arXiv subjects

Bistra Dilkina

Publications and source records attributed to Bistra Dilkina.

At least 19 recordsLinked to original sources

arXiv2026

Domain-Aware Machine Learning for Accelerating MILP-Based Motion Planning with Temporal Logic and Chance Constraints

Motion-planning problems with temporal-logic or chance constraints are often encoded as mixed-integer linear programs (MILPs). Although these encodings provide rigorous specifications, their combinatorial structure can make planning prohibitively slow. Machine learning for combinatorial optimization (ML4CO) has accelerated general-purpose MILP solving, but its standard graph representations discard semantic information available in control problems, such as variable roles, time indices, sample identities, and formula structure. We introduce a domain-aware ML4CO framework for MILP-based motion planning with temporal logic and chance constraints. The framework augments a conventional variable--constraint bipartite graph with features derived from the planning formulation and uses the resulting representation for two solver-guidance tasks: selecting branching backdoors and configuring solver parameters. We study three domains---Signal Temporal Logic (STL) planning, chance-constrained planning through Conformal Predictive Programming (CPP), and multi-agent Capability Temporal Logic (CaTL) planning---and compare against solver defaults, domain-agnostic learned methods, non-learned branching rules, MCTS transfer, and SMAC3 transfer. Across the tested distributions, domain-aware backdoor selection has the lowest reported mean solve time in all three domains, improving on default Gurobi by 14.4--20.4%. Domain-aware configuration also has the lowest mean primal gap and primal integral in all three domains under a fixed SCIP time limit. These results show that exposing control-specific structure can improve learned MILP guidance beyond generic optimization features.

eess.SY↗

arXiv2026

FunL2O: LLM-Guided Feature Function Design for Learning to Optimize

Learning-to-optimize (L2O) methods accelerate repeated optimization by training models to predict solutions, warm starts, branching decisions, or other forms of solver guidance. A critical yet largely overlooked component of these pipelines is the feature function that maps problem instances to inputs for machine learning models. Existing L2O methods typically rely on hand-crafted features, making representation design manual and largely fixed across domains. We introduce FunL2O, the first unified framework for automating feature design through LLM-driven program evolution for L2O. In a FunSearch-style loop, an LLM proposes executable feature functions, while a fixed evaluation process retrains the original L2O model and measures downstream optimization performance. We evaluate FunL2O on linear and quadratic programming tasks involving solution prediction and warm-starting, as well as on mixed-integer optimization tasks using GNN-guided backdoor branching and Predict-and-Search. Across continuous and discrete optimization tasks and four LLMs, the evolved features consistently outperform hand-crafted representations. These results establish LLM-driven feature evolution as a general and effective approach to automating representation design in L2O.

cs.LG↗

arXiv2026

Machine Learning Guided Optimal Transmission Switching to Mitigate Wildfire Ignition Risk

To mitigate acute wildfire ignition risks, utilities de-energize power lines in high-risk areas. The Optimal Power Shutoff (OPS) problem optimizes line energization statuses to manage wildfire ignition risks through de-energizations while reducing load shedding. OPS problems are computationally challenging Mixed-Integer Linear Programs (MILPs) that must be solved rapidly and frequently in operational settings. For a particular power system, OPS instances share a common structure with varying parameters related to wildfire risks, loads, and renewable generation. This motivates the use of Machine Learning (ML) for solving OPS problems by exploiting shared patterns across instances. In this paper, we develop an ML-guided framework that quickly produces high-quality de-energization decisions by extending existing ML-guided MILP solution methods while integrating domain knowledge on the number of energized and de-energized lines. Results on a large-scale realistic California-based synthetic test system show that the proposed ML-guided method produces high-quality solutions faster than traditional optimization methods.

cs.LG↗

arXiv2026

ML-Guided Primal Heuristics for Mixed Binary Quadratic Programs

Mixed Binary Quadratic Programs (MBQPs) are an important and complex set of problems in combinatorial optimization. As solving large-scale combinatorial optimization problems is challenging, primal heuristics have been developed to quickly identify high-quality solutions within a short amount of time. Recently, a growing body of research has also used machine learning to accelerate solution methods for challenging combinatorial optimization problems. Despite the increasing popularity of these ML-guided methods, a large body of work has focused on Mixed-Integer Linear Programs (MILPs). MBQPs are challenging to solve due to the combinatorial complexity coupled with nonlinearities. This work proposes ML-guided primal heuristics for Mixed Binary Quadratic Programs (MBQPs) by adapting and extending existing work on ML-guided MILP solution prediction to MBQPs. We introduce a new neural network architecture for MBQP solution prediction and a new training data collection procedure. Moreover, we extend existing loss functions in solution prediction and propose to combine contrastive and weighted cross-entropy losses. We evaluate the methods on standard and real-world MBQP benchmarks and show that the developed ML-guided methods significantly outperform existing primal heuristics and state-of-the-art solvers. Furthermore, models trained with our proposed extension with combined losses outperform other ML-based methods adapted from MILPs and improve generalization in cross-regional inference on a real-world wind farm layout optimization problem.

cs.LG↗

arXiv2026

ID-PaS+ : Identity-Aware Predict-and-Search for General Mixed-Integer Linear Programs

Mixed-Integer Linear Programs (MIPs) are powerful and flexible tools for modeling a wide range of real-world combinatorial optimization problems. Predict-and-Search methods operate by using a predictive model to estimate promising variable assignments and then guiding a search procedure toward high-quality solutions. Recent research has demonstrated that incorporating machine learning (ML) into the Predict-and-Search framework significantly enhances its performance. Still, it is restricted to binary-only problems and overlooks the presence of fixed variable structures that commonly arise in real-world settings. This work extends the current Predict-and-Search (PAS) framework to parametric general parametric MIPs and introduces ID-PAS+, an identity-aware learning framework that enables the ML model to handle heterogeneous variable types more effectively. Experiments on several real-world large-scale problems demonstrate that ID-PAS+ consistently achieves superior performance compared to the state-of-the-art solver Gurobi and PAS.

cs.AI↗

arXiv2025

Application-Driven Innovation in Machine Learning

In this position paper, we argue that application-driven research has been systemically under-valued in the machine learning community. As applications of machine learning proliferate, innovative algorithms inspired by specific real-world challenges have become increasingly important. Such work offers the potential for significant impact not merely in domains of application but also in machine learning itself. In this paper, we describe the paradigm of application-driven research in machine learning, contrasting it with the more standard paradigm of methods-driven research. We illustrate the benefits of application-driven machine learning and how this approach can productively synergize with methods-driven work. Despite these benefits, we find that reviewing, hiring, and teaching practices in machine learning often hold back application-driven innovation. We outline how these processes may be improved.

cs.LG↗

arXiv2025

Gala: Global LLM Agents for Text-to-Model Translation

Natural language descriptions of optimization or satisfaction problems are challenging to translate into correct MiniZinc models, as this process demands both logical reasoning and constraint programming expertise. We introduce Gala, a framework that addresses this challenge with a global agentic approach: multiple specialized large language model (LLM) agents decompose the modeling task by global constraint type. Each agent is dedicated to detecting and generating code for a specific class of global constraint, while a final assembler agent integrates these constraint snippets into a complete MiniZinc model. By dividing the problem into smaller, well-defined sub-tasks, each LLM handles a simpler reasoning challenge, potentially reducing overall complexity. We conduct initial experiments with several LLMs and show better performance against baselines such as one-shot prompting and chain-of-thought prompting. Finally, we outline a comprehensive roadmap for future work, highlighting potential enhancements and directions for improvement.

cs.AI↗

arXiv2025

LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning

Since the release of Deepseek-R1, reinforcement learning with verifiable rewards (RLVR) has become a central approach for training large language models (LLMs) on reasoning tasks. Recent work has largely focused on modifying loss functions to make RLVR more efficient and effective. In this paper, motivated by studies of overthinking in LLMs, we propose Length-aware Sampling for Policy Optimization (LSPO), a novel meta-RLVR algorithm that dynamically selects training data at each step based on the average response length. We evaluate LSPO across multiple base models and datasets, demonstrating that it consistently improves learning effectiveness. In addition, we conduct a detailed ablation study to examine alternative ways of incorporating length signals into dynamic sampling, offering further insights and highlighting promising directions for future research.

cs.LG↗

arXiv2025

ParBalans: Parallel Multi-Armed Bandits-based Adaptive Large Neighborhood Search

Solving Mixed-Integer Programming (MIP) problems often requires substantial computational resources due to their combinatorial nature. Parallelization has emerged as a critical strategy to accelerate solution times and enhance scalability to tackle large, complex instances. This paper investigates the parallelization capabilities of Balans, a recently proposed multi-armed bandits-based adaptive large neighborhood search for MIPs. While Balans's modular architecture inherently supports parallel exploration of diverse parameter configurations, this potential has not been thoroughly examined. To address this gap, we introduce ParBalans, an extension that leverages both solver-level and algorithmic-level parallelism to improve performance on challenging MIP instances. Our experimental results demonstrate that ParBalans exhibits competitive performance compared to the state-of-the-art commercial solver Gurobi, particularly on hard optimization benchmarks.

cs.AI↗

arXiv2025

Balans: Multi-Armed Bandits-based Adaptive Large Neighborhood Search for Mixed-Integer Programming Problem

Mixed-integer programming (MIP) is a powerful paradigm for modeling and solving various important combinatorial optimization problems. Recently, learning-based approaches have shown a potential to speed up MIP solving via offline training that then guides important design decisions during the search. However, a significant drawback of these methods is their heavy reliance on offline training, which requires collecting training datasets and computationally costly training epochs yet offering only limited generalization to unseen (larger) instances. In this paper, we propose Balans, an adaptive meta-solver for MIPs with online learning capability that does not require any supervision or apriori training. At its core, Balans is based on adaptive large-neighborhood search, operating on top of an MIP solver by successive applications of destroy and repair neighborhood operators. During the search, the selection among different neighborhood definitions is guided on the fly for the instance at hand via multi-armed bandit algorithms. Our extensive experiments on hard optimization instances show that Balans offers significant performance gains over the default MIP solver, is better than committing to any single best neighborhood, and improves over the state-of-the-art large-neighborhood search for MIPs. Finally, we release Balans as a highly configurable, MIP solver agnostic, open-source software.

cs.AI↗

arXiv2025

Efficient Primal Heuristics for Mixed Binary Quadratic Programs Using Suboptimal Rounding Guidance

Mixed Binary Quadratic Programs (MBQPs) are a class of NP-hard problems that arise in a wide range of applications, including finance, machine learning, and chemical and energy systems. Large-scale MBQPs are challenging to solve with exact algorithms due to the combinatorial search space and nonlinearity. Primal heuristics have been developed to quickly identify high-quality solutions to challenging combinatorial optimization problems. In this paper, we propose an extension for two well-established rounding-based primal heuristics, RENS and Undercover. Instead of using the optimal solution to a relaxation for variable rounding and search as in RENS, we use a suboptimal relaxation solution of the MBQP as the basis for rounding and guidance for searching over a restricted subproblem where a certain percentage of binary variables are free. We apply a similar idea to the Undercover heuristic that fixes a variable cover to the rounded relaxation values. Instead, we relax a subset of the cover variables based on the suboptimal relaxation and search over a larger restricted subproblem. We evaluate our proposed methods on synthetic MBQP benchmarks and real-world wind farm layout optimization problem instances. The results show that our proposed heuristics identify high-quality solutions within a small time limit and significantly reduce the primal gap and primal integral compared to RENS, Undercover, and solvers with additional primal heuristics integrated inside Branch-and-Bound.

math.OC↗

arXiv2025

Multi-task Representation Learning for Mixed Integer Linear Programming

Mixed Integer Linear Programs (MILPs) are highly flexible and powerful tools for modeling and solving complex real-world combinatorial optimization problems. Recently, machine learning (ML)-guided approaches have demonstrated significant potential in improving MILP-solving efficiency. However, these methods typically rely on separate offline data collection and training processes, which limits their scalability and adaptability. This paper introduces the first multi-task learning framework for ML-guided MILP solving. The proposed framework provides MILP embeddings helpful in guiding MILP solving across solvers (e.g., Gurobi and SCIP) and across tasks (e.g., Branching and Solver configuration). Through extensive experiments on three widely used MILP benchmarks, we demonstrate that our multi-task learning model performs similarly to specialized models within the same distribution. Moreover, it significantly outperforms them in generalization across problem sizes and tasks.

cs.AI↗

arXiv2025

Iterative Deepening Sampling as Efficient Test-Time Scaling

Recent reasoning models, such as OpenAI's O1 series, have demonstrated exceptional performance on complex reasoning tasks and revealed new test-time scaling laws. Inspired by this, many people have been studying how to train models to achieve effective self-evaluation and self-correction to further enable the scaling paradigm. However, less studied is how to efficiently scale test-time compute from a fixed model, and this remains a challenge. In this paper, we address this challenge by focusing on enhancing the quality of self-reflection data generation for complex problem-solving at test time, which can also subsequently improve the training of next-generation large language models (LLMs). Specifically, we explore how systematically triggering a model's self-correction mechanisms can improve performance on challenging reasoning tasks. To this end, we propose a novel iterative deepening sampling algorithm framework designed to enhance self-correction and generate higher-quality samples. Through extensive experiments on Math500 and AIME benchmarks, we demonstrate that our method achieves a higher success rate on difficult tasks and provide detailed ablation studies to analyze its effectiveness across diverse settings.

cs.CL↗

arXiv2025

RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents

In the past year, large language models (LLMs) have had remarkable success in domains outside the traditional natural language processing, and their capacity is further expanded into the so-called LLM agents when connected with external tools. In all domains, the prompt to the LLMs has been shown to make a big difference in what the LLM would generate and thus affect the performance of the LLM agents. Therefore, automatic prompt engineering (APE) has become an important question for many researchers and users of LLMs. However, previous works in APE rely on a final checker to evaluate the performance of the given prompt -- a requirement that is hard to meet in the case of LLM agents, where intermediate feedback is easier to obtain, and the final evaluation could be expensive, inaccurate, or even missing. In this paper, we propose a novel method, \textsc{RePrompt}, which does a ``gradient descent"-like approach to optimize the step-by-step instructions in the prompts given to LLM agents, based on the chat history obtained from interactions and reflections with LLM agents. By leveraging intermediate feedback, \textsc{RePrompt} can optimize the prompt without the need for a final solution checker. We evaluate our approach on PDDL generation, TravelPlanner, and Meeting Planning to show that our method could generally improve performance for different reasoning tasks.

cs.CL↗

arXiv2024

Distributional MIPLIB: a Multi-Domain Library for Advancing ML-Guided MILP Methods

Mixed Integer Linear Programming (MILP) is a fundamental tool for modeling combinatorial optimization problems. Recently, a growing body of research has used machine learning to accelerate MILP solving. Despite the increasing popularity of this approach, there is a lack of a common repository that provides distributions of similar MILP instances across different domains, at different hardness levels, with standardized test sets. In this paper, we introduce Distributional MIPLIB, a multi-domain library of problem distributions for advancing ML-guided MILP methods. We curate MILP distributions from existing work in this area as well as real-world problems that have not been used, and classify them into different hardness levels. It will facilitate research in this area by enabling comprehensive evaluation on diverse and realistic domains. We empirically illustrate the benefits of using Distributional MIPLIB as a research vehicle in two ways. We evaluate the performance of ML-guided variable branching on previously unused distributions to identify potential areas for improvement. Moreover, we propose to learn branching policies from a mix of distributions, demonstrating that mixed distributions achieve better performance compared to homogeneous distributions when there is limited data and generalize well to larger instances. The dataset is publicly available at https://sites.google.com/usc.edu/distributional-miplib/home.

cs.LG↗

arXiv2024

Learning Backdoors for Mixed Integer Linear Programs with Contrastive Learning

Many real-world problems can be efficiently modeled as Mixed Integer Linear Programs (MILPs) and solved with the Branch-and-Bound method. Prior work has shown the existence of MILP backdoors, small sets of variables such that prioritizing branching on them when possible leads to faster running times. However, finding high-quality backdoors that improve running times remains an open question. Previous work learns to estimate the relative solver speed of randomly sampled backdoors through ranking and then decide whether to use the highest-ranked backdoor candidate. In this paper, we utilize the Monte-Carlo tree search method to collect backdoors for training, rather than relying on random sampling, and adapt a contrastive learning framework to train a Graph Attention Network model to predict backdoors. Our method, evaluated on several common MILP problem domains, demonstrates performance improvements over both Gurobi and previous models.

cs.AI↗

arXiv2024

GenCO: Generating Diverse Designs with Combinatorial Constraints

Deep generative models like GAN and VAE have shown impressive results in generating unconstrained objects like images. However, many design settings arising in industrial design, material science, computer graphics and more require that the generated objects satisfy hard combinatorial constraints or meet objectives in addition to modeling a data distribution. To address this, we propose GenCO, a generative framework that guarantees constraint satisfaction throughout training by leveraging differentiable combinatorial solvers to enforce feasibility. GenCO imposes the generative loss on provably feasible solutions rather than intermediate soft solutions, meaning that the deep generative network can focus on ensuring the generated objects match the data distribution without having to also capture feasibility. This shift enables practitioners to enforce hard constraints on the generated outputs during end-to-end training, enabling assessments of their feasibility and introducing additional combinatorial loss components to deep generative training. We demonstrate the effectiveness of our approach on a variety of generative combinatorial tasks, including game level generation, map creation for path planning, and photonic device design, consistently demonstrating its capability to yield diverse, high-quality solutions that verifiably adhere to user-specified combinatorial properties.

cs.LG↗

arXiv2024

No Panacea in Planning: Algorithm Selection for Suboptimal Multi-Agent Path Finding

Since more and more algorithms are proposed for multi-agent path finding (MAPF) and each of them has its strengths, choosing the correct one for a specific scenario that fulfills some specified requirements is an important task. Previous research in algorithm selection for MAPF built a standard workflow and showed that machine learning can help. In this paper, we study general solvers for MAPF, which further include suboptimal algorithms. We propose different groups of optimization objectives and learning tasks to handle the new tradeoff between runtime and solution quality. We conduct extensive experiments to show that the same loss can not be used for different groups of optimization objectives, and that standard computer vision models are no worse than customized architecture. We also provide insightful discussions on how feature-sensitive pre-processing is needed for learning for MAPF, and how different learning metrics are correlated to different learning tasks.

cs.MA↗