
New RL algorithm tackles non-stationary environments with flexible policy updates.
problem Non-stationary reinforcement learning with time-varying rewards and transition probabilities.
method Model-free policy-based algorithm NS-NAC with restart-based exploration and dynamic learning rates.
result Dynamic regret of i l d e O ( ∣ S ∣ 1 / 2 ∣ A ∣ 1 / 2 Δ T 1 / 6 T 5 / 6 ) ilde{\mathscr O}(|S|^{1/2}|A|^{1/2}Δ_T^{1/6}T^{5/6}) i l d e O ( ∣ S ∣ 1/2 ∣ A ∣ 1/2 Δ T 1/6 T 5/6 ) for both algorithms. Novel Bayesian approach for non-stationary linear contextual bandits.
problem Non-stationary linear contextual bandits.
method Weighted Sequential Bayesian (WSB) inference.
result Established frequentist regret guarantees for new algorithms.
New algorithm tracks changes in infinite action space rewards.
problem Non-stationary Lipschitz bandits with infinite actions.
method Adaptive tracking of significant shifts using hierarchical discretization.
result Achieves minimax-optimal dynamic regret bound of O ~ ( i l d e L 1 / 3 T 2 / 3 ) \mathcal{\widetilde{O}}( ilde{L}^{1/3}T^{2/3}) O ( i l d e L 1/3 T 2/3 ) . DARLING tackles non-stationary RL with guarantees, improving dynamic regret.
problem Non-stationary reinforcement learning in unknown change points.
method Detection Augmented Reinforcement Learning (DARLING) for tabular and linear MDPs.
result DARLING matches minimax lower bounds in tabular and linear MDPs.
ETGPSSM efficiently models high-dimensional, non-stationary systems with reduced complexity.
problem Prohibitive computational and parametric complexity in high-dimensional, non-stationary dynamical systems.
method ETGPSSM integrates a single shared GP with input-dependent normalizing flows for scalable and flexible modeling.
result ETGPSSM outperforms existing models in computational efficiency and accuracy.
We introduce GLR-klUCB, a novel algorithm for the piecewise iid non-stationary bandit problem with bounded rewards. This algorithm combines an efficient bandit algorithm, kl-UCB, with an efficient, parameter-free, changepoint detector, the Bernoulli Generalized Likelihood Ratio Test, for which we provide new theoretica…
We consider the multi armed bandit problem in non-stationary environments. Based on the Bayesian method, we propose a variant of Thompson Sampling which can be used in both rested and restless bandit scenarios. Applying discounting to the parameters of prior distribution, we describe a way to systematically reduce the …
This paper refines the weighted strategy for non-stationary parametric bandits, improving regret bounds.
problem Non-stationary environments with gradual drifting patterns.
method Refined analysis framework for the weighted strategy in linear and generalized linear bandits.
result A simpler weight-based algorithm with improved regret bounds compared to previous studies.
New algorithm tackles non-stationary RL with near-optimal regret bounds.
problem Model-free reinforcement learning in non-stationary Markov decision processes.
method Proposed RestartQ-UCB algorithm with Freedman-type bonus terms.
result Achieves near-optimal dynamic regret bound in non-stationary RL.
New TS algorithms improve performance in non-stationary multi-armed bandit problems.
problem Sequential decision-making with evolving action rewards.
method Sliding-window Thompson sampling approaches with different priors.
result Unified regret upper bound for arbitrary non-stationary MABs.
One of the challenges in model-based control of stochastic dynamical systems is that the state transition dynamics are involved, and it is not easy or efficient to make good-quality predictions of the states. Moreover, there are not many representational models for the majority of autonomous systems, as it is not easy …
This paper refines the weighted strategy for non-stationary parametric bandits and MDPs, improving regret bounds.
problem Non-stationary environments with gradual drifting patterns.
method Refined analysis framework for the weighted strategy, leading to simpler and more efficient algorithms.
result Improved regret bounds for linear bandits, generalized linear bandits, and self-concordant bandits.
New method tracks shifts in infinite-armed bandits without prior knowledge.
problem Tracking shifts in non-stationary infinite-armed bandits.
method Blackbox conversion of finite-armed MAB to infinite-armed non-stationary, randomized elimination.
result First parameter-free optimal regret bounds for all reservoir regularity regimes.
Paper introduces MN-DAG for modeling evolving causal relationships in multivariate time series.
problem Modeling causal relationships that evolve over time and occur at different scales.
method Probabilistic generative model based on spectral and causality theories, combined with Bayesian stochastic variational inference.
result MN-CASTLE outperforms baseline models in identifying causal relationships in multivariate time series data.
Proposes a flexible MGP model for dynamic, sparse correlations.
problem Handling dynamic and sparse correlations in multivariate data.
method Non-stationary MGP with dynamic spike-and-slab prior and EM algorithm.
result Captures dynamic and sparse correlations effectively.
Bandit Convex Optimization (BCO) is a fundamental framework for modeling sequential decision-making with partial information, where the only feedback available to the player is the one-point or two-point function values. In this paper, we investigate BCO in non-stationary environments and choose the \emph{dynamic regre…
Warped Gaussian process model for non-stationary time series forecasting.
problem Non-stationary time series with gradually varying volatility, change points, or both.
method Non-parametric warping of input distances with Gaussian process, gradient optimization for training.
result State-of-the-art forecasting performance at lower implementation and computation cost.
Study online conformal prediction for non-stationary data with optimal training-conditional regret.
problem Online prediction for non-stationary data streams with unknown distribution drift.
method Proposes split-conformal and full-conformal algorithms that adapt to drift detection and incorporate stability for online learning.
result Proves minimax-optimal regret for online full conformal algorithm under appropriate restrictions.
A novel GPDA method for high-dimensional functional data.
problem Classification and feature selection challenges in high-dimensional, non-stationary functional data.
method Unified two-layer non-stationary Gaussian process with Ising prior for variable selection and classification.
result Demonstrated superior performance on simulated and proteomics datasets.
Bayesian non-parametric model adapts to concept drifts in streaming data.
problem Inference under concept drift phenomenon for non-stationary data streams.
method Variational inference algorithm for Dirichlet process mixture models with exponential forgetting.
result The proposed model outperforms state-of-the-art algorithms in clustering problems.
New algorithms adaptively calibrate predictions in non-stationary environments, matching optimal rates.
problem Designing online prediction algorithms that adapt to varying levels of non-stationarity.
method Epoch-based scheduling and non-uniform partitioning of the prediction space.
result Achieves adaptive calibration guarantees under multiple measures with optimal rates.
New framework for probabilistic linear solvers reduces manual effort.
problem Manual implementation of probabilistic iterative methods is laborious.
method Affine Tracing: Automatically constructs PIMs from standard implementations.
result Any realistic affine PIM is calibrated, motivating their adoption.
SmoothFBO tackles non-stationary functional bilevel optimization.
problem Current FBO methods are limited to static offline settings and perform poorly in online, non-stationary scenarios.
method SmoothFBO introduces a time-smoothed stochastic hypergradient estimator with a window parameter to handle non-stationarity.
result SmoothFBO achieves sublinear regret and outperforms existing methods in non-stationary hyperparameter optimization and model-based reinforcement learning.
Study on inventory control with changing demand, proposing adaptive algorithms.
problem Inventory control with non-stationary demand distributions.
method Adaptive online algorithms optimizing base-stock policies.
result Sharp separation in adaptability across different inventory models.
Proposes a new algorithm for non-stationary bandits.
problem Non-stationary reward distributions in contextual bandits.
method Multiscale changepoint detection for adaptive learning.
result Regret bound analysis and superior performance in experiments.
Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.
problem Understanding and handling non-stationary environments in reinforcement learning.
method Demonstrated that transformers can achieve nearly optimal dynamic regret bounds in non-stationary settings.
result Transformers can approximate and learn strategies for non-stationary environments, matching or outperforming existing expert algorithms.
Humans and animals can learn complex predictive models that allow them to accurately and reliably reason about real-world phenomena, and they can adapt such models extremely quickly in the face of unexpected changes. Deep neural network models allow us to represent very complex functions, but lack this capacity for rap…
Study incentivizes exploration in non-stationary MAB with compensation.
problem Incentivized exploration for non-stationary stochastic bandits with biased feedback.
method Proposed algorithms for abruptly-changing and continuously-changing non-stationary environments.
result Achieves sublinear regret and compensation over time.
New algorithm tackles non-stationary reinforcement learning with general function approximation.
problem Understanding non-stationary MDPs with function approximation.
method Dynamic Bellman Eluder (DBE) dimension for complexity, sliding window mechanism, confidence set design.
result Upper bound on dynamic regret for proposed SW-OPEA algorithm.
Proposes a method to forecast non-stationary time series.
problem Challenges of non-stationary conditional distributions in deep learning.
method Bayesian dynamic model + deep conditional distribution model.
result Adapts to non-stationary time series better than state-of-the-art solutions.
Financial markets are complex environments that produce enormous amounts of noisy and non-stationary data. One fundamental problem is online portfolio selection, the goal of which is to exploit this data to sequentially select portfolios of assets to achieve positive investment outcomes while managing risks. Various al…
Unified framework for Bayesian online learning in changing conditions.
problem Probabilistic online learning in non-stationary environments.
method BONE framework with three modelling choices and two algorithmic choices.
result Framework allows for reinterpreting and proposing new methods.
New definitions of ESP for quantum reservoir computing handle non-stationary systems.
problem Traditional ESP does not apply to non-stationary systems.
method Introduce two new categories of ESP: non-stationary ESP and subset/subspace ESP.
result Demonstrates correspondence between non-stationary ESP and QRC with NARMA tasks.
Study combines VICReg and TNC for better encoding of non-stationary seismic signals.
problem Ineffective self-supervised learning on non-stationary time series.
method Combines VICReg and Temporal Neighborhood Coding (TNC).
result Effective for self-supervised learning on non-stationary seismic signals.
We propose non-stationary spectral kernels for Gaussian process regression. We propose to model the spectral density of a non-stationary kernel function as a mixture of input-dependent Gaussian process frequency density surfaces. We solve the generalised Fourier transform with such a model, and present a family of non-…