Rong Zhu

Zehua Zhao, Zhixian Huang, Junren Li et al.

Current benchmarks for evaluating the chemical reasoning capabilities of Large Language Models (LLMs) are limited by oversimplified tasks, lack of process-level evaluation, and misalignment with expert-level chemistry skills. To address these issues, we introduce SUPERChem, a benchmark of 500 expert-curated reasoning-intensive chemistry problems, covering diverse subfields and provided in both multimodal and text-only formats. Original content and an iterative curation pipeline eliminate flawed items and mitigate data contamination. Each problem is paired with an expert-authored solution path, enabling Reasoning Path Fidelity (RPF) scoring to evaluate reasoning quality beyond final-answer accuracy. Evaluations against a human baseline of 40.3% accuracy show that even the best-performing model, GPT-5 (High), reaches only 38.5%, followed closely by Gemini 2.5 Pro (37.9%) and DeepSeek-V3.1-Think (37.3%). SUPERChem elicits multi-step, multimodal reasoning, reveals model-dependent effects of visual information, and distinguishes high-fidelity reasoners from heuristic ones. By providing a challenging benchmark and a reliable evaluation framework, SUPERChem aims to facilitate the advancement of LLMs toward expert-level chemical intelligence. The dataset of the benchmark is available at https://huggingface.co/datasets/ZehuaZhao/SUPERChem.

Rong J. B. Zhu, James M. Murray

Off-policy algorithms, in which a behavior policy differs from the target policy and is used to gain experience for learning, have proven to be of great practical value in reinforcement learning. However, even for simple convex problems such as linear value function approximation, these algorithms are not guaranteed to be stable. To address this, alternative algorithms that are provably convergent in such cases have been introduced, the most well known being gradient descent temporal difference (GTD) learning. This algorithm and others like it, however, tend to converge much more slowly than conventional temporal difference learning. In this paper we propose gradient descent temporal difference-difference (Gradient-DD) learning in order to improve GTD2, a GTD algorithm, by introducing second-order differences in successive parameter updates. We investigate this algorithm in the framework of linear value function approximation, theoretically proving its convergence by applying the theory of stochastic approximation. %analytically showing its improvement over GTD2. Studying the model empirically on the random walk task, the Boyan-chain task, and the Baird's off-policy counterexample, we find substantial improvement over GTD2 and, in several cases, better performance even than conventional TD learning.

Tianjing Zeng, Junwei Lan, Jiahong Ma et al.

Cardinality estimation (CardEst) is essential for optimizing query execution plans. Recent ML-based CardEst methods achieve high accuracy but face deployment challenges due to high preparation costs and lack of transferability across databases. In this paper, we propose PRICE, a PRetrained multI-table CardEst model, which addresses these limitations. PRICE takes low-level but transferable features w.r.t. data distributions and query information and elegantly applies self-attention models to learn meta-knowledge to compute cardinality in any database. It is generally applicable to any unseen new database to attain high estimation accuracy, while its preparation cost is as little as the basic one-dimensional histogram-based CardEst methods. Moreover, PRICE can be finetuned to further enhance its performance on any specific database. We pretrained PRICE using 30 diverse datasets, completing the process in about 5 hours with a resulting model size of only about 40MB. Evaluations show that PRICE consistently outperforms existing methods, achieving the highest estimation accuracy on several unseen databases and generating faster execution plans with lower overhead. After finetuning with a small volume of databasespecific queries, PRICE could even find plans very close to the optimal ones. Meanwhile, PRICE is generally applicable to different settings such as data updates, data scaling, and query workload shifts. We have made all of our data and codes publicly available at https://github.com/StCarmen/PRICE.

Yuxing Han, Ziniu Wu, Peizhi Wu et al.

Cardinality estimation (CardEst) plays a significant role in generating high-quality query plans for a query optimizer in DBMS. In the last decade, an increasing number of advanced CardEst methods (especially ML-based) have been proposed with outstanding estimation accuracy and inference latency. However, there exists no study that systematically evaluates the quality of these methods and answer the fundamental problem: to what extent can these methods improve the performance of query optimizer in real-world settings, which is the ultimate goal of a CardEst method. In this paper, we comprehensively and systematically compare the effectiveness of CardEst methods in a real DBMS. We establish a new benchmark for CardEst, which contains a new complex real-world dataset STATS and a diverse query workload STATS-CEB. We integrate multiple most representative CardEst methods into an open-source database system PostgreSQL, and comprehensively evaluate their true effectiveness in improving query plan quality, and other important aspects affecting their applicability, ranging from inference latency, model size, and training time, to update efficiency and accuracy. We obtain a number of key findings for the CardEst methods, under different data and query settings. Furthermore, we find that the widely used estimation accuracy metric(Q-Error) cannot distinguish the importance of different sub-plan queries during query optimization and thus cannot truly reflect the query plan quality generated by CardEst methods. Therefore, we propose a new metric P-Error to evaluate the performance of CardEst methods, which overcomes the limitation of Q-Error and is able to reflect the overall end-to-end performance of CardEst methods. We have made all of the benchmark data and evaluation code publicly available at https://github.com/Nathaniel-Han/End-to-End-CardEst-Benchmark.

Rong Zhu, Mattia Rigotti

Designing efficient exploration is central to Reinforcement Learning due to the fundamental problem posed by the exploration-exploitation dilemma. Bayesian exploration strategies like Thompson Sampling resolve this trade-off in a principled way by modeling and updating the distribution of the parameters of the action-value function, the outcome model of the environment. However, this technique becomes infeasible for complex environments due to the computational intractability of maintaining probability distributions over parameters of outcome models of corresponding complexity. Moreover, the approximation techniques introduced to mitigate this issue typically result in poor exploration-exploitation trade-offs, as observed in the case of deep neural network models with approximate posterior methods that have been shown to underperform in the deep bandit scenario. In this paper we introduce Sample Average Uncertainty (SAU), a simple and efficient uncertainty measure for contextual bandits. While Bayesian approaches like Thompson Sampling estimate outcomes uncertainty indirectly by first quantifying the variability over the parameters of the outcome model, SAU is a frequentist approach that directly estimates the uncertainty of the outcomes based on the value predictions. Importantly, we show theoretically that the uncertainty measure estimated by SAU asymptotically matches the uncertainty provided by Thompson Sampling, as well as its regret bounds. Because of its simplicity SAU can be seamlessly applied to deep contextual bandits as a very scalable drop-in replacement for epsilon-greedy exploration. We confirm empirically our theory by showing that SAU-based exploration outperforms current state-of-the-art deep Bayesian bandit methods on several real-world datasets at modest computation cost. Code is available at \url{https://github.com/ibm/sau-explore}.

Rong Zhu, Tianjing Zeng, Andreas Pfadler et al.

Cardinality estimation (CardEst), a central component of the query optimizer, plays a significant role in generating high-quality query plans in DBMS. The CardEst problem has been extensively studied in the last several decades, using both traditional and ML-enhanced methods. Whereas, the hardest problem in CardEst, i.e., how to estimate the join query size on multiple tables, has not been extensively solved. Current methods either reply on independence assumptions or apply techniques with heavy burden, whose performance is still far from satisfactory. Even worse, existing CardEst methods are often designed to optimize one goal, i.e., inference speed or estimation accuracy, which can not adapt to different occasions. In this paper, we propose a very general framework, called Glue, to tackle with these challenges. Its key idea is to elegantly decouple the correlations across different tables and losslessly merge single table CardEst results to estimate the join query size. Glue supports obtaining the single table-wise CardEst results using any existing CardEst method and can process any complex join schema. Therefore, it easily adapts to different scenarios having different performance requirements, i.e., OLTP with fast estimation time or OLAP with high estimation accuracy. Meanwhile, we show that Glue can be seamlessly integrated into the plan search process and is able to support counting distinct number of values. All these properties exhibit the potential advances of deploying Glue in real-world DBMS.

Rong Zhu, Branislav Kveton

This paper studies regret minimization in a multi-armed bandit. It is well known that side information, such as the prior distribution of arm means in Thompson sampling, can improve the statistical efficiency of the bandit algorithm. While the prior is a blessing when correctly specified, it is a curse when misspecified. To address this issue, we introduce the assumption of a random-effect model to bandits. In this model, the mean arm rewards are drawn independently from an unknown distribution, which we estimate. We derive a random-effect estimator of the arm means, analyze its uncertainty, and design a UCB algorithm ReUCB that uses it. We analyze ReUCB and derive an upper bound on its $n$-round Bayes regret, which improves upon not using the random-effect structure. Our experiments show that ReUCB can outperform Thompson sampling, without knowing the prior distribution of arm means.

Ziniu Wu, Pei Yu, Peilun Yang et al.

Recently, the database management system (DBMS) community has witnessed the power of machine learning (ML) solutions for DBMS tasks. Despite their promising performance, these existing solutions can hardly be considered satisfactory. First, these ML-based methods in DBMS are not effective enough because they are optimized on each specific task, and cannot explore or understand the intrinsic connections between tasks. Second, the training process has serious limitations that hinder their practicality, because they need to retrain the entire model from scratch for a new DB. Moreover, for each retraining, they require an excessive amount of training data, which is very expensive to acquire and unavailable for a new DB. We propose to explore the transferabilities of the ML methods both across tasks and across DBs to tackle these fundamental drawbacks. In this paper, we propose a unified model MTMLF that uses a multi-task training procedure to capture the transferable knowledge across tasks and a pre-train fine-tune procedure to distill the transferable meta knowledge across DBs. We believe this paradigm is more suitable for cloud DB service, and has the potential to revolutionize the way how ML is used in DBMS. Furthermore, to demonstrate the predicting power and viability of MTMLF, we provide a concrete and very promising case study on query optimization tasks. Last but not least, we discuss several concrete research opportunities along this line of work.

Ziniu Wu, Amir Shaikhha, Rong Zhu et al.

Cardinality estimation (CardEst) is an essential component in query optimizers and a fundamental problem in DBMS. A desired CardEst method should attain good algorithm performance, be stable to varied data settings, and be friendly to system deployment. However, no existing CardEst method can fulfill the three criteria at the same time. Traditional methods often have significant algorithm drawbacks such as large estimation errors. Recently proposed deep learning based methods largely improve the estimation accuracy but their performance can be greatly affected by data and often difficult for system deployment. In this paper, we revitalize the Bayesian networks (BN) for CardEst by incorporating the techniques of probabilistic programming languages. We present BayesCard, the first framework that inherits the advantages of BNs, i.e., high estimation accuracy and interpretability, while overcomes their drawbacks, i.e. low structure learning and inference efficiency. This makes BayesCard a perfect candidate for commercial DBMS deployment. Our experimental results on several single-table and multi-table benchmarks indicate BayesCard's superiority over existing state-of-the-art CardEst methods: BayesCard achieves comparable or better accuracy, 1-2 orders of magnitude faster inference time, 1-3 orders faster training time, 1-3 orders smaller model size, and 1-2 orders faster updates. Meanwhile, BayesCard keeps stable performance when varying data with different settings. We also deploy BayesCard into PostgreSQL. On the IMDB benchmark workload, it improves the end-to-end query time by 13.3%, which is very close to the optimal result of 14.2% using an oracle of true cardinality.

Rong Zhu, Andreas Pfadler, Ziniu Wu et al.

Structure Learning for Bayesian network (BN) is an important problem with extensive research. It plays central roles in a wide variety of applications in Alibaba Group. However, existing structure learning algorithms suffer from considerable limitations in real world applications due to their low efficiency and poor scalability. To resolve this, we propose a new structure learning algorithm LEAST, which comprehensively fulfills our business requirements as it attains high accuracy, efficiency and scalability at the same time. The core idea of LEAST is to formulate the structure learning into a continuous constrained optimization problem, with a novel differentiable constraint function measuring the acyclicity of the resulting graph. Unlike with existing work, our constraint function is built on the spectral radius of the graph and could be evaluated in near linear time w.r.t. the graph node size. Based on it, LEAST can be efficiently implemented with low storage overhead. According to our benchmark evaluation, LEAST runs 1 to 2 orders of magnitude faster than state of the art method with comparable accuracy, and it is able to scale on BNs with up to hundreds of thousands of variables. In our production environment, LEAST is deployed and serves for more than 20 applications with thousands of executions per day. We describe a concrete scenario in a ticket booking service in Alibaba, where LEAST is applied to build a near real-time automatic anomaly detection and root error cause analysis system. We also show that LEAST unlocks the possibility of applying BN structure learning in new areas, such as large-scale gene expression data analysis and explainable recommendation system.

Rong Zhu, Mattia Rigotti

The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an efficient algorithm to mitigate this bias. However, this comes at the price of an underestimation of action values, in addition to increased memory requirements and a slower convergence. In this paper, we introduce a new way to address the maximization bias in the form of a "self-correcting algorithm" for approximating the maximum of an expected value. Our method balances the overestimation of the single estimator used in conventional Q-learning and the underestimation of the double estimator used in Double Q-learning. Applying this strategy to Q-learning results in Self-correcting Q-learning. We show theoretically that this new algorithm enjoys the same convergence guarantees as Q-learning while being more accurate. Empirically, it performs better than Double Q-learning in domains with rewards of high variance, and it even attains faster convergence than Q-learning in domains with rewards of zero or low variance. These advantages transfer to a Deep Q Network implementation that we call Self-correcting DQN and which outperforms regular DQN and Double DQN on several tasks in the Atari 2600 domain.

Rong Zhu, Ziniu Wu, Yuxing Han et al.

Query optimizers rely on accurate cardinality estimation (CardEst) to produce good execution plans. The core problem of CardEst is how to model the rich joint distribution of attributes in an accurate and compact manner. Despite decades of research, existing methods either over simplify the models only using independent factorization which leads to inaccurate estimates, or over complicate them by lossless conditional factorization without any independent assumption which results in slow probability computation. In this paper, we propose FLAT, a CardEst method that is simultaneously fast in probability computation, lightweight in model size and accurate in estimation quality. The key idea of FLAT is a novel unsupervised graphical model, called FSPN. It utilizes both independent and conditional factorization to adaptively model different levels of attributes correlations, and thus dovetails their advantages. FLAT supports efficient online probability computation in near liner time on the underlying FSPN model, provides effective offline model construction and enables incremental model updates. It can estimate cardinality for both single table queries and multi table join queries. Extensive experimental study demonstrates the superiority of FLAT over existing CardEst methods on well known IMDB benchmarks: FLAT achieves 1 to 5 orders of magnitude better accuracy, 1 to 3 orders of magnitude faster probability computation speed and 1 to 2 orders of magnitude lower storage cost. We also integrate FLAT into Postgres to perform an end to end test. It improves the query execution time by 12.9% on the benchmark workload, which is very close to the optimal result 14.2% using the true cardinality.

Ziniu Wu, Rong Zhu, Andreas Pfadler et al.

We introduce factorize sum split product networks (FSPNs), a new class of probabilistic graphical models (PGMs). FSPNs are designed to overcome the drawbacks of existing PGMs in terms of estimation accuracy and inference efficiency. Specifically, Bayesian networks (BNs) have low inference speed and performance of tree structured sum product networks(SPNs) significantly degrades in presence of highly correlated variables. FSPNs absorb their advantages by adaptively modeling the joint distribution of variables according to their dependence degree, so that one can simultaneously attain the two desirable goals: high estimation accuracy and fast inference speed. We present efficient probability inference and structure learning algorithms for FSPNs, along with a theoretical analysis and extensive evaluation evidence. Our experimental results on synthetic and benchmark datasets indicate the superiority of FSPN over other PGMs.

Rong Zhu, Jiming Jiang

For optimization on large-scale data, exactly calculating its solution may be computationally difficulty because of the large size of the data. In this paper we consider subsampled optimization for fast approximating the exact solution. In this approach, one gets a surrogate dataset by sampling from the full data, and then obtains an approximate solution by solving the subsampled optimization based on the surrogate. One main theoretical contributions are to provide the asymptotic properties of the approximate solution with respect to the exact solution as statistical guarantees, and to rigorously derive an accurate approximation of the mean squared error (MSE) and an approximately unbiased MSE estimator. These results help us better diagnose the subsampled optimization in the context that a confidence region on the exact solution is provided using the approximate solution. The other consequence of our results is to propose an optimal sampling method, Hessian-based sampling, whose probabilities are proportional to the norms of Newton directions. Numerical experiments with least-squares and logistic regression show promising performance, in line with our results.

Rong Zhu

In modern data analysis, random sampling is an efficient and widely-used strategy to overcome the computational difficulties brought by large sample size. In previous studies, researchers conducted random sampling which is according to the input data but independent on the response variable, however the response variable may also be informative for sampling. In this paper we propose an adaptive sampling called the gradient-based sampling which is dependent on both the input data and the output for fast solving of least-square (LS) problems. We draw the data points by random sampling from the full data according to their gradient values. This sampling is computationally saving, since the running time of computing the sampling probabilities is reduced to O(nd) where n is the full sample size and d is the dimension of the input. Theoretically, we establish an error bound analysis of the general importance sampling with respect to LS solution from full data. The result establishes an improved performance of the use of our gradient- based sampling. Synthetic and real data sets are used to empirically argue that the gradient-based sampling has an obvious advantage over existing sampling methods from two aspects of statistical efficiency and computational saving.

Rong Zhu, Ping Ma, Michael W. Mahoney et al.

A significant hurdle for analyzing large sample data is the lack of effective statistical computing and inference methods. An emerging powerful approach for analyzing large sample data is subsampling, by which one takes a random subsample from the original full sample and uses it as a surrogate for subsequent computation and estimation. In this paper, we study subsampling methods under two scenarios: approximating the full sample ordinary least-square (OLS) estimator and estimating the coefficients in linear regression. We present two algorithms, weighted estimation algorithm and unweighted estimation algorithm, and analyze asymptotic behaviors of their resulting subsample estimators under general conditions. For the weighted estimation algorithm, we propose a criterion for selecting the optimal sampling probability by making use of the asymptotic results. On the basis of the criterion, we provide two novel subsampling methods, the optimal subsampling and the predictor- length subsampling methods. The predictor-length subsampling method is based on the L2 norm of predictors rather than leverage scores. Its computational cost is scalable. For unweighted estimation algorithm, we show that its resulting subsample estimator is not consistent to the full sample OLS estimator. However, it has better performance than the weighted estimation algorithm for estimating the coefficients. Simulation studies and a real data example are used to demonstrate the effectiveness of our proposed subsampling methods.

Rong Zhu

Large sample size brings the computation bottleneck for modern data analysis. Subsampling is one of efficient strategies to handle this problem. In previous studies, researchers make more fo- cus on subsampling with replacement (SSR) than on subsampling without replacement (SSWR). In this paper we investigate a kind of SSWR, poisson subsampling (PSS), for fast algorithm in ordinary least-square problem. We establish non-asymptotic property, i.e, the error bound of the correspond- ing subsample estimator, which provide a tradeoff between computation cost and approximation efficiency. Besides the non-asymptotic result, we provide asymptotic consistency and normality of the subsample estimator. Methodologically, we propose a two-step subsampling algorithm, which is efficient with respect to a statistical objective and independent on the linear model assumption.. Synthetic and real data are used to empirically study our proposed subsampling strategies. We argue by these empirical studies that, (1) our proposed two-step algorithm has obvious advantage when the assumed linear model does not accurate, and (2) the PSS strategy performs obviously better than SSR when the subsampling ratio increases.