A Tractable Online Learning Algorithm for the Multinomial Logit Contextual Bandit

• URL: http://arxiv.org/abs/2011.14033v7
• Date: Sun, 14 Apr 2024 14:47:24 GMT
• Title: A Tractable Online Learning Algorithm for the Multinomial Logit Contextual Bandit
• Authors: Priyank Agrawal, Theja Tulabandhula, Vashist Avadhanula,
• Abstract summary: We consider a dynamic set optimization problem, where a decision-maker offers a subset of products to a consumer. We model consumer choice behavior using the widely used Multinomial Logit (MNL) model. We show that the regret is bounded by $O(sqrtdT + kappa)$, significantly improving the performance over existing methods.
• Score: 2.9998316151418107
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we consider the contextual variant of the MNL-Bandit problem. More specifically, we consider a dynamic set optimization problem, where a decision-maker offers a subset (assortment) of products to a consumer and observes the response in every round. Consumers purchase products to maximize their utility. We assume that a set of attributes describe the products, and the mean utility of a product is linear in the values of these attributes. We model consumer choice behavior using the widely used Multinomial Logit (MNL) model and consider the decision maker problem of dynamically learning the model parameters while optimizing cumulative revenue over the selling horizon $T$. Though this problem has attracted considerable attention in recent times, many existing methods often involve solving an intractable non-convex optimization problem. Their theoretical performance guarantees depend on a problem-dependent parameter which could be prohibitively large. In particular, existing algorithms for this problem have regret bounded by $O(\sqrt{\kappa d T})$, where $\kappa$ is a problem-dependent constant that can have an exponential dependency on the number of attributes. In this paper, we propose an optimistic algorithm and show that the regret is bounded by $O(\sqrt{dT} + \kappa)$, significantly improving the performance over existing methods. Further, we propose a convex relaxation of the optimization step, which allows for tractable decision-making while retaining the favourable regret guarantee.

Related papers

• Projection-free Algorithms for Online Convex Optimization with Adversarial Constraints [10.047668792033033]
  We study a generalization of the Online Convex Optimization (OCO) framework with time-varying adversarial constraints. In this problem, after selecting a feasible action from the convex decision set $X,$ a convex constraint function is revealed alongside the cost function in each round. We propose a *projection-free* online policy which makes a single call to a Linear Program (LP) solver per round.
  arXiv  Detail & Related papers  (2025-01-28T13:04:32Z)
• Minimax Optimality in Contextual Dynamic Pricing with General Valuation Models [4.156757591117864]
  We propose a novel algorithm that achieves improved regret bounds while minimizing assumptions about the problem. Our method extends beyond linear valuation models commonly used in dynamic pricing by considering general function spaces.
  arXiv  Detail & Related papers  (2024-06-24T23:43:56Z)
• Stop Relying on No-Choice and Do not Repeat the Moves: Optimal, Efficient and Practical Algorithms for Assortment Optimization [38.57171985309975]
  We develop efficient algorithms for the problem of regret in assortment selection with emphPlackett Luce (PL) based user choices. Our methods are practical, provably optimal, and devoid of the aforementioned limitations of the existing methods.
  arXiv  Detail & Related papers  (2024-02-29T07:17:04Z)
• End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty [55.04219793298687]
  The Predict-Then-Forecast (PtO) paradigm in machine learning aims to maximize downstream decision quality. This paper extends the PtO methodology to optimization problems with nondifferentiable Ordered Weighted Averaging (OWA) objectives. It shows how optimization of OWA functions can be effectively integrated with parametric prediction for fair and robust optimization under uncertainty.
  arXiv  Detail & Related papers  (2024-02-12T16:33:35Z)
• Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency [90.40062452292091]
  We present the first computationally efficient algorithm for linear bandits with heteroscedastic noise. Our algorithm is adaptive to the unknown variance of noise and achieves an $tildeO(d sqrtsum_k = 1K sigma_k2 + d)$ regret. We also propose a variance-adaptive algorithm for linear mixture Markov decision processes (MDPs) in reinforcement learning.
  arXiv  Detail & Related papers  (2023-02-21T00:17:24Z)
• Symmetric Tensor Networks for Generative Modeling and Constrained Combinatorial Optimization [72.41480594026815]
  Constrained optimization problems abound in industry, from portfolio optimization to logistics. One of the major roadblocks in solving these problems is the presence of non-trivial hard constraints which limit the valid search space. In this work, we encode arbitrary integer-valued equality constraints of the form Ax=b, directly into U(1) symmetric networks (TNs) and leverage their applicability as quantum-inspired generative models.
  arXiv  Detail & Related papers  (2022-11-16T18:59:54Z)
• Markov Decision Process modeled with Bandits for Sequential Decision Making in Linear-flow [73.1896399783641]
  In membership/subscriber acquisition and retention, we sometimes need to recommend marketing content for multiple pages in sequence. We propose to formulate the problem as an MDP with Bandits where Bandits are employed to model the transition probability matrix. We observe the proposed MDP with Bandits algorithm outperforms Q-learning with $epsilon$-greedy and decreasing $epsilon$, independent Bandits, and interaction Bandits.
  arXiv  Detail & Related papers  (2021-07-01T03:54:36Z)
• Online Model Selection for Reinforcement Learning with Function Approximation [50.008542459050155]
  We present a meta-algorithm that adapts to the optimal complexity with $tildeO(L5/6 T2/3)$ regret. We also show that the meta-algorithm automatically admits significantly improved instance-dependent regret bounds.
  arXiv  Detail & Related papers  (2020-11-19T10:00:54Z)
• Alternating Direction Method of Multipliers for Quantization [15.62692130672419]
  We study the performance of the Alternating Direction Method of Multipliers for Quantization ($texttADMM-Q$) algorithm. We develop a few variants of $texttADMM-Q$ that can handle inexact update rules. We empirically evaluate the efficacy of our proposed approaches.
  arXiv  Detail & Related papers  (2020-09-08T01:58:02Z)
• Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation [107.06364966905821]
  We study the exploration-exploitation dilemma in the linear quadratic regulator (LQR) setting. Inspired by the extended value iteration algorithm used in optimistic algorithms for finite MDPs, we propose to relax the optimistic optimization of ofulq. We show that an $epsilon$-optimistic controller can be computed efficiently by solving at most $Obig(log (1/epsilon)big)$ Riccati equations.
  arXiv  Detail & Related papers  (2020-07-13T16:30:47Z)
• Constrained Multiagent Rollout and Multidimensional Assignment with the Auction Algorithm [0.0]
  We consider an extension of the rollout algorithm that applies to constrained deterministic dynamic programming. We show that if the base produces a feasible solution, the rollout algorithm has a cost improvement property. We show that the cost improvement property is maintained with an alternative implementation that has greatly reduced computational requirements.
  arXiv  Detail & Related papers  (2020-02-18T07:09:06Z)

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.