Mean-based algorithms: A lower bound and regret

• URL: http://arxiv.org/abs/2606.04931v1
• Date: Wed, 03 Jun 2026 14:23:41 GMT
• Title: Mean-based algorithms: A lower bound and regret
• Abstract summary: Mean-based algorithms assign low probability to actions with low average rewards.<n>We study mean-based algorithms when the time horizon is unknown and only bandit feedback is available.<n>Experiments show that mean-based algorithms, although slightly slower, can perform competitively with other bandit-feedback algorithms.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mean-based algorithms are a class of online learning algorithms that assign low probability to actions with low average rewards. Recent work indicates these algorithms converge favorably to serially undominated actions, which approximate Nash equilibria in economic games. However, empirical studies also show slower convergence compared to established algorithms in bandit-feedback scenarios. We study mean-based algorithms when the time horizon is unknown and only bandit feedback is available. In this setting, we provide the first lower bound on the algorithm-defining sequence $γ_t$ that formally establishes a limit on how fast these algorithms can learn. Additionally, we propose two mean-based algorithms: one generalizes $ε$-greedy, and the other extends the mean-based Exp3 to unknown horizons. Our experiments show that mean-based algorithms, although slightly slower, can perform competitively with other bandit-feedback algorithms. We further analyze the relationship to no-regret algorithms. Depending on the choice of $γ_t$, the intersection with no-regret algorithms is non-trivial, and we show that algorithms exist that are both mean-based and no-regret. This adds context to the "exploitability" of this class of algorithms that previous contributions suggest.

Related papers

• Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards [40.99322897009357]
  We propose two novel algorithms based on truncation and mean of medians. Our truncation-based algorithm supports online learning, distinguishing it from existing truncation-based approaches. Our algorithms improve the regret bounds by a logarithmic factor compared to existing algorithms when $epsilon=1$.
  arXiv  Detail & Related papers  (2023-10-28T13:01:10Z)
• On Universally Optimal Algorithms for A/B Testing [49.429419538826444]
  We study the problem of best-arm identification with fixed budget in multi-armed bandits with Bernoulli rewards. For the problem with two arms, also known as the A/B testing problem, we prove that there is no algorithm that performs as well as the algorithm sampling each arm equally.
  arXiv  Detail & Related papers  (2023-08-23T08:38:53Z)
• Causal Bandits without Graph Learning [28.021500949026766]
  We develop an efficient algorithm for finding the parent node of the reward node using atomic interventions. We extend our algorithm to the case when the reward node has multiple parents.
  arXiv  Detail & Related papers  (2023-01-26T20:27:14Z)
• Critic Algorithms using Cooperative Networks [0.0]
  An algorithm is proposed for policy evaluation in Markov Decision Processes. The algorithm tracks the Projected Bellman Error and is implemented as a true gradient based algorithm.
  arXiv  Detail & Related papers  (2022-01-19T19:47:18Z)
• Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers [12.09273192079783]
  We consider interactive learning in the realizable setting and develop a general framework to handle problems ranging from best arm identification to active classification. We design novel computationally efficient algorithms for the realizable setting that match the minimax lower bound up to logarithmic factors.
  arXiv  Detail & Related papers  (2021-11-09T02:33:36Z)
• Machine Learning for Online Algorithm Selection under Censored Feedback [71.6879432974126]
  In online algorithm selection (OAS), instances of an algorithmic problem class are presented to an agent one after another, and the agent has to quickly select a presumably best algorithm from a fixed set of candidate algorithms. For decision problems such as satisfiability (SAT), quality typically refers to the algorithm's runtime. In this work, we revisit multi-armed bandit algorithms for OAS and discuss their capability of dealing with the problem. We adapt them towards runtime-oriented losses, allowing for partially censored data while keeping a space- and time-complexity independent of the time horizon.
  arXiv  Detail & Related papers  (2021-09-13T18:10:52Z)
• Corralling Stochastic Bandit Algorithms [54.10645564702416]
  We show that the regret of the corralling algorithms is no worse than that of the best algorithm containing the arm with the highest reward. We show that the gap between the highest reward and other rewards depends on the gap between the highest reward and other rewards.
  arXiv  Detail & Related papers  (2020-06-16T15:33:12Z)
• Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds [48.312484940846]
  We revisit the problem of online learning with sleeping experts/bandits. In each time step, only a subset of the actions are available for the algorithm to choose from. We give an algorithm that provides a no-approximate-regret guarantee for the general sleeping expert/bandit problems.
  arXiv  Detail & Related papers  (2020-03-07T02:13:21Z)
• Model Selection in Contextual Stochastic Bandit Problems [51.94632035240787]
  We develop a meta-algorithm that selects between base algorithms. We show through a lower bound that even when one of the base algorithms has $O(sqrtT)$ regret, in general it is impossible to get better than $Omega(sqrtT)$ regret.
  arXiv  Detail & Related papers  (2020-03-03T18:46:34Z)
• Lagrangian Decomposition for Neural Network Verification [148.0448557991349]
  A fundamental component of neural network verification is the computation of bounds on the values their outputs can take. We propose a novel approach based on Lagrangian Decomposition. We show that we obtain bounds comparable with off-the-shelf solvers in a fraction of their running time.
  arXiv  Detail & Related papers  (2020-02-24T17:55:10Z)

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.