arXiv subjects

Haoruo Zhao

Publications and source records attributed to Haoruo Zhao.

10 recordsLinked to original sources

arXiv2026

From Subsumption to Satisfiability: LLM-Assisted Active Learning for OWL Ontologies

In active learning, membership queries (MQs) allow a learner to pose questions to a teacher, such as ''Is every apple a fruit?'', to which the teacher responds correctly with yes or no. These MQs can be viewed as subsumption tests with respect to the target ontology. Inspired by the standard reduction of subsumption to satisfiability in description logics, we reformulate each candidate axiom into its corresponding counter-concept and verbalise it in controlled natural language before presenting it to Large Language Models (LLMs). We introduce LLMs as a third component that provides real-world examples approximating an instance of the counter-concept. This design property ensures that only Type II errors may occur in ontology modelling; in the worst case, these errors merely delay the construction process without introducing inconsistencies. Experimental results on 13 commercial LLMs show that recall, corresponding to Type II errors in our framework, remains stable across several well-established ontologies.

cs.AI↗

arXiv2026

Code vs Serialized AST Inputs for LLM-Based Code Summarization: An Empirical Study

Summarizing source code into natural language descriptions (code summarization) helps developers better understand program functionality and reduce the burden of software maintenance. Abstract Syntax Trees (ASTs), as opposed to source code, have been shown to improve summarization quality in traditional encoder-decoder-based code summarization models. However, most large language model (LLM)-based code summarization methods rely on raw code or only incorporate partial AST signals, meaning that the potential of complete AST representation has not been fully explored for LLMs. This paper presents AST(NIT), an AST augmentation and serialization method that preserves lexical details and encodes structural information into LLM-compatible sequences. Experiments with the LLaMA-3.1-8B model on the CodeXGLUE Python dataset show that the proposed serialized ASTs reduce the length of LLM inputs, require shorter training times, and achieve summarization quality comparable to existing approaches.

cs.SE↗

arXiv2025

CSI-4CAST: A Hybrid Deep Learning Model for CSI Prediction with Comprehensive Robustness and Generalization Testing

Channel state information (CSI) prediction is a promising strategy for ensuring reliable and efficient operation of massive multiple-input multiple-output (mMIMO) systems by providing timely downlink (DL) CSI. While deep learning-based methods have advanced beyond conventional model-driven and statistical approaches, they remain limited in robustness to practical non-Gaussian noise, generalization across diverse channel conditions, and computational efficiency. This paper introduces CSI-4CAST, a hybrid deep learning architecture that integrates 4 key components, i.e., Convolutional neural network residuals, Adaptive correction layers, ShuffleNet blocks, and Transformers, to efficiently capture both local and long-range dependencies in CSI prediction. To enable rigorous evaluation, this work further presents a comprehensive benchmark, CSI-RRG for Regular, Robustness and Generalization testing, which includes more than 300,000 samples across 3,060 realistic scenarios for both TDD and FDD systems. The dataset spans multiple channel models, a wide range of delay spreads and user velocities, and diverse noise types and intensity degrees. Experimental results show that CSI-4CAST achieves superior prediction accuracy with substantially lower computational cost, outperforming baselines in 81.5% of TDD scenarios and 44.4% of FDD scenario, the best performance among all evaluated models, while reducing FLOPs by 5x and 3x compared to LLM4CP, the strongest baseline. In addition, evaluation over CSI-RRG provides valuable insights into how different channel factors affect the performance and generalization capability of deep learning models. Both the dataset (https://huggingface.co/CSI-4CAST) and evaluation protocols (https://github.com/AI4OPT/CSI-4CAST) are publicly released to establish a standardized benchmark and to encourage further research on robust and efficient CSI prediction.

cs.LG↗

arXiv2025

DualSchool: How Reliable are LLMs for Optimization Education?

Consider the following task taught in introductory optimization courses which addresses challenges articulated by the community at the intersection of (generative) AI and OR: generate the dual of a linear program. LLMs, being trained at web-scale, have the conversion process and many instances of Primal to Dual Conversion (P2DC) at their disposal. Students may thus reasonably expect that LLMs would perform well on the P2DC task. To assess this expectation, this paper introduces DualSchool, a comprehensive framework for generating and verifying P2DC instances. The verification procedure of DualSchool uses the Canonical Graph Edit Distance, going well beyond existing evaluation methods for optimization models, which exhibit many false positives and negatives when applied to P2DC. Experiments performed by DualSchool reveal interesting findings. Although LLMs can recite the conversion procedure accurately, state-of-the-art open LLMs fail to consistently produce correct duals. This finding holds even for the smallest two-variable instances and for derivative tasks, such as correctness, verification, and error classification. The paper also discusses the implications for educators, students, and the development of large reasoning systems.

cs.LG↗

arXiv2024

Compact Optimality Verification for Optimization Proxies

Recent years have witnessed increasing interest in optimization proxies, i.e., machine learning models that approximate the input-output mapping of parametric optimization problems and return near-optimal feasible solutions. Following recent work by (Nellikkath & Chatzivasileiadis, 2021), this paper reconsiders the optimality verification problem for optimization proxies, i.e., the determination of the worst-case optimality gap over the instance distribution. The paper proposes a compact formulation for optimality verification and a gradient-based primal heuristic that brings substantial computational benefits to the original formulation. The compact formulation is also more general and applies to non-convex optimization problems. The benefits of the compact formulation are demonstrated on large-scale DC Optimal Power Flow and knapsack problems.

math.OC↗

arXiv2024

Bound Tightening using Rolling-Horizon Decomposition for Neural Network Verification

Neural network verification aims at providing formal guarantees on the output of trained neural networks, to ensure their robustness against adversarial examples and enable their deployment in safety-critical applications. This paper introduces a new approach to neural network verification using a novel mixed-integer programming rolling-horizon decomposition method. The algorithm leverages the layered structure of neural networks, by employing optimization-based bound-tightening on smaller sub-graphs of the original network in a rolling-horizon fashion. This strategy strikes a balance between achieving tighter bounds and ensuring the tractability of the underlying mixed-integer programs. Extensive numerical experiments, conducted on instances from the VNN-COMP benchmark library, demonstrate that the proposed approach yields significantly improved bounds compared to existing effective bound propagation methods. Notably, the parallelizable nature of the proposed method proves effective in solving open verification problems. Our code is built and released as part of the open-source mathematical modeling tool Gravity (https://github.com/coin-or/Gravity), which is extended to support generic neural network models.

math.OC↗

arXiv2023

On the Viability of Stochastic Economic Dispatch for Real-Time Energy Market Clearing

Over the past decade, the rapid adoption of intermittent renewable energy sources (RES), especially wind and solar generation, has posed challenges in managing real-time uncertainty and variability. In the U.S., Independent System Operators (ISOs) solve a security-constrained economic dispatch (SCED) every five minutes to clear real-time electricity markets, co-optimizing energy dispatch and reserve to minimize costs while meeting physical and reliability constraints. All SCED formulations in the U.S. are deterministic and mostly consider a single time period, limiting their effectiveness in managing real-time operational uncertainty from RES intermittency. This limitation is highlighted by the recent introduction of multiple short-term ramping products in U.S. markets, aiming to bridge the gap between deterministic and stochastic SCED formulations. While stochastic formulations address uncertainty in a unified and endogenous manner, their adoption has been hindered by high computational costs and, to a lesser extent, the availability of probabilistic forecasts. This paper revisits these concerns and demonstrates that stochastic economic dispatch is now a viable technology for real-time market clearing. It introduces the stochastic look-ahead dispatch (SLAD) formulation for real-time market clearing and presents an accelerated Benders' decomposition to solve it efficiently. Extensive experiments on a real, industry-sized transmission grid demonstrate the computational scalability of the proposed approach, with SLAD instances being solved in under 5 minutes. Furthermore, results show that SLAD provides more than 50% additional savings compared to flexiramp products and is more robust to the forecasting methodology. Therefore, SLAD is a promising approach for uncertainty management in real-time electricity markets.

math.OC↗

arXiv2022

Just-In-Time Learning for Operational Risk Assessment in Power Grids

In a grid with a significant share of renewable generation, operators will need additional tools to evaluate the operational risk due to the increased volatility in load and generation. The computational requirements of the forward uncertainty propagation problem, which must solve numerous security-constrained economic dispatch (SCED) optimizations, is a major barrier for such real-time risk assessment. This paper proposes a Just-In-Time Risk Assessment Learning Framework (JITRALF) as an alternative. JITRALF trains risk surrogates, one for each hour in the day, using Machine Learning (ML) to predict the quantities needed to estimate risk, without explicitly solving the SCED problem. This significantly reduces the computational burden of the forward uncertainty propagation and allows for fast, real-time risk estimation. The paper also proposes a novel, asymmetric loss function and shows that models trained using the asymmetric loss perform better than those using symmetric loss functions. JITRALF is evaluated on the French transmission system for assessing the risk of insufficient operating reserves, the risk of load shedding, and the expected operating cost.

eess.SY↗

arXiv2022

Risk-Aware Control and Optimization for High-Renewable Power Grids

The transition of the electrical power grid from fossil fuels to renewable sources of energy raises fundamental challenges to the market-clearing algorithms that drive its operations. Indeed, the increased stochasticity in load and the volatility of renewable energy sources have led to significant increases in prediction errors, affecting the reliability and efficiency of existing deterministic optimization models. The RAMC project was initiated to investigate how to move from this deterministic setting into a risk-aware framework where uncertainty is quantified explicitly and incorporated in the market-clearing optimizations. Risk-aware market-clearing raises challenges on its own, primarily from a computational standpoint. This paper reviews how RAMC approaches risk-aware market clearing and presents some of its innovations in uncertainty quantification, optimization, and machine learning. Experimental results on real networks are presented.

math.OC↗

arXiv2021

A Linear Outer Approximation of Line Losses for DC-based Optimal Power Flow Problems

This paper proposes a novel and simple linear model to capture line losses for use in linearized DC models, such as optimal power flow (DC-OPF) and security-constrained economic dispatch (SCED). The \textit{Line Loss Outer Approximation} (LLOA) model implements an outer approximation of the line losses lazily and typically terminates in a small number of iterations. Experiments on large-scale power systems demonstrate the accuracy and computational efficiency of LLOA and contrast it with classical line loss approaches. The results seem to indicate that LLOA is a practical and useful model for real-world applications, providing a good tradeoff between accuracy, computational efficiency, and implementation simplicity. In particular, the LLOA method may have significant advantages compared to the traditional loss factor formulation for multi-period, stochastic optimization problems where good reference points may not be available. The paper also provides a comprehensive overview and evaluation of approximation methods for line losses.

math.OC↗