PyTorchKR Papers

최신 논문

총 3,030편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2506.07581

FedCGD: Collective Gradient Divergence Optimized Scheduling for Wireless Federated Learning

Federated learning (FL) is a promising paradigm for multiple devices to cooperatively train a model. When applied in wireless networks, two issues consistently affect the performance of FL, i.e., data heterogeneity of devices and limited bandwidth. Many papers have investigated device scheduling strategies considering the two issues. However, most of them recognize data heterogeneity as a property of individual devices. In this paper, we prove that the convergence speed of FL is affected by the sum of device-level and sample-level collective gradient divergence (CGD). The device-level CGD refers to the gradient divergence of the scheduled device group, instead of the sum of the individual device divergence. The sample-level CGD is statistically upper bounded by sampling variance, which is inversely proportional to the total number of samples scheduled for local update. To derive a tractable form of the device-level CGD, we further consider a classification problem and transform it into the weighted earth moving distance (WEMD) between the group distribution and the global distribution. Then we propose FedCGD algorithm to minimize the sum of multi-level CGDs by balancing WEMD and sampling variance, within polynomial time. Simulation shows that the proposed strategy increases classification accuracy on the CIFAR-10 dataset by up to 4.2\% while scheduling 41.8\% fewer devices, and flexibly switches between reducing WEMD and reducing sampling variance.

arXiv:2506.08882

Filling in the Blanks: Applying Data Imputation in incomplete Water Metering Data

In this work, we explore the application of recent data imputation techniques to enhance monitoring and management of water distribution networks using smart water meters, based on data derived from a real-world IoT water grid monitoring deployment. Despite the detailed data produced by such meters, data gaps due to technical issues can significantly impact operational decisions and efficiency. Our results, by comparing various imputation methods, such as k-Nearest Neighbors, MissForest, Transformers, and Recurrent Neural Networks, indicate that effective data imputation can substantially enhance the quality of the insights derived from water consumption data as we study their effect on accuracy and reliability of water metering data to provide solutions in applications like leak detection and predictive maintenance scheduling.

arXiv:2506.08850공식 코드 · Papers with Code

Agile Reinforcement Learning for Real-Time Task Scheduling in Edge Computing

Soft real-time applications are becoming increasingly complex, posing significant challenges for scheduling offloaded tasks in edge computing environments while meeting task timing constraints. Moreover, the exponential growth of the search space, presence of multiple objectives and parameters, and highly dynamic nature of edge computing environments further exacerbate the complexity of task scheduling. As a result, schedulers based on heuristic and metaheuristic algorithms frequently encounter difficulties in generating optimal or near-optimal task schedules due to their constrained ability to adapt to the dynamic conditions and complex environmental characteristics of edge computing. Accordingly, reinforcement learning algorithms have been incorporated into schedulers to address the complexity and dynamic conditions inherent in task scheduling in edge computing. However, a significant limitation of reinforcement learning algorithms is the prolonged learning time required to adapt to new environments and to address medium- and large-scale problems. This challenge arises from the extensive global action space and frequent random exploration of irrelevant actions. Therefore, this study proposes Agile Reinforcement learning (aRL), in which the RL-agent performs informed exploration and executes only relevant actions. Consequently, the predictability of the RL-agent is enhanced, leading to rapid adaptation and convergence, which positions aRL as a suitable candidate for scheduling the tasks of soft real-time applications in edge computing. The experiments demonstrate that the combination of informed exploration and action-masking methods enables aRL to achieve a higher hit-ratio and converge faster than the baseline approaches.

arXiv:2506.08263

Learning-Based Multiuser Scheduling in MIMO-OFDM Systems with Hybrid Beamforming

We investigate the multiuser scheduling problem in multiple-input multiple-output (MIMO) systems using orthogonal frequency division multiplexing (OFDM) and hybrid beamforming in which a base station (BS) communicates with multiple users over millimeter wave (mmWave) channels in the downlink. Improved scheduling is critical for enhancing spectral efficiency and the long-term performance of the system from the perspective of proportional fairness (PF) metric in hybrid beamforming systems due to its limited multiplexing gain. Our objective is to maximize PF by properly designing the analog and digital precoders within the hybrid beamforming and selecting the users subject to the number of radio frequency (RF) chains. Leveraging the characteristics of mmWave channels, we apply a two-timescale protocol. On a long timescale, we assign an analog beam to each user. Scheduling the users and designing the digital precoder are done accordingly on a short timescale. To conduct scheduling, we propose combinatorial solutions, such as greedy and sorting algorithms, followed by a machine learning (ML) approach. Our numerical results highlight the trade-off between the performance and complexity of the proposed approaches. Consequently, we show that the choice of approach depends on the specific criteria within a given scenario.

arXiv:2506.08972

Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System

Autonomous agents powered by multimodal large language models have been developed to facilitate task execution on mobile devices. However, prior work has predominantly focused on atomic tasks -- such as shot-chain execution tasks and single-screen grounding tasks -- while overlooking the generalization to compositional tasks, which are indispensable for real-world applications. This work introduces UI-NEXUS, a comprehensive benchmark designed to evaluate mobile agents on three categories of compositional operations: Simple Concatenation, Context Transition, and Deep Dive. UI-NEXUS supports interactive evaluation in 20 fully controllable local utility app environments, as well as 30 online Chinese and English service apps. It comprises 100 interactive task templates with an average optimal step count of 14.05. Experimental results across a range of mobile agents with agentic workflow or agent-as-a-model show that UI-NEXUS presents significant challenges. Specifically, existing agents generally struggle to balance performance and efficiency, exhibiting representative failure modes such as under-execution, over-execution, and attention drift, causing visible atomic-to-compositional generalization gap. Inspired by these findings, we propose AGENT-NEXUS, a lightweight and efficient scheduling system to tackle compositional mobile tasks. AGENT-NEXUS extrapolates the abilities of existing mobile agents by dynamically decomposing long-horizon tasks to a series of self-contained atomic subtasks. AGENT-NEXUS achieves 24% to 40% task success rate improvement for existing mobile agents on compositional operation tasks within the UI-NEXUS benchmark without significantly sacrificing inference overhead. The demo video, dataset, and code are available on the project page at https://ui-nexus.github.io.

arXiv:2506.09050공식 코드 · Papers with Code

ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering

How well do AI systems perform in algorithm engineering for hard optimization problems in domains such as package-delivery routing, crew scheduling, factory production planning, and power-grid balancing? We introduce ALE-Bench, a new benchmark for evaluating AI systems on score-based algorithmic programming contests. Drawing on real tasks from the AtCoder Heuristic Contests, ALE-Bench presents optimization problems that are computationally hard and admit no known exact solution. Unlike short-duration, pass/fail coding benchmarks, ALE-Bench encourages iterative solution refinement over long time horizons. Our software framework supports interactive agent architectures that leverage test-run feedback and visualizations. Our evaluation of frontier LLMs revealed that while they demonstrate high performance on specific problems, a notable gap remains compared to humans in terms of consistency across problems and long-horizon problem-solving capabilities. This highlights the need for this benchmark to foster future AI advancements.

arXiv:2506.08026공식 코드 · Papers with Code

TIP-Search: Time-Predictable Inference Scheduling for Market Prediction under Uncertain Load

This paper proposes TIP-Search, a time-predictable inference scheduling framework for real-time market prediction under uncertain workloads. Motivated by the strict latency demands in high-frequency financial systems, TIP-Search dynamically selects a deep learning model from a heterogeneous pool, aiming to maximize predictive accuracy while satisfying per-task deadline constraints. Our approach profiles latency and generalization performance offline, then performs online task-aware selection without relying on explicit input domain labels. We evaluate TIP-Search on three real-world limit order book datasets (FI-2010, Binance BTC/USDT, LOBSTER AAPL) and demonstrate that it outperforms static baselines with up to 8.5% improvement in accuracy and 100% deadline satisfaction. Our results highlight the effectiveness of TIP-Search in robust low-latency financial inference under uncertainty.

arXiv:2506.07564

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Despite their growing capabilities, today's agent frameworks remain fragile, lacking principled mechanisms for secure information flow, reliability, and multi-agent coordination. In this work, we introduce SAFEFLOW, a new protocol-level framework for building trustworthy LLM/VLM-based agents. SAFEFLOW enforces fine-grained information flow control (IFC), precisely tracking provenance, integrity, and confidentiality of all the data exchanged between agents, tools, users, and environments. By constraining LLM reasoning to respect these security labels, SAFEFLOW prevents untrusted or adversarial inputs from contaminating high-integrity decisions. To ensure robustness in concurrent multi-agent settings, SAFEFLOW introduces transactional execution, conflict resolution, and secure scheduling over shared state, preserving global consistency across agents. We further introduce mechanisms, including write-ahead logging, rollback, and secure caches, that further enhance resilience against runtime errors and policy violations. To validate the performances, we built SAFEFLOWBENCH, a comprehensive benchmark suite designed to evaluate agent reliability under adversarial, noisy, and concurrent operational conditions. Extensive experiments demonstrate that agents built with SAFEFLOW maintain impressive task performance and security guarantees even in hostile environments, substantially outperforming state-of-the-art. Together, SAFEFLOW and SAFEFLOWBENCH lay the groundwork for principled, robust, and secure agent ecosystems, advancing the frontier of reliable autonomy.

arXiv:2506.04328

Quantum-Inspired Genetic Optimization for Patient Scheduling in Radiation Oncology

Among the genetic algorithms generally used for optimization problems in the recent decades, quantum-inspired variants are known for fast and high-fitness convergence and small resource requirement. Here the application to the patient scheduling problem in proton therapy is reported. Quantum chromosomes are tailored to possess the superposed data of patient IDs and gantry statuses. Selection and repair strategies are also elaborated for reliable convergence to a clinically feasible schedule although the employed model is not complex. Clear advantage in population size is shown over the classical counterpart in our numerical results for both a medium-size test case and a large-size practical problem instance. It is, however, observed that program run time is rather long for the large-size practical case, which is due to the limitation of classical emulation and demands the forthcoming true quantum computation. Our results also revalidate the stability of the conventional classical genetic algorithm.

arXiv:2506.04296

Deep learning for predicting hauling fleet production capacity under uncertainties in open pit mines using real and simulated data

Accurate short-term forecasting of hauling-fleet capacity is crucial in open-pit mining, where weather fluctuations, mechanical breakdowns, and variable crew availability introduce significant operational uncertainties. We propose a deep-learning framework that blends real-world operational records (high-resolution rainfall measurements, fleet performance telemetry) with synthetically generated mechanical-breakdown scenarios to enable the model to capture fluctuating high-impact failure events. We evaluate two architectures: an XGBoost regressor achieving a median absolute error (MedAE) of 14.3 per cent and a Long Short-Term Memory network with a MedAE of 15.1 per cent. Shapley Additive exPlanations (SHAP) value analyses identify cumulative rainfall, historical payload trends, and simulated breakdown frequencies as dominant predictors. Integration of simulated breakdown data and shift-planning features notably reduces prediction volatility. Future work will further integrate maintenance-scheduling indicators (Mean Time Between Failures, Mean Time to Repair), detailed human resource data (operator absenteeism, crew efficiency metrics), blast event scheduling, and other operational constraints to enhance forecast robustness and adaptability. This hybrid modelling approach offers a comprehensive decision-support tool for proactive, data-driven fleet management under dynamically uncertain conditions.

arXiv:2506.02576공식 코드 · Papers with Code

ADFormer: Aggregation Differential Transformer for Passenger Demand Forecasting

Passenger demand forecasting helps optimize vehicle scheduling, thereby improving urban efficiency. Recently, attention-based methods have been used to adequately capture the dynamic nature of spatio-temporal data. However, existing methods that rely on heuristic masking strategies cannot fully adapt to the complex spatio-temporal correlations, hindering the model from focusing on the right context. These works also overlook the high-level correlations that exist in the real world. Effectively integrating these high-level correlations with the original correlations is crucial. To fill this gap, we propose the Aggregation Differential Transformer (ADFormer), which offers new insights to demand forecasting promotion. Specifically, we utilize Differential Attention to capture the original spatial correlations and achieve attention denoising. Meanwhile, we design distinct aggregation strategies based on the nature of space and time. Then, the original correlations are unified with the high-level correlations, enabling the model to capture holistic spatio-temporal relations. Experiments conducted on taxi and bike datasets confirm the effectiveness and efficiency of our model, demonstrating its practical value. The code is available at https://github.com/decisionintelligence/ADFormer.

arXiv:2506.05229공식 코드 · Papers with Code

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts

Transformer models struggle with long-context inference due to their quadratic time and linear memory complexity. Recurrent Memory Transformers (RMTs) offer a solution by reducing the asymptotic cost to linear time and constant memory usage. However, their memory update mechanism leads to sequential execution, causing a performance bottleneck. We introduce Diagonal Batching, a scheduling scheme that unlocks parallelism across segments in RMTs while preserving exact recurrence. This approach eliminates the sequential constraint, enabling efficient GPU inference even for single long-context inputs without complex batching and pipelining techniques. Because the technique is purely a run-time computation reordering, existing RMT models adopt it with no retraining. Applied to a LLaMA-1B ARMT model, Diagonal Batching yields a 3.3x speedup over standard full-attention LLaMA-1B and a 1.8x speedup over the sequential RMT implementation on 131,072-token sequences. By removing sequential bottleneck, Diagonal Batching reduces inference cost and latency, thereby strengthening RMTs as a practical solution for real-world, long-context applications.

arXiv:2506.04263

Dynamic Epsilon Scheduling: A Multi-Factor Adaptive Perturbation Budget for Adversarial Training

Adversarial training is among the most effective strategies for defending deep neural networks against adversarial examples. A key limitation of existing adversarial training approaches lies in their reliance on a fixed perturbation budget, which fails to account for instance-specific robustness characteristics. While prior works such as IAAT and MMA introduce instance-level adaptations, they often rely on heuristic or static approximations of data robustness. In this paper, we propose Dynamic Epsilon Scheduling (DES), a novel framework that adaptively adjusts the adversarial perturbation budget per instance and per training iteration. DES integrates three key factors: (1) the distance to the decision boundary approximated via gradient-based proxies, (2) prediction confidence derived from softmax entropy, and (3) model uncertainty estimated via Monte Carlo dropout. By combining these cues into a unified scheduling strategy, DES tailors the perturbation budget dynamically to guide more effective adversarial learning. Experimental results on CIFAR-10 and CIFAR-100 show that our method consistently improves both adversarial robustness and standard accuracy compared to fixed-epsilon baselines and prior adaptive methods. Moreover, we provide theoretical insights into the stability and convergence of our scheduling policy. This work opens a new avenue for instance-aware, data-driven adversarial training methods.

arXiv:2506.03059

Backpressure-based Mean-field Type Game for Scheduling in Multi-Hop Wireless Sensor Networks

We propose a Mean-Field Type Game (MFTG) framework for effective scheduling in multi-hop wireless sensor networks (WSNs) using backpressure as a performance criterion. Traditional backpressure algorithms leverage queue differentials to regulate data flow and maintain network stability. In this work, we extend the backpressure framework by incorporating a mean-field term into the cost functional, capturing the global behavior of the system alongside local dynamics. The resulting model utilizes the strengths of non-cooperative mean-field type games, enabling nodes to make decentralized decisions based on both individual queue states and system mean-field effects while accounting for stochastic network interactions. By leveraging the interplay between backpressure dynamics and mean-field coupling, the approach balances local optimization with global efficiency. Numerical simulations demonstrate the efficacy of the proposed method in handling congestion and scheduling in large-scale WSNs.

arXiv:2506.02707

Unit Commitment with Cost-Oriented Temporal Resolution

Time-adaptive unit commitment (UC) has recently been investigated to reduce the scheduling costs by flexibly varying the temporal resolution, which is usually determined by clustering the net load patterns. However, there exists a misalignment between cost and net load patterns due to the discrete start-up costs and out-of-merit-order dispatch triggered by ramping and other constraints. The optimal time-adaptive resolution cannot be completely captured by clustering-based method. This paper proposes a cost-oriented method to address this misalignment by a novel bilevel optimization approach that is efficiently solved through a heuristic greedy algorithm. The impact of varying temporal resolution on the final scheduling costs are tested, based on which the temporal resolution is heuristically updated, achieving significant cost reduction without increasing the number of temporal periods. Subsequently, an improved discretized Adam optimization method together with offline warm start and online refinement strategy is proposed to efficiently search for the better temporal resolution configuration. Results show that the proposed cost-oriented UC temporal resolution determination method achieves enhanced cost efficiency.

arXiv:2506.01712

A Vertical Approach to Designing and Managing Sustainable Heterogeneous Edge Data Centers

The increasing demand for Artificial Intelligence (AI) computing poses significant environmental challenges, with both operational and embodied carbon emissions becoming major contributors. This paper presents a carbon-aware holistic methodology for designing and managing sustainable Edge Data Centers (EDCs), based on three design principles that challenge the state-of-the-art optimization paradigms. Our approach employs vertical integration across the architecture, system, and runtime layers, balances operational and embodied carbon emissions while considering EDC performance as a co-optimization objective, rather than a constraint. At the architecture level, we propose carbon-aware and approximate accelerator designs to reduce embodied carbon. At the system level, we enhance resource utilization and adapt to real-time carbon intensity variations to minimize operational emissions. Finally, at the runtime level, we develop dynamic scheduling frameworks that adjust execution, based on energy constraints and carbon intensity.

arXiv:2506.01358

Prediction of the Conditional Probability Densities of Time Interval Extrema with Application to Risk-Sensitive Scheduling

Planning and scheduling activities in the electrical power system, such as the commitment of reserve generation, often involve the statistical characterization of peak demand. Due to the stationarity assumption of classical extreme value analysis (EVA), existing approaches in the industry apply EVA on simulated annual peaks created by weather-dependent surrogate models using Monte-Carlo simulations on a per-scenario basis. In day-ahead scheduling, the daily peak demand changes upon various factors besides temperature, Monte-Carlo experiments become intractable, and state-of-the-art generalized additive model for location, scale and shape (GAMLSS)-based nonstationary EVA is often impractical due to convergence issues on high-dimensional covariates. This article explores uncharted territories and proposes a novel nonstationary EVA estimator that predicts the probable peaks of high-resolution time intervals and their corresponding conditional probability densities based on calendar information and weather conditions where historical peaks are observed. Compared to GAMLSS, our method automatically discovers and robustly models complex relationships between the covariate and the peak demand density. We present a case study on the determination of day-ahead scheduling capacity and demonstrate that compared to the industry approach, our approach results in a 38% reduction in the yearly total committed capacity while maintaining the given risk requirement.

arXiv:2505.24159

A Causation-Based Framework for Pricing and Cost Allocation of Energy, Reserves, and Transmission in Modern Power Systems

The increasing vulnerability of power systems has heightened the need for operating reserves to manage contingencies such as generator outages, line failures, and sudden load variations. Unlike energy costs, driven by consumer demand, operating reserve costs arise from addressing the most critical credible contingencies - prompting the question: how should these costs be allocated through efficient pricing mechanisms? As an alternative to previously reported schemes, this paper presents a new causation-based pricing framework for electricity markets based on contingency-constrained energy and reserve scheduling models. Major salient features include a novel security charge mechanism along with the explicit definition of prices for up-spinning reserves, down-spinning reserves, and transmission services. These features ensure more comprehensive and efficient cost-reflective market operations. Moreover, the proposed nodal pricing scheme yields revenue adequacy and neutrality while promoting reliability incentives for generators based on the cost-causation principle. An additional salient aspect of the proposed framework is the economic incentive for transmission assets, which are remunerated based on their use to deliver energy and reserves across all contingency states. Numerical results from two case studies illustrate the performance of the proposed pricing scheme.

arXiv:2506.04276

Autonomous Collaborative Scheduling of Time-dependent UAVs, Workers and Vehicles for Crowdsensing in Disaster Response

Natural disasters have caused significant losses to human society, and the timely and efficient acquisition of post-disaster environmental information is crucial for the effective implementation of rescue operations. Due to the complexity of post-disaster environments, existing sensing technologies face challenges such as weak environmental adaptability, insufficient specialized sensing capabilities, and limited practicality of sensing solutions. This paper explores the heterogeneous multi-agent online autonomous collaborative scheduling algorithm HoAs-PALN, aimed at achieving efficient collection of post-disaster environmental information. HoAs-PALN is realized through adaptive dimensionality reduction in the matching process and local Nash equilibrium game, facilitating autonomous collaboration among time-dependent UAVs, workers and vehicles to enhance sensing scheduling. (1) In terms of adaptive dimensionality reduction during the matching process, HoAs-PALN significantly reduces scheduling decision time by transforming a five-dimensional matching process into two categories of three-dimensional matching processes; (2) Regarding the local Nash equilibrium game, HoAs-PALN combines the softmax function to optimize behavior selection probabilities and introduces a local Nash equilibrium determination mechanism to ensure scheduling decision performance. Finally, we conducted detailed experiments based on extensive real-world and simulated data. Compared with the baselines (GREEDY, K-WTA, MADL and MARL), HoAs-PALN improves task completion rates by 64.12%, 46.48%, 16.55%, and 14.03% on average, respectively, while each online scheduling decision takes less than 10 seconds, demonstrating its effectiveness in dynamic post-disaster environments.

arXiv:2506.03828공식 코드 · Papers with Code

AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance

AI for Industrial Asset Lifecycle Management aims to automate complex operational workflows -- such as condition monitoring, maintenance planning, and intervention scheduling -- to reduce human workload and minimize system downtime. Traditional AI/ML approaches have primarily tackled these problems in isolation, solving narrow tasks within the broader operational pipeline. In contrast, the emergence of AI agents and large language models (LLMs) introduces a next-generation opportunity: enabling end-to-end automation across the entire asset lifecycle. This paper envisions a future where AI agents autonomously manage tasks that previously required distinct expertise and manual coordination. To this end, we introduce AssetOpsBench -- a unified framework and environment designed to guide the development, orchestration, and evaluation of domain-specific agents tailored for Industry 4.0 applications. We outline the key requirements for such holistic systems and provide actionable insights into building agents that integrate perception, reasoning, and control for real-world industrial operations. The software is available at https://github.com/IBM/AssetOpsBench.