We study the problem of selecting a subset from a large action space shared by a family of bandits, with the goal of achieving performance nearly matching that of using the full action space. We assume that similar actions tend to have related payoffs, modeled by a Gaussian process. To exploit this structure, we propose a simple epsilon-net algorithm to select a representative subset. We provide theoretical guarantees for its performance and compare it empirically to Thompson Sampling and Upper Confidence Bound.
Protein fitness optimization involves finding a protein sequence that maximizes desired quantitative properties in a combinatorially large design space of possible sequences. Recent developments in steering protein generative models (e.g diffusion models, language models) offer a promising approach. However, by and large, past studies have optimized surrogate rewards and/or utilized large amounts of labeled data for steering, making it unclear how well existing methods perform and compare to each other in real-world optimization campaigns where fitness is measured by low-throughput wet-lab assays. In this study, we explore fitness optimization using small amounts (hundreds) of labeled sequence-fitness pairs and comprehensively evaluate strategies such as classifier guidance and posterior sampling for guiding generation from different discrete diffusion models of protein sequences. We also demonstrate how guidance can be integrated into adaptive sequence selection akin to Thompson sampling in Bayesian optimization, showing that plug-and-play guidance strategies offer advantages compared to alternatives such as reinforcement learning with protein language models.
Diffusion models have shown significant potential in generating oracle items that best match user preference with guidance from user historical interaction sequences. However, the quality of guidance is often compromised by unpredictable missing data in observed sequence, leading to suboptimal item generation. Since missing data is uncertain in both occurrence and content, recovering it is impractical and may introduce additional errors. To tackle this challenge, we propose a novel dual-side Thompson sampling-based Diffusion Model (TDM), which simulates extra missing data in the guidance signals and allows diffusion models to handle existing missing data through extrapolation. To preserve user preference evolution in sequences despite extra missing data, we introduce Dual-side Thompson Sampling to implement simulation with two probability models, sampling by exploiting user preference from both item continuity and sequence stability. TDM strategically removes items from sequences based on dual-side Thompson sampling and treats these edited sequences as guidance for diffusion models, enhancing models' robustness to missing data through consistency regularization. Additionally, to enhance the generation efficiency, TDM is implemented under the denoising diffusion implicit models to accelerate the reverse process. Extensive experiments and theoretical analysis validate the effectiveness of TDM in addressing missing data in sequential recommendations.
In this study, we investigate the problem of dynamic multi-product selection and pricing by introducing a novel framework based on a \textit{censored multinomial logit} (C-MNL) choice model. In this model, sellers present a set of products with prices, and buyers filter out products priced above their valuation, purchasing at most one product from the remaining options based on their preferences. The goal is to maximize seller revenue by dynamically adjusting product offerings and prices, while learning both product valuations and buyer preferences through purchase feedback. To achieve this, we propose a Lower Confidence Bound (LCB) pricing strategy. By combining this pricing strategy with either an Upper Confidence Bound (UCB) or Thompson Sampling (TS) product selection approach, our algorithms achieve regret bounds of $\tilde{O}(d^{\frac{3}{2}}\sqrt{T/\kappa})$ and $\tilde{O}(d^{2}\sqrt{T/\kappa})$, respectively. Finally, we validate the performance of our methods through simulations, demonstrating their effectiveness.
Prompt optimization aims to search for effective prompts that enhance the performance of large language models (LLMs). Although existing prompt optimization methods have discovered effective prompts, they often differ from sophisticated prompts carefully designed by human experts. Prompt design strategies, representing best practices for improving prompt performance, can be key to improving prompt optimization. Recently, a method termed the Autonomous Prompt Engineering Toolbox (APET) has incorporated various prompt design strategies into the prompt optimization process. In APET, the LLM is needed to implicitly select and apply the appropriate strategies because prompt design strategies can have negative effects. This implicit selection may be suboptimal due to the limited optimization capabilities of LLMs. This paper introduces Optimizing Prompts with sTrategy Selection (OPTS), which implements explicit selection mechanisms for prompt design. We propose three mechanisms, including a Thompson sampling-based approach, and integrate them into EvoPrompt, a well-known prompt optimizer. Experiments optimizing prompts for two LLMs, Llama-3-8B-Instruct and GPT-4o mini, were conducted using BIG-Bench Hard. Our results show that the selection of prompt design strategies improves the performance of EvoPrompt, and the Thompson sampling-based mechanism achieves the best overall results. Our experimental code is provided at https://github.com/shiralab/OPTS .
Existing actor-critic algorithms, which are popular for continuous control reinforcement learning (RL) tasks, suffer from poor sample efficiency due to lack of principled exploration mechanism within them. Motivated by the success of Thompson sampling for efficient exploration in RL, we propose a novel model-free RL algorithm, Langevin Soft Actor Critic (LSAC), which prioritizes enhancing critic learning through uncertainty estimation over policy optimization. LSAC employs three key innovations: approximate Thompson sampling through distributional Langevin Monte Carlo (LMC) based $Q$ updates, parallel tempering for exploring multiple modes of the posterior of the $Q$ function, and diffusion synthesized state-action samples regularized with $Q$ action gradients. Our extensive experiments demonstrate that LSAC outperforms or matches the performance of mainstream model-free RL algorithms for continuous control tasks. Notably, LSAC marks the first successful application of an LMC based Thompson sampling in continuous control tasks with continuous action spaces.
Bayesian bandit algorithms with approximate Bayesian inference have been widely used in real-world applications. However, there is a large discrepancy between the superior practical performance of these approaches and their theoretical justification. Previous research only indicates a negative theoretical result: Thompson sampling could have a worst-case linear regret $\Omega(T)$ with a constant threshold on the inference error measured by one $\alpha$-divergence. To bridge this gap, we propose an Enhanced Bayesian Upper Confidence Bound (EBUCB) framework that can efficiently accommodate bandit problems in the presence of approximate inference. Our theoretical analysis demonstrates that for Bernoulli multi-armed bandits, EBUCB can achieve the optimal regret order $O(\log T)$ if the inference error measured by two different $\alpha$-divergences is less than a constant, regardless of how large this constant is. To our best knowledge, our study provides the first theoretical regret bound that is better than $o(T)$ in the setting of constant approximate inference error. Furthermore, in concordance with the negative results in previous studies, we show that only one bounded $\alpha$-divergence is insufficient to guarantee a sub-linear regret.
We propose a novel linear bandit algorithm called LinMED (Linear Minimum Empirical Divergence), which is a linear extension of the MED algorithm that was originally designed for multi-armed bandits. LinMED is a randomized algorithm that admits a closed-form computation of the arm sampling probabilities, unlike the popular randomized algorithm called linear Thompson sampling. Such a feature proves useful for off-policy evaluation where the unbiased evaluation requires accurately computing the sampling probability. We prove that LinMED enjoys a near-optimal regret bound of $d\sqrt{n}$ up to logarithmic factors where $d$ is the dimension and $n$ is the time horizon. We further show that LinMED enjoys a $\frac{d^2}{\Delta}\left(\log^2(n)\right)\log\left(\log(n)\right)$ problem-dependent regret where $\Delta$ is the smallest sub-optimality gap, which is lower than $\frac{d^2}{\Delta}\log^3(n)$ of the standard algorithm OFUL (Abbasi-yadkori et al., 2011). Our empirical study shows that LinMED has a competitive performance with the state-of-the-art algorithms.
We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the frame of contextual dueling bandits. This formulation, subsuming recent paradigms such as online RLHF and online DPO, inherently quests for sample-efficient algorithms that incorporate online active exploration. Leveraging insights from bandit theory, we introduce a unified algorithm based on Thompson sampling and highlight its applications in two distinct LLM alignment scenarios. The practical agent that efficiently implements this algorithm, named SEA (Sample-Efficient Alignment), is empirically validated through extensive experiments across three model scales (1B, 2.8B, 6.9B) and three preference learning algorithms (DPO, IPO, SLiC). The results demonstrate that SEA achieves highly sample-efficient alignment with oracle's preferences, outperforming recent active exploration methods for LLMs. Additionally, we release the implementation of SEA together with an efficient codebase designed for online alignment of LLMs, aiming to accelerate future research in this field.
Bayesian optimization devolves the global optimization of a costly objective function to the global optimization of a sequence of acquisition functions. This inner-loop optimization can be catastrophically difficult if it involves posterior sample paths, especially in higher dimensions. We introduce an efficient global optimization strategy for posterior samples based on global rootfinding. It provides gradient-based optimizers with two sets of judiciously selected starting points, designed to combine exploration and exploitation. The number of starting points can be kept small without sacrificing optimization quality. Remarkably, even with just one point from each set, the global optimum is discovered most of the time. The algorithm scales practically linearly to high dimensions, breaking the curse of dimensionality. For Gaussian process Thompson sampling (GP-TS), we demonstrate remarkable improvement in both inner- and outer-loop optimization, surprisingly outperforming alternatives like EI and GP-UCB in most cases. Our approach also improves the performance of other posterior sample-based acquisition functions, such as variants of entropy search. Furthermore, we propose a sample-average formulation of GP-TS, which has a parameter to explicitly control exploitation and can be computed at the cost of one posterior sample. Our implementation is available at https://github.com/UQUH/TSRoots .
In Bayesian optimization, a black-box function is maximized via the use of a surrogate model. We apply distributed Thompson sampling, using a Gaussian process as a surrogate model, to approach the multi-agent Bayesian optimization problem. In our distributed Thompson sampling implementation, each agent receives sampled points from neighbors, where the communication network is encoded in a graph; each agent utilizes their own Gaussian process to model the objective function. We demonstrate theoretical bounds on Bayesian average regret and Bayesian simple regret, where the bound depends on the structure of the communication graph. Unlike in batch Bayesian optimization, this bound is applicable in cases where the communication graph amongst agents is constrained. When compared to sequential single-agent Thompson sampling, our bound guarantees faster convergence with respect to time as long as the communication graph is connected. We confirm the efficacy of our algorithm with numerical simulations on traditional optimization test functions, demonstrating the significance of graph connectivity on improving regret convergence.
In this study, we consider multi-class multi-server asymmetric queueing systems consisting of $N$ queues on one side and $K$ servers on the other side, where jobs randomly arrive in queues at each time. The service rate of each job-server assignment is unknown and modeled by a feature-based Multi-nomial Logit (MNL) function. At each time, a scheduler assigns jobs to servers, and each server stochastically serves at most one job based on its preferences over the assigned jobs. The primary goal of the algorithm is to stabilize the queues in the system while learning the service rates of servers. To achieve this goal, we propose algorithms based on UCB and Thompson Sampling, which achieve system stability with an average queue length bound of $O(\min\{N,K\}/\epsilon)$ for a large time horizon $T$, where $\epsilon$ is a traffic slackness of the system. Furthermore, the algorithms achieve sublinear regret bounds of $\tilde{O}(\min\{\sqrt{T} Q_{\max},T^{3/4}\})$, where $Q_{\max}$ represents the maximum queue length over agents and times. Lastly, we provide experimental results to demonstrate the performance of our algorithms.
We consider Thompson Sampling (TS) for linear combinatorial semi-bandits and subgaussian rewards. We propose the first known TS whose finite-time regret does not scale exponentially with the dimension of the problem. We further show the "mismatched sampling paradox": A learner who knows the rewards distributions and samples from the correct posterior distribution can perform exponentially worse than a learner who does not know the rewards and simply samples from a well-chosen Gaussian posterior. The code used to generate the experiments is available at https://github.com/RaymZhang/CTS-Mismatched-Paradox
Batched Bayesian optimization (BO) can accelerate molecular design by efficiently identifying top-performing compounds from a large chemical library. Existing acquisition strategies for batch design in BO aim to balance exploration and exploitation. This often involves optimizing non-additive batch acquisition functions, necessitating approximation via myopic construction and/or diversity heuristics. In this work, we propose an acquisition strategy for discrete optimization that is motivated by pure exploitation, qPO (multipoint Probability of Optimality). qPO maximizes the probability that the batch includes the true optimum, which is expressible as the sum over individual acquisition scores and thereby circumvents the combinatorial challenge of optimizing a batch acquisition function. We differentiate the proposed strategy from parallel Thompson sampling and discuss how it implicitly captures diversity. Finally, we apply our method to the model-guided exploration of large chemical libraries and provide empirical evidence that it is competitive with and complements other state-of-the-art methods in batched Bayesian optimization.
In Reinforcement Learning (RL), multi-armed Bandit (MAB) problems have found applications across diverse domains such as recommender systems, healthcare, and finance. Traditional MAB algorithms typically assume stationary reward distributions, which limits their effectiveness in real-world scenarios characterized by non-stationary dynamics. This paper addresses this limitation by introducing and evaluating novel Bandit algorithms designed for non-stationary environments. First, we present the Adaptive Discounted Thompson Sampling (ADTS) algorithm, which enhances adaptability through relaxed discounting and sliding window mechanisms to better respond to changes in reward distributions. We then extend this approach to the Portfolio Optimization problem by introducing the Combinatorial Adaptive Discounted Thompson Sampling (CADTS) algorithm, which addresses computational challenges within Combinatorial Bandits and improves dynamic asset allocation. Additionally, we propose a novel architecture called Bandit Networks, which integrates the outputs of ADTS and CADTS, thereby mitigating computational limitations in stock selection. Through extensive experiments using real financial market data, we demonstrate the potential of these algorithms and architectures in adapting to dynamic environments and optimizing decision-making processes. For instance, the proposed bandit network instances present superior performance when compared to classic portfolio optimization approaches, such as capital asset pricing model, equal weights, risk parity, and Markovitz, with the best network presenting an out-of-sample Sharpe Ratio 20% higher than the best performing classical model.
Anytime multi-agent path finding (MAPF) is a promising approach to scalable path optimization in multi-agent systems. MAPF-LNS, based on Large Neighborhood Search (LNS), is the current state-of-the-art approach where a fast initial solution is iteratively optimized by destroying and repairing selected paths of the solution. Current MAPF-LNS variants commonly use an adaptive selection mechanism to choose among multiple destroy heuristics. However, to determine promising destroy heuristics, MAPF-LNS requires a considerable amount of exploration time. As common destroy heuristics are non-adaptive, any performance bottleneck caused by these heuristics cannot be overcome via adaptive heuristic selection alone, thus limiting the overall effectiveness of MAPF-LNS in terms of solution cost. In this paper, we propose Adaptive Delay-based Destroy-and-Repair Enhanced with Success-based Self-Learning (ADDRESS) as a single-destroy-heuristic variant of MAPF-LNS. ADDRESS applies restricted Thompson Sampling to the top-K set of the most delayed agents to select a seed agent for adaptive LNS neighborhood generation. We evaluate ADDRESS in multiple maps from the MAPF benchmark set and demonstrate cost improvements by at least 50% in large-scale scenarios with up to a thousand agents, compared with the original MAPF-LNS and other state-of-the-art methods.
The optimization of yields in multi-reactor systems, which are advanced tools in heterogeneous catalysis research, presents a significant challenge due to hierarchical technical constraints. To this respect, this work introduces a novel approach called process-constrained batch Bayesian optimization via Thompson sampling (pc-BO-TS) and its generalized hierarchical extension (hpc-BO-TS). This method, tailored for the efficiency demands in multi-reactor systems, integrates experimental constraints and balances between exploration and exploitation in a sequential batch optimization strategy. It offers an improvement over other Bayesian optimization methods. The performance of pc-BO-TS and hpc-BO-TS is validated in synthetic cases as well as in a realistic scenario based on data obtained from high-throughput experiments done on a multi-reactor system available in the REALCAT platform. The proposed methods often outperform other sequential Bayesian optimizations and existing process-constrained batch Bayesian optimization methods. This work proposes a novel approach to optimize the yield of a reaction in a multi-reactor system, marking a significant step forward in digital catalysis and generally in optimization methods for chemical engineering.
Thompson Sampling is a principled method for balancing exploration and exploitation, but its real-world adoption faces computational challenges in large-scale or non-conjugate settings. While ensemble-based approaches offer partial remedies, they typically require prohibitively large ensemble sizes. We propose Ensemble++, a scalable exploration framework using a novel shared-factor ensemble architecture with random linear combinations. For linear bandits, we provide theoretical guarantees showing that Ensemble++ achieves regret comparable to exact Thompson Sampling with only $\Theta(d \log T)$ ensemble sizes--significantly outperforming prior methods. Crucially, this efficiency holds across both compact and finite action sets with either time-invariant or time-varying contexts without configuration changes. We extend this theoretical foundation to nonlinear rewards by replacing fixed features with learnable neural representations while preserving the same incremental update principle, effectively bridging theory and practice for real-world tasks. Comprehensive experiments across linear, quadratic, neural, and GPT-based contextual bandits validate our theoretical findings and demonstrate Ensemble++'s superior regret-computation tradeoff versus state-of-the-art methods.
Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to implement and not generalizable to Deep RL. While the emerging approximate sampling-based exploration schemes are promising, most existing algorithms are specific to linear Markov Decision Processes (MDP) with suboptimal regret bounds, or only use the most basic samplers such as Langevin Monte Carlo. In this work, we propose an algorithmic framework that incorporates different approximate sampling methods with the recently proposed Feel-Good Thompson Sampling (FGTS) approach (Zhang, 2022; Dann et al., 2021), which was previously known to be computationally intractable in general. When applied to linear MDPs, our regret analysis yields the best known dependency of regret on dimensionality, surpassing existing randomized algorithms. Additionally, we provide explicit sampling complexity for each employed sampler. Empirically, we show that in tasks where deep exploration is necessary, our proposed algorithms that combine FGTS and approximate sampling perform significantly better compared to other strong baselines. On several challenging games from the Atari 57 suite, our algorithms achieve performance that is either better than or on par with other strong baselines from the deep RL literature.
The combination of Monte Carlo tree search and neural networks has revolutionized online planning. As neural network approximations are often imperfect, we ask whether uncertainty estimates about the network outputs could be used to improve planning. We develop a Bayesian planning approach that facilitates such uncertainty quantification, inspired by classical ideas from the meta-reasoning literature. We propose a Thompson sampling based algorithm for searching the tree of possible actions, for which we prove the first (to our knowledge) finite time Bayesian regret bound, and propose an efficient implementation for a restricted family of posterior distributions. In addition we propose a variant of the Bayes-UCB method applied to trees. Empirically, we demonstrate that on the ProcGen Maze and Leaper environments, when the uncertainty estimates are accurate but the neural network output is inaccurate, our Bayesian approach searches the tree much more effectively. In addition, we investigate whether popular uncertainty estimation methods are accurate enough to yield significant gains in planning. Our code is available at: https://github.com/nirgreshler/bayesian-online-planning.