Solving Inverse Problem for Multi-armed Bandits via Convex Optimization

• URL: http://arxiv.org/abs/2501.18945v3
• Date: Thu, 26 Jun 2025 10:49:32 GMT
• Title: Solving Inverse Problem for Multi-armed Bandits via Convex Optimization
• Abstract summary: We consider the inverse problem of multi-armed bandits (IMAB) that are widely used in neuroscience and psychology research for behavior modelling.<n>We first show that the IMAB problem is not convex in general, but can be relaxed to a convex problem via variable transformation.<n>We discuss a condition where our method provides global solution to the IMAB problem with certificate, as well as approximations to further save computing time.
• Score: 10.218348617571257
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider the inverse problem of multi-armed bandits (IMAB) that are widely used in neuroscience and psychology research for behavior modelling. We first show that the IMAB problem is not convex in general, but can be relaxed to a convex problem via variable transformation. Based on this result, we propose a two-step sequential heuristic for (approximately) solving the IMAB problem. We discuss a condition where our method provides global solution to the IMAB problem with certificate, as well as approximations to further save computing time. Numerical experiments indicate that our heuristic method is more robust than directly solving the IMAB problem via repeated local optimization, and can achieve the performance of Monte Carlo methods within a significantly decreased running time. We provide the implementation of our method based on CVXPY, which allows straightforward application by users not well versed in convex optimization.

Related papers

• Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe [61.68406997155879]
  State-of-the-art Large Language Model (LLM) pruning methods operate layer-wise, minimizing the per-layer pruning error on a small dataset to avoid full retraining.<n>Existing methods hence rely on greedy convexs that ignore the weight interactions in the pruning objective.<n>Our method drastically reduces the per-layer pruning error, outperforms strong baselines on state-of-the-art GPT architectures, and remains memory-efficient.
  arXiv  Detail & Related papers  (2025-10-15T16:13:44Z)
• Towards graph neural networks for provably solving convex optimization problems [5.966097889241178]
  We propose an iterative MPNN framework to solve convex optimization problems with provable feasibility guarantees. Experimental results show that our approach outperforms existing neural baselines in solution quality and feasibility.
  arXiv  Detail & Related papers  (2025-02-04T16:11:41Z)
• Non-Myopic Multi-Objective Bayesian Optimization [64.31753000439514]
  We consider the problem of finite-horizon sequential experimental design to solve multi-objective optimization problems.<n>This problem arises in many real-world applications, including materials design.<n>We propose the first set of non-myopic methods for MOO problems.
  arXiv  Detail & Related papers  (2024-12-11T04:05:29Z)
• Feature selection in linear SVMs via a hard cardinality constraint: a scalable SDP decomposition approach [3.7876216422538485]
  We study the embedded feature selection problem in linear Support Vector Machines (SVMs) in which a cardinality constraint is employed.<n>The problem is NP-hard due to the presence of the cardinality constraint, even though the original linear SVM amounts to a solvable problem in time.<n>To handle the hard problem, we first introduce two mixed-integer formulations for which novel semidefinite relaxations are proposed.
  arXiv  Detail & Related papers  (2024-04-15T19:15:32Z)
• Best Arm Identification with Fixed Budget: A Large Deviation Perspective [54.305323903582845]
  We present sred, a truly adaptive algorithm that can reject arms in it any round based on the observed empirical gaps between the rewards of various arms. In particular, we present sred, a truly adaptive algorithm that can reject arms in it any round based on the observed empirical gaps between the rewards of various arms.
  arXiv  Detail & Related papers  (2023-12-19T13:17:43Z)
• Moreau Envelope ADMM for Decentralized Weakly Convex Optimization [55.2289666758254]
  This paper proposes a proximal variant of the alternating direction method of multipliers (ADMM) for distributed optimization. The results of our numerical experiments indicate that our method is faster and more robust than widely-used approaches.
  arXiv  Detail & Related papers  (2023-08-31T14:16:30Z)
• Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior [0.0]
  We address the problem of solving ill-posed inverse problems in imaging where the prior is a JPal autoencoder (VAE) We show that our technique is quite sufficient that it satisfies the proposed objective function. Results also show the robustness of our approach to provide more robust estimates.
  arXiv  Detail & Related papers  (2021-03-02T11:18:34Z)
• Parallel Stochastic Mirror Descent for MDPs [72.75921150912556]
  We consider the problem of learning the optimal policy for infinite-horizon Markov decision processes (MDPs) Some variant of Mirror Descent is proposed for convex programming problems with Lipschitz-continuous functionals. We analyze this algorithm in a general case and obtain an estimate of the convergence rate that does not accumulate errors during the operation of the method.
  arXiv  Detail & Related papers  (2021-02-27T19:28:39Z)
• A Hybrid Framework Using a QUBO Solver For Permutation-Based Combinatorial Optimization [5.460573052311485]
  We propose a hybrid framework to solve large-scale permutation-based problems using a high-performance quadratic unconstrained binary optimization solver. We propose techniques to overcome the challenges in using a QUBO solver that typically comes with limited numbers of bits.
  arXiv  Detail & Related papers  (2020-09-27T07:15:25Z)
• Conditional gradient methods for stochastically constrained convex minimization [54.53786593679331]
  We propose two novel conditional gradient-based methods for solving structured convex optimization problems. The most important feature of our framework is that only a subset of the constraints is processed at each iteration. Our algorithms rely on variance reduction and smoothing used in conjunction with conditional gradient steps, and are accompanied by rigorous convergence guarantees.
  arXiv  Detail & Related papers  (2020-07-07T21:26:35Z)
• Stochastic gradient algorithms from ODE splitting perspective [0.0]
  We present a different view on optimization, which goes back to the splitting schemes for approximate solutions of ODE. In this work, we provide a connection between descent approach and gradient first-order splitting scheme for ODE. We consider the special case of splitting, which is inspired by machine learning applications and derive a new upper bound on the global splitting error for it.
  arXiv  Detail & Related papers  (2020-04-19T22:45:32Z)
• GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction [69.94831587339539]
  We present a modified Cross-Entropy Method (CEM) that uses a masked auto-regressive neural network for modeling uniform distributions over the solution space. Our algorithm is able to express complicated solution spaces, thus allowing it to track a variety of different solution regions.
  arXiv  Detail & Related papers  (2020-02-17T20:21:20Z)

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.