Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent

• URL: http://arxiv.org/abs/2605.25590v1
• Date: Mon, 25 May 2026 08:40:32 GMT
• Title: Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent
• Abstract summary: We study nonstationary linear computation (GLBs), where the expected reward is modeled through a nonlinear link function with an unknown time-varying parameter.<n>We propose a new algorithm for nonstationary GLBs that utilize discounted online mirror descent (DOMD) for parameter estimation, thereby incurring only $O(1)$ for memory costs per round.
• Score: 39.805192541498634
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We study nonstationary generalized linear bandits (GLBs), where the expected reward is modeled through a nonlinear link function with an unknown time-varying parameter. This framework encompasses a broad class of reward models, including linear, Bernoulli, and binomial rewards. Existing approaches are predominantly based on maximum-likelihood estimation (MLE), using sliding-window, restart, or discounting mechanisms to handle nonstationarity. Although these methods achieve statistically efficient regret guarantees, they generally require revisiting past observations at every round, which leads to computation and memory costs that grow with time; moreover, several of them rely on a non-convex projection step. In this paper, we propose DOMD-GLB, a new algorithm for nonstationary GLBs that utilizes discounted online mirror descent (DOMD) for parameter estimation, thereby incurring only $O(1)$ computation and memory costs per round. We prove dynamic regret bounds of order $\tilde{O} \big(c_μ^{-1/2} d^{3/4} P_T^{1/4} T^{3/4}\big)$ in drifting environments and $\tilde{O}\big(c_μ^{-1/3} d^{2/3} Γ_T^{1/3} T^{2/3}\big) $in piecewise-stationary environments, where $d$ denotes the feature dimension, $T$ the time horizon, $P_T$ the path length, $Γ_T$ the number of change points, and $c_μ$ a curvature parameter associated with the link function, while substantially improving computational efficiency over prior work. To the best of our knowledge, this is the first algorithm for nonstationary GLBs with per-round computation and memory costs independent of time.

Related papers

• Generalized Linear Bandits with Memory [30.756127188585907]
  We study generalized linear bandits with memory, an endogenous non-stationary setting in which rewards depend on past actions through a finite memory matrix.<n>We show that the previously known $tildeO(T3/4)$ regret bound stems from a loose analysis, and we provide a sharpened analysis that recovers a $tildeO(sqrtT)$ regret rate in the linear case.
  arXiv  Detail & Related papers  (2026-08-16T16:39:09Z)
• Mild Over-Parameterization Benefits Asymmetric Tensor PCA [12.923414933046574]
  Asymmetric PCA (ATPCA) is prototypical model for studying the trade-offs between sample complexity, computation, and memory.<n>We focus on the setting where $overlinek geq 4$ is even and consider descent-based algorithms under a limited memory budget.
  arXiv  Detail & Related papers  (2026-04-11T13:34:48Z)
• Statistical Inference for Linear Functionals of Online Least-squares SGD when $t \gtrsim d^{1+δ}$ [7.884611719110979]
  Gradient Descent (SGD) has become a cornerstone method in modern data science.<n>In this work, we establish emphnon-asymptotic Berry--Esseen bounds for linear functionals of online least-squares SGD.
  arXiv  Detail & Related papers  (2025-10-22T16:25:49Z)
• From Continual Learning to SGD and Back: Better Rates for Continual Linear Models [50.11453013647086]
  We analyze the forgetting, i.e., loss on previously seen tasks, after $k$ iterations.<n>We develop novel last-iterate upper bounds in the realizable least squares setup.<n>We prove for the first time that randomization alone, with no task repetition, can prevent catastrophic in sufficiently long task sequences.
  arXiv  Detail & Related papers  (2025-04-06T18:39:45Z)
• Sparse Linear Bandits with Blocking Constraints [22.01704171400845]
  We investigate the high-dimensional sparse linear bandits problem in a data-poor regime.<n>We show novel offline statistical guarantees of the lasso estimator for the linear model.<n>We propose a meta-algorithm based on corralling that does not need knowledge of optimal sparsity parameter $k$ at minimal cost to regret.
  arXiv  Detail & Related papers  (2024-10-26T01:42:03Z)
• Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path [80.60592344361073]
  We study the Shortest Path (SSP) problem with a linear mixture transition kernel. An agent repeatedly interacts with a environment and seeks to reach certain goal state while minimizing the cumulative cost. Existing works often assume a strictly positive lower bound of the iteration cost function or an upper bound of the expected length for the optimal policy.
  arXiv  Detail & Related papers  (2024-02-14T07:52:00Z)
• Revisiting Weighted Strategy for Non-stationary Parametric Bandits [82.1942459195896]
  This paper revisits the weighted strategy for non-stationary parametric bandits. We propose a refined analysis framework, which produces a simpler weight-based algorithm. Our new framework can be used to improve regret bounds of other parametric bandits.
  arXiv  Detail & Related papers  (2023-03-05T15:11:14Z)
• Pseudonorm Approachability and Applications to Regret Minimization [73.54127663296906]
  We convert high-dimensional $ell_infty$-approachability problems to low-dimensional pseudonorm approachability problems. We develop an algorithmic theory of pseudonorm approachability, analogous to previous work on approachability for $ell$ and other norms.
  arXiv  Detail & Related papers  (2023-02-03T03:19:14Z)
• Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation [25.60689712525918]
  We study reinforcement learning with linear function approximation where the transition probability and reward functions are linear. We propose a novel-efficient algorithm, LSVI-UCB$+$, which achieves an $widetildeO(HdsqrtT)$ regret bound where $H$ is the episode length, $d$ is the feature dimension, and $T$ is the number of steps.
  arXiv  Detail & Related papers  (2022-06-23T06:04:21Z)
• Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward [66.81579829897392]
  We propose a novel offline reinforcement learning algorithm called Pessimistic vAlue iteRaTion with rEward Decomposition (PARTED) PARTED decomposes the trajectory return into per-step proxy rewards via least-squares-based reward redistribution, and then performs pessimistic value based on the learned proxy reward. To the best of our knowledge, PARTED is the first offline RL algorithm that is provably efficient in general MDP with trajectory-wise reward.
  arXiv  Detail & Related papers  (2022-06-13T19:11:22Z)
• Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs [111.75736569611159]
  We propose the first computationally efficient horizon-free algorithm for linear mixture MDPs. Our algorithm adapts a weighted least square estimator for the unknown transitional dynamic. This also improves upon the best-known algorithms in this setting when $sigma_k2$'s are known.
  arXiv  Detail & Related papers  (2022-05-23T17:59:18Z)
• Variance-Aware Confidence Set: Variance-Dependent Bound for Linear Bandits and Horizon-Free Bound for Linear Mixture MDP [76.94328400919836]
  We show how to construct variance-aware confidence sets for linear bandits and linear mixture Decision Process (MDP) For linear bandits, we obtain an $widetildeO(mathrmpoly(d)sqrt1 + sum_i=1Ksigma_i2) regret bound, where $d is the feature dimension. For linear mixture MDP, we obtain an $widetildeO(mathrmpoly(d)sqrtK)$ regret bound, where
  arXiv  Detail & Related papers  (2021-01-29T18:57:52Z)
• Efficient Learning in Non-Stationary Linear Markov Decision Processes [17.296084954104415]
  We study episodic reinforcement learning in non-stationary linear (a.k.a. low-rank) Markov Decision Processes (MDPs) We propose OPT-WLSVI an optimistic model-free algorithm based on weighted least squares value which uses exponential weights to smoothly forget data that are far in the past. We show that our algorithm, when competing against the best policy at each time, achieves a regret that is upper bounded by $widetildemathcalO(d5/4H2 Delta1/4 K3/4)$ where $d$
  arXiv  Detail & Related papers  (2020-10-24T11:02:45Z)
• Truncated Linear Regression in High Dimensions [26.41623833920794]
  In truncated linear regression, $(A_i, y_i)_i$ whose dependent variable equals $y_i= A_irm T cdot x* + eta_i$ is some fixed unknown vector of interest. The goal is to recover $x*$ under some favorable conditions on the $A_i$'s and the noise distribution. We prove that there exists a computationally and statistically efficient method for recovering $k$-sparse $n$-dimensional vectors $x*$ from $m$ truncated samples.
  arXiv  Detail & Related papers  (2020-07-29T00:31:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.