Author name cluster

Shengbo Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAAI Conference 2026 Conference Paper

LAMDA: Two-Phase HPO via Learning Prior from Low-Fidelity Data

Fan Li
Shengbo Wang
Ke Li

Hyperparameter Optimization (HPO) is crucial in machine learning, aiming to optimize hyperparameters to enhance model performance. Although existing methods that leverage prior knowledge—drawn from either previous experiments or expert insights—can accelerate optimization, acquiring a correct prior for a specific HPO task is non-trivial. In this work, we propose to relieve the reliance on external knowledge by learning a reliable prior {directly} from low-fidelity (LF) problems. We introduce {Lamda}, an algorithm-agnostic framework designed to boost any baseline HPO algorithm. Specifically, {Lamda} operates in two phases: (1) it learns a reliable prior by exploring the LF landscape under limited computational budgets, and (2) it leverages this learned prior to guide the HPO process. We showcase how the {Lamda} framework can be integrated with various HPO algorithms to boost their performance, and further conduct theoretical analysis towards the integrated Bayesian optimization and bandit-based Hyperband. We conduct experiments on 56 HPO problems spanning diverse domains and model scales. Results show that {Lamda} consistently enhances its baseline algorithms. Compared to nine state-of-the-art HPO algorithms, our {Lamda} variant achieves the best performance in 51 out of 56 HPO tasks while it is the second best algorithm in the other 5 cases.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Preference Is More than Comparisons: Rethinking Dueling Bandits with Augmented Human Feedback

Shengbo Wang
Hong Sun
Ke Li

Interactive preference elicitation (IPE) aims to substantially reduce human effort while acquiring human preferences in wide personalization systems. Dueling bandit (DB) algorithms enable optimal decision-making in IPE building on pairwise comparisons. However, they remain inefficient when human feedback is sparse. Existing methods address sparsity by heavily relying on parametric reward models, whose rigid assumptions are vulnerable to misspecification. In contrast, we explore an alternative perspective based on feedback augmentation, and introduce critical improvements to the model-free DB framework. Specifically, we introduce augmented confidence bounds to integrate augmented human feedback under generalized concentration properties, and analyze the multi-factored performance trade-off via regret analysis. Our prototype algorithm achieves competitive performance across several IPE benchmarks, including recommendation, multi-objective optimization, and response optimization for large language models, demonstrating the potential of our approach for provably efficient IPE in broader applications.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning

Zijun Chen
Shengbo Wang
Nian Si

Motivated by practical applications where stable long-term performance is critical—such as robotics, operations research, and healthcare—we study the problem of distributionally robust (DR) average-reward reinforcement learning. We propose two algorithms that achieve near-optimal sample complexity. The first reduces the problem to a DR discounted Markov decision process (MDP), while the second, Anchored DR Average-Reward MDP, introduces an anchoring state to stabilize the controlled transition kernels within the uncertainty set. Assuming the nominal MDP is uniformly ergodic, we prove that both algorithms attain a sample complexity of $\widetilde{O}\left(|\mathbf{S}||\mathbf{A}| t_{\mathrm{mix}}^2\varepsilon^{-2}\right)$ for estimating the optimal policy as well as the robust average reward under KL and $f_k$-divergence-based uncertainty sets, provided the uncertainty radius is sufficiently small. Here, $\varepsilon$ is the target accuracy, $|\mathbf{S}|$ and $|\mathbf{A}|$ denote the sizes of the state and action spaces, and $t_{\mathrm{mix}}$ is the mixing time of the nominal MDP. This represents the first finite-sample convergence guarantee for DR average-reward reinforcement learning. We further validate the convergence rates of our algorithms through numerical experiments.

PDF Details

NeurIPS Conference 2024 Conference Paper

An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations

Shengbo Wang
Jose Blanchet
Peter Glynn

Overparameterized stochastic differential equation (SDE) models have achieved remarkable success in various complex environments, such as PDE-constrained optimization, stochastic control and reinforcement learning, financial engineering, and neural SDEs. These models often feature system evolution coefficients that are parameterized by a high-dimensional vector $\theta \in \mathbb{R}^n$, aiming to optimize expectations of the SDE, such as a value function, through stochastic gradient ascent. Consequently, designing efficient gradient estimators for which the computational complexity scales well with $n$ is of significant interest. This paper introduces a novel unbiased stochastic gradient estimator—the generator gradient estimator—for which the computation time remains stable in $n$. In addition to establishing the validity of our methodology for general SDEs with jumps, we also perform numerical experiments that test our estimator in linear-quadratic control problems parameterized by high-dimensional neural networks. The results show a significant improvement in efficiency compared to the widely used pathwise differentiation method: Our estimator achieves near-constant computation times, increasingly outperforms its counterpart as $n$ increases, and does so without compromising estimation variance. These empirical findings highlight the potential of our proposed methodology for optimizing SDEs in contemporary applications.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Constrained Bayesian Optimization under Partial Observations: Balanced Improvements and Provable Convergence

Shengbo Wang
Ke Li

The partially observable constrained optimization problems (POCOPs) impede data-driven optimization techniques since an infeasible solution of POCOPs can provide little information about the objective as well as the constraints. We endeavor to design an efficient and provable method for expensive POCOPs under the framework of constrained Bayesian optimization. Our method consists of two key components. Firstly, we present an improved design of the acquisition functions that introduce balanced exploration during optimization. We rigorously study the convergence properties of this design to demonstrate its effectiveness. Secondly, we propose Gaussian processes embedding different likelihoods as the surrogate model for partially observable constraints. This model leads to a more accurate representation of the feasible regions compared to traditional classification-based models. Our proposed method is empirically studied on both synthetic and real-world problems. The results demonstrate the competitiveness of our method for solving POCOPs.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandits

Tian Huang
Shengbo Wang
Ke Li

The ultimate goal of multi-objective optimization (MO) is to assist human decision-makers (DMs) in identifying solutions of interest (SOI) that optimally reconcile multiple objectives according to their preferences. Preference-based evolutionary MO (PBEMO) has emerged as a promising framework that progressively approximates SOI by involving human in the optimization-cum-decision-making process. Yet, current PBEMO approaches are prone to be inefficient and misaligned with the DM’s true aspirations, especially when inadvertently exploiting mis-calibrated reward models. This is further exacerbated when considering the stochastic nature of human feedback. This paper proposes a novel framework that navigates MO to SOI by directly leveraging human feedback without being restricted by a predefined reward model nor cumbersome model selection. Specifically, we developed a clustering-based stochastic dueling bandits algorithm that strategically scales well to high-dimensional dueling bandits, and achieves a regret of $\mathcal{O}(K^2\log T)$, where $K$ is the number of clusters and $T$ is the number of rounds. The learned preferences are then transformed into a unified probabilistic format that can be readily adapted to prevalent EMO algorithms. This also leads to a principled termination criterion that strategically manages human cognitive loads and computational budget. Experiments on $48$ benchmark test problems, including synthetic problems, RNA inverse design and protein structure prediction, fully demonstrate the effectiveness of our proposed approach.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Optimal Sample Complexity for Average Reward Markov Decision Processes

Shengbo Wang
Jose H. Blanchet
Peter W. Glynn

We resolve the open question regarding the sample complexity of policy learning for maximizing the long-run average reward associated with a uniformly ergodic Markov decision process (MDP), assuming a generative model. In this context, the existing literature provides a sample complexity upper bound of $\widetilde O(|S||A|t_{\text{mix}}^2 \epsilon^{-2})$ and a lower bound of $\Omega(|S||A|t_{\text{mix}} \epsilon^{-2})$. In these expressions, $|S|$ and $|A|$ denote the cardinalities of the state and action spaces respectively, $t_{\text{mix}}$ serves as a uniform upper limit for the total variation mixing times, and $\epsilon$ signifies the error tolerance. Therefore, a notable gap of $t_{\text{mix}}$ still remains to be bridged. Our primary contribution is the development of an estimator for the optimal policy of average reward MDPs with a sample complexity of $\widetilde O(|S||A|t_{\text{mix}}\epsilon^{-2})$. This marks the first algorithm and analysis to reach the literature's lower bound. Our new algorithm draws inspiration from ideas in Li et al. (2020), Jin \& Sidford (2021), and Wang et al. (2023). Additionally, we conduct numerical experiments to validate our theoretical findings.

Details

JMLR Journal 2024 Journal Article

Sample Complexity of Variance-Reduced Distributionally Robust Q-Learning

Shengbo Wang
Nian Si
Jose Blanchet
Zhengyuan Zhou

Dynamic decision-making under distributional shifts is of fundamental interest in theory and applications of reinforcement learning: The distribution of the environment in which the data is collected can differ from that of the environment in which the model is deployed. This paper presents two novel model-free algorithms, namely the distributionally robust Q-learning and its variance-reduced counterpart, that can effectively learn a robust policy despite distributional shifts. These algorithms are designed to efficiently approximate the $q$-function of an infinite-horizon $\gamma$-discounted robust Markov decision process with Kullback-Leibler ambiguity set to an entry-wise $\epsilon$-degree of precision. Further, the variance-reduced distributionally robust Q-learning combines the synchronous Q-learning with variance-reduction techniques to enhance its performance. Consequently, we establish that it attains a minimax sample complexity upper bound of $\tilde O(|\mathbf{S}||\mathbf{A}|(1-\gamma)^{-4}\epsilon^{-2})$, where $\mathbf{S}$ and $\mathbf{A}$ denote the state and action spaces. This is the first complexity result that is independent of the ambiguity size $\delta$, thereby providing new complexity theoretic insights. Additionally, a series of numerical experiments confirm the theoretical findings and the efficiency of the algorithms in handling distributional shifts. [abs] [ pdf ][ bib ] &copy JMLR 2024. ( edit, beta )

PDF Details