Author name cluster

Guanbo 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.

4 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Efficient Randomized Experiments Using Foundation Models

Piersilvio De Bartolomeis
Javier Abad
Guanbo Wang
Konstantin Donhauser
Raymond Duch
Fanny Yang
Issa Dahabreh

Randomized experiments are the preferred approach for evaluating the effects of interventions, but they are costly and often yield estimates with substantial uncertainty. On the other hand, in silico experiments leveraging foundation models offer a cost-effective alternative that can potentially attain higher statistical precision. However, the benefits of in silico experiments come with a significant risk: statistical inferences are not valid if the models fail to accurately predict experimental responses to interventions. In this paper, we propose a novel approach that integrates the predictions from multiple foundation models with experimental data while preserving valid statistical inference. Our estimator is consistent and asymptotically normal, with asymptotic variance no larger than the standard estimator based on experimental data alone. Importantly, these statistical properties hold even when model predictions are arbitrarily biased. Empirical results across several randomized experiments show that our estimator offers substantial precision gains, equivalent to a reduction of up to 20\% in the sample size needed to match the same precision as the standard estimator based on experimental data alone.

PDF Details

NeurIPS Conference 2025 Conference Paper

Gains: Fine-grained Federated Domain Adaptation in Open Set

Zhengyi Zhong
Wenzheng Jiang
Weidong Bao
Ji Wang
Qi Wang
Guanbo Wang
Yongheng Deng
Ju Ren

Conventional federated learning (FL) assumes a closed world with a fixed total number of clients. In contrast, new clients continuously join the FL process in real-world scenarios, introducing new knowledge. This raises two critical demands: detecting new knowledge, i. e. , knowledge discovery, and integrating it into the global model, i. e. , knowledge adaptation. Existing research focuses on coarse-grained knowledge discovery, and often sacrifices source domain performance and adaptation efficiency. To this end, we propose a fine-grained federated domain adaptation approach in open set (Gains). Gains splits the model into an encoder and a classifier, empirically revealing features extracted by the encoder are sensitive to domain shifts while classifier parameters are sensitive to class increments. Based on this, we develop fine-grained knowledge discovery and contribution-driven aggregation techniques to identify and incorporate new knowledge. Additionally, an anti-forgetting mechanism is designed to preserve source domain performance, ensuring balanced adaptation. Experimental results on multi-domain datasets across three typical data-shift scenarios demonstrate that Gains significantly outperforms other baselines in performance for both source-domain and target-domain clients. Code is available at: https: //github. com/Zhong-Zhengyi/Gains.

PDF Details

TMLR Journal 2024 Journal Article

A general framework for formulating structured variable selection

Guanbo Wang
Mireille Schnitzer
Tom Chen
Rui Wang
Robert W Platt

In variable selection, a selection rule that prescribes the permissible sets of selected variables (called a "selection dictionary") is desirable due to the inherent structural constraints among the candidate variables. Such selection rules can be complex in real-world data analyses, and failing to incorporate such restrictions could not only compromise the interpretability of the model but also lead to decreased prediction accuracy. However, no general framework has been proposed to formalize selection rules and their applications, which poses a significant challenge for practitioners seeking to integrate these rules into their analyses. In this work, we establish a framework for structured variable selection that can incorporate universal structural constraints. We develop a mathematical language for constructing arbitrary selection rules, where the selection dictionary is formally defined. We demonstrate that all selection rules can be expressed as combinations of operations on constructs, facilitating the identification of the corresponding selection dictionary. We use a detailed and complex example to illustrate the developed framework. Once this selection dictionary is derived, practitioners can apply their own user-defined criteria to select the optimal model. Additionally, our framework enhances existing penalized regression methods for variable selection by providing guidance on how to appropriately group variables to achieve the desired selection rule. Furthermore, our innovative framework opens the door to establishing new $\ell_0$-based penalized regression techniques that can be tailored to respect arbitrary selection rules, thereby expanding the possibilities for more robust and tailored model development.

PDF Details

ICLR Conference 2023 Conference Paper

CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning

Sheng Yue 0001
Guanbo Wang
Wei Shao 0006
Zhaofeng Zhang
Sen Lin 0001
Ju Ren 0001
Junshan Zhang

This work aims to tackle a major challenge in offline Inverse Reinforcement Learning (IRL), namely the reward extrapolation error, where the learned reward function may fail to explain the task correctly and misguide the agent in unseen environments due to the intrinsic covariate shift. Leveraging both expert data and lower-quality diverse data, we devise a principled algorithm (namely CLARE) that solves offline IRL efficiently via integrating "conservatism" into a learned reward function and utilizing an estimated dynamics model. Our theoretical analysis provides an upper bound on the return gap between the learned policy and the expert policy, based on which we characterize the impact of covariate shift by examining subtle two-tier tradeoffs between the exploitation (on both expert and diverse data) and exploration (on the estimated dynamics model). We show that CLARE can provably alleviate the reward extrapolation error by striking the right exploitation-exploration balance therein. Extensive experiments corroborate the significant performance gains of CLARE over existing state-of-the-art algorithms on MuJoCo continuous control tasks (especially with a small offline dataset), and the learned reward is highly instructive for further learning.

Details