PyTorchKR Papers

최신 논문

총 7,781편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2504.04982

Transforming Future Data Center Operations and Management via Physical AI

Data centers (DCs) as mission-critical infrastructures are pivotal in powering the growth of artificial intelligence (AI) and the digital economy. The evolution from Internet DC to AI DC has introduced new challenges in operating and managing data centers for improved business resilience and reduced total cost of ownership. As a result, new paradigms, beyond the traditional approaches based on best practices, must be in order for future data centers. In this research, we propose and develop a novel Physical AI (PhyAI) framework for advancing DC operations and management. Our system leverages the emerging capabilities of state-of-the-art industrial products and our in-house research and development. Specifically, it presents three core modules, namely: 1) an industry-grade in-house simulation engine to simulate DC operations in a highly accurate manner, 2) an AI engine built upon NVIDIA PhysicsNemo for the training and evaluation of physics-informed machine learning (PIML) models, and 3) a digital twin platform built upon NVIDIA Omniverse for our proposed 5-tier digital twin framework. This system presents a scalable and adaptable solution to digitalize, optimize, and automate future data center operations and management, by enabling real-time digital twins for future data centers. To illustrate its effectiveness, we present a compelling case study on building a surrogate model for predicting the thermal and airflow profiles of a large-scale DC in a real-time manner. Our results demonstrate its superior performance over traditional time-consuming Computational Fluid Dynamics/Heat Transfer (CFD/HT) simulation, with a median absolute temperature prediction error of 0.18 {\deg}C. This emerging approach would open doors to several potential research directions for advancing Physical AI in future DC operations.

arXiv:2504.03692

A Theoretical Framework for Graph-based Digital Twins for Supply Chain Management and Optimization

Supply chain management is growing increasingly complex due to globalization, evolving market demands, and sustainability pressures, yet traditional systems struggle with fragmented data and limited analytical capabilities. Graph-based modeling offers a powerful way to capture the intricate relationships within supply chains, while Digital Twins (DTs) enable real-time monitoring and dynamic simulations. However, current implementations often face challenges related to scalability, data integration, and the lack of sustainability-focused metrics. To address these gaps, we propose a Graph-Based Digital Twin Framework for Supply Chain Optimization, which combines graph modeling with DT architecture to create a dynamic, real-time representation of supply networks. Our framework integrates a Data Integration Layer to harmonize disparate sources, a Graph Construction Module to model complex dependencies, and a Simulation and Analysis Engine for scalable optimization. Importantly, we embed sustainability metrics - such as carbon footprints and resource utilization - into operational dashboards to drive eco-efficiency. By leveraging the synergy between graph-based modeling and DTs, our approach enhances scalability, improves decision-making, and enables organizations to proactively manage disruptions, cut costs, and transition toward greener, more resilient supply chains.

arXiv:2504.03682

Intelligent Resource Allocation Optimization for Cloud Computing via Machine Learning

With the rapid expansion of cloud computing applications, optimizing resource allocation has become crucial for improving system performance and cost efficiency. This paper proposes an intelligent resource allocation algorithm that leverages deep learning (LSTM) for demand prediction and reinforcement learning (DQN) for dynamic scheduling. By accurately forecasting computing resource demands and enabling real-time adjustments, the proposed system enhances resource utilization by 32.5%, reduces average response time by 43.3%, and lowers operational costs by 26.6%. Experimental results in a production cloud environment confirm that the method significantly improves efficiency while maintaining high service quality. This study provides a scalable and effective solution for intelligent cloud resource management, offering valuable insights for future cloud optimization strategies.

arXiv:2504.06293공식 코드 · Papers with Code

Generative AI Enhanced Financial Risk Management Information Retrieval

Risk management in finance involves recognizing, evaluating, and addressing financial risks to maintain stability and ensure regulatory compliance. Extracting relevant insights from extensive regulatory documents is a complex challenge requiring advanced retrieval and language models. This paper introduces RiskData, a dataset specifically curated for finetuning embedding models in risk management, and RiskEmbed, a finetuned embedding model designed to improve retrieval accuracy in financial question-answering systems. The dataset is derived from 94 regulatory guidelines published by the Office of the Superintendent of Financial Institutions (OSFI) from 1991 to 2024. We finetune a state-of-the-art sentence BERT embedding model to enhance domain-specific retrieval performance typically for Retrieval-Augmented Generation (RAG) systems. Experimental results demonstrate that RiskEmbed significantly outperforms general-purpose and financial embedding models, achieving substantial improvements in ranking metrics. By open-sourcing both the dataset and the model, we provide a valuable resource for financial institutions and researchers aiming to develop more accurate and efficient risk management AI solutions.

arXiv:2504.05881

Actuarial Learning for Pension Fund Mortality Forecasting

For the assessment of the financial soundness of a pension fund, it is necessary to take into account mortality forecasting so that longevity risk is consistently incorporated into future cash flows. In this article, we employ machine learning models applied to actuarial science ({\it actuarial learning}) to make mortality predictions for a relevant sample of pension funds' participants. Actuarial learning represents an emerging field that involves the application of machine learning (ML) and artificial intelligence (AI) techniques in actuarial science. This encompasses the use of algorithms and computational models to analyze large sets of actuarial data, such as regression trees, random forest, boosting, XGBoost, CatBoost, and neural networks (eg. FNN, LSTM, and MHA). Our results indicate that some ML/AI algorithms present competitive out-of-sample performance when compared to the classical Lee-Carter model. This may indicate interesting alternatives for consistent liability evaluation and effective pension fund risk management.

arXiv:2504.04295

Dynamic Hedging Strategies in Derivatives Markets with LLM-Driven Sentiment and News Analytics

Dynamic hedging strategies are essential for effective risk management in derivatives markets, where volatility and market sentiment can greatly impact performance. This paper introduces a novel framework that leverages large language models (LLMs) for sentiment analysis and news analytics to inform hedging decisions. By analyzing textual data from diverse sources like news articles, social media, and financial reports, our approach captures critical sentiment indicators that reflect current market conditions. The framework allows for real-time adjustments to hedging strategies, adapting positions based on continuous sentiment signals. Backtesting results on historical derivatives data reveal that our dynamic hedging strategies achieve superior risk-adjusted returns compared to conventional static approaches. The incorporation of LLM-driven sentiment analysis into hedging practices presents a significant advancement in decision-making processes within derivatives trading. This research showcases how sentiment-informed dynamic hedging can enhance portfolio management and effectively mitigate associated risks.

arXiv:2504.04292

Cross-Asset Risk Management: Integrating LLMs for Real-Time Monitoring of Equity, Fixed Income, and Currency Markets

Large language models (LLMs) have emerged as powerful tools in the field of finance, particularly for risk management across different asset classes. In this work, we introduce a Cross-Asset Risk Management framework that utilizes LLMs to facilitate real-time monitoring of equity, fixed income, and currency markets. This innovative approach enables dynamic risk assessment by aggregating diverse data sources, ultimately enhancing decision-making processes. Our model effectively synthesizes and analyzes market signals to identify potential risks and opportunities while providing a holistic view of asset classes. By employing advanced analytics, we leverage LLMs to interpret financial texts, news articles, and market reports, ensuring that risks are contextualized within broader market narratives. Extensive backtesting and real-time simulations validate the framework, showing increased accuracy in predicting market shifts compared to conventional methods. The focus on real-time data integration enhances responsiveness, allowing financial institutions to manage risks adeptly under varying market conditions and promoting financial stability through the advanced application of LLMs in risk analysis.

arXiv:2504.02881

Better Bill GPT: Comparing Large Language Models against Legal Invoice Reviewers

Legal invoice review is a costly, inconsistent, and time-consuming process, traditionally performed by Legal Operations, Lawyers or Billing Specialists who scrutinise billing compliance line by line. This study presents the first empirical comparison of Large Language Models (LLMs) against human invoice reviewers - Early-Career Lawyers, Experienced Lawyers, and Legal Operations Professionals-assessing their accuracy, speed, and cost-effectiveness. Benchmarking state-of-the-art LLMs against a ground truth set by expert legal professionals, our empirically substantiated findings reveal that LLMs decisively outperform humans across every metric. In invoice approval decisions, LLMs achieve up to 92% accuracy, surpassing the 72% ceiling set by experienced lawyers. On a granular level, LLMs dominate line-item classification, with top models reaching F-scores of 81%, compared to just 43% for the best-performing human group. Speed comparisons are even more striking - while lawyers take 194 to 316 seconds per invoice, LLMs are capable of completing reviews in as fast as 3.6 seconds. And cost? AI slashes review expenses by 99.97%, reducing invoice processing costs from an average of $4.27 per invoice for human invoice reviewers to mere cents. These results highlight the evolving role of AI in legal spend management. As law firms and corporate legal departments struggle with inefficiencies, this study signals a seismic shift: The era of LLM-powered legal spend management is not on the horizon, it has arrived. The challenge ahead is not whether AI can perform as well as human reviewers, but how legal teams will strategically incorporate it, balancing automation with human discretion.

arXiv:2504.03170

Water Mapping and Change Detection Using Time Series Derived from the Continuous Monitoring of Land Disturbance Algorithm

Given the growing environmental challenges, accurate monitoring and prediction of changes in water bodies are essential for sustainable management and conservation. The Continuous Monitoring of Land Disturbance (COLD) algorithm provides a valuable tool for real-time analysis of land changes, such as deforestation, urban expansion, agricultural activities, and natural disasters. This capability enables timely interventions and more informed decision-making. This paper assesses the effectiveness of the algorithm to estimate water bodies and track pixel-level water trends over time. Our findings indicate that COLD-derived data can reliably estimate estimate water frequency during stable periods and delineate water bodies. Furthermore, it enables the evaluation of trends in water areas after disturbances, allowing for the determination of whether water frequency increases, decreases, or remains constant.

arXiv:2504.02841

Dynamic Investment Strategies Through Market Classification and Volatility: A Machine Learning Approach

This study introduces a dynamic investment framework to enhance portfolio management in volatile markets, offering clear advantages over traditional static strategies. Evaluates four conventional approaches : equal weighted, minimum variance, maximum diversification, and equal risk contribution under dynamic conditions. Using K means clustering, the market is segmented into ten volatility-based states, with transitions forecasted by a Bayesian Markov switching model employing Dirichlet priors and Gibbs sampling. This enables real-time asset allocation adjustments. Tested across two asset sets, the dynamic portfolio consistently achieves significantly higher risk-adjusted returns and substantially higher total returns, outperforming most static methods. By integrating classical optimization with machine learning and Bayesian techniques, this research provides a robust strategy for optimizing investment outcomes in unpredictable market environments.

arXiv:2504.02840

Statistical applications of the 20/60/20 rule in risk management and portfolio optimization

This paper explores the applications of the 20/60/20 rule-a heuristic method that segments data into top-performing, average-performing, and underperforming groups-in mathematical finance. We review the statistical foundations of this rule and demonstrate its usefulness in risk management and portfolio optimization. Our study highlights three key applications. First, we apply the rule to stock market data, showing that it enables effective population clustering. Second, we introduce a novel, easy-to-implement method for extracting heavy-tail characteristics in risk management. Third, we integrate spatial reasoning based on the 20/60/20 rule into portfolio optimization, enhancing robustness and improving performance. To support our findings, we develop a new measure for quantifying tail heaviness and employ conditional statistics to reconstruct the unconditional distribution from the core data segment. This reconstructed distribution is tested on real financial data to evaluate whether the 20/60/20 segmentation effectively balances capturing extreme risks with maintaining the stability of central returns. Our results offer insights into financial data behavior under heavy-tailed conditions and demonstrate the potential of the 20/60/20 rule as a complementary tool for decision-making in finance.

arXiv:2504.03499

Optimistic Learning for Communication Networks

AI/ML-based tools are at the forefront of resource management solutions for communication networks. Deep learning, in particular, is highly effective in facilitating fast and high-performing decision-making whenever representative training data is available to build offline accurate models. Conversely, online learning solutions do not require training and enable adaptive decisions based on runtime observations, alas are often overly conservative. This extensive tutorial proposes the use of optimistic learning (OpL) as a decision engine for resource management frameworks in modern communication systems. When properly designed, such solutions can achieve fast and high-performing decisions -- comparable to offline-trained models -- while preserving the robustness and performance guarantees of the respective online learning approaches. We introduce the fundamental concepts, algorithms and results of OpL, discuss the roots of this theory and present different approaches to defining and achieving optimism. We proceed to showcase how OpL can enhance resource management in communication networks for several key problems such as caching, edge computing, network slicing, and workload assignment in decentralized O-RAN platforms. Finally, we discuss the open challenges that must be addressed to unlock the full potential of this new resource management approach.

arXiv:2504.03229

A Robust Method for Fault Detection and Severity Estimation in Mechanical Vibration Data

This paper proposes a robust method for fault detection and severity estimation in multivariate time-series data to enhance predictive maintenance of mechanical systems. We use the Temporal Graph Convolutional Network (T-GCN) model to capture both spatial and temporal dependencies among variables. This enables accurate future state predictions under varying operational conditions. To address the challenge of fluctuating anomaly scores that reduce fault severity estimation accuracy, we introduce a novel fault severity index based on the mean and standard deviation of anomaly scores. This generates a continuous and reliable severity measurement. We validate the proposed method using two experimental datasets: an open IMS bearing dataset and data collected from a fanjet electric propulsion system. Results demonstrate that our method significantly reduces abrupt fluctuations and inconsistencies in anomaly scores. This provides a more dependable foundation for maintenance planning and risk management in safety-critical applications.

arXiv:2504.02993

Route Recommendations for Traffic Management Under Learned Partial Driver Compliance

In this paper, we aim to mitigate congestion in traffic management systems by guiding travelers along system-optimal (SO) routes. However, we recognize that most theoretical approaches assume perfect driver compliance, which often does not reflect reality, as drivers tend to deviate from recommendations to fulfill their personal objectives. Therefore, we propose a route recommendation framework that explicitly learns partial driver compliance and optimizes traffic flow under realistic adherence. We first compute an SO edge flow through flow optimization techniques. Next, we train a compliance model based on historical driver decisions to capture individual responses to our recommendations. Finally, we formulate a stochastic optimization problem that minimizes the gap between the target SO flow and the realized flow under conditions of imperfect adherence. Our simulations conducted on a grid network reveal that our approach significantly reduces travel time compared to baseline strategies, demonstrating the practical advantage of incorporating learned compliance into traffic management.

arXiv:2504.02916

Feature Engineering on LMS Data to Optimize Student Performance Prediction

Nearly every educational institution uses a learning management system (LMS), often producing terabytes of data generated by thousands of people. We examine LMS grade and login data from a regional comprehensive university, specifically documenting key considerations for engineering features from these data when trying to predict student performance. We specifically document changes to LMS data patterns since Covid-19, which are critical for data scientists to account for when using historic data. We compare numerous engineered features and approaches to utilizing those features for machine learning. We finish with a summary of the implications of including these features into more comprehensive student performance models.

arXiv:2504.02855

Exploration of Multi-Element Collaborative Research and Application for Modern Power System Based on Generative Large Models

The transition to intelligent, low-carbon power systems necessitates advanced optimization strategies for managing renewable energy integration, energy storage, and carbon emissions. Generative Large Models (GLMs) provide a data-driven approach to enhancing forecasting, scheduling, and market operations by processing multi-source data and capturing complex system dynamics. This paper explores the role of GLMs in optimizing load-side management, energy storage utilization, and electricity carbon, with a focus on Smart Wide-area Hybrid Energy Systems with Storage and Carbon (SGLSC). By leveraging spatiotemporal modeling and reinforcement learning, GLMs enable dynamic energy scheduling, improve grid stability, enhance carbon trading strategies, and strengthen resilience against extreme weather events. The proposed framework highlights the transformative potential of GLMs in achieving efficient, adaptive, and low-carbon power system operations.

arXiv:2504.02811

An Assessment of the CO$_2$ Emission Reduction Potential of Residential Load Management in Developing and Developed Countries

Intermittent renewable energies are increasingly dominating electricity grids and are forecasted to be the main force driving out fossil fuels from the grid in most major economies until 2040. However, grids based on intermittent renewables are challenged by diurnal and seasonal mismatch between supply of sun and wind and demand for electricity, including for heat pumps and electric two and four wheelers. Load management and demand response measures promise to adjust for this mismatch, utilizing information- and price-based approaches to steer demand towards times with high supply of intermittent renewables. Here, we systematically review the literature estimating CO$_2$ savings from residential load management in developing and developed nations. We find that load management holds high potential, locally differentiated with energy mix (including the respective share of renewables and fossils), climate zone, and the regulatory environment and price mechanism. Most identified studies suggest a mitigation potential between 1 and 20%. Load management becomes more relevant with higher shares of intermittent renewables, and when electricity prices are high. Importantly, load management aligns consumers' financial incentives with climate change mitigation, thus rendering accompanying strategies politically feasible. We summarize key regulatory steps to facilitate load management in economies and to realize relevant consumer surplus and mitigation potential.

arXiv:2504.02441

Cognitive Memory in Large Language Models

This paper examines memory mechanisms in Large Language Models (LLMs), emphasizing their importance for context-rich responses, reduced hallucinations, and improved efficiency. It categorizes memory into sensory, short-term, and long-term, with sensory memory corresponding to input prompts, short-term memory processing immediate context, and long-term memory implemented via external databases or structures. The text-based memory section covers acquisition (selection and summarization), management (updating, accessing, storing, and resolving conflicts), and utilization (full-text search, SQL queries, semantic search). The KV cache-based memory section discusses selection methods (regularity-based summarization, score-based approaches, special token embeddings) and compression techniques (low-rank compression, KV merging, multimodal compression), along with management strategies like offloading and shared attention mechanisms. Parameter-based memory methods (LoRA, TTT, MoE) transform memories into model parameters to enhance efficiency, while hidden-state-based memory approaches (chunk mechanisms, recurrent transformers, Mamba model) improve long-text processing by combining RNN hidden states with current methods. Overall, the paper offers a comprehensive analysis of LLM memory mechanisms, highlighting their significance and future research directions.

arXiv:2504.02781

Towards Green AI-Native Networks: Evaluation of Neural Circuit Policy for Estimating Energy Consumption of Base Stations

Optimization of radio hardware and AI-based network management software yield significant energy savings in radio access networks. The execution of underlying Machine Learning (ML) models, which enable energy savings through recommended actions, may require additional compute and energy, highlighting the opportunity to explore and adopt accurate and energy-efficient ML technologies. This work evaluates the novel use of sparsely structured Neural Circuit Policies (NCPs) in a use case to estimate the energy consumption of base stations. Sparsity in ML models yields reduced memory, computation and energy demand, hence facilitating a low-cost and scalable solution. We also evaluate the generalization capability of NCPs in comparison to traditional and widely used ML models such as Long Short Term Memory (LSTM), via quantifying their sensitivity to varying model hyper-parameters (HPs). NCPs demonstrated a clear reduction in computational overhead and energy consumption. Moreover, results indicated that the NCPs are robust to varying HPs such as number of epochs and neurons in each layer, making them a suitable option to ease model management and to reduce energy consumption in Machine Learning Operations (MLOps) in telecommunications.

arXiv:2504.02662

Integrating Human Knowledge Through Action Masking in Reinforcement Learning for Operations Research

Reinforcement learning (RL) provides a powerful method to address problems in operations research. However, its real-world application often fails due to a lack of user acceptance and trust. A possible remedy is to provide managers with the possibility of altering the RL policy by incorporating human expert knowledge. In this study, we analyze the benefits and caveats of including human knowledge via action masking. While action masking has so far been used to exclude invalid actions, its ability to integrate human expertise remains underexplored. Human knowledge is often encapsulated in heuristics, which suggest reasonable, near-optimal actions in certain situations. Enforcing such actions should hence increase trust among the human workforce to rely on the model's decisions. Yet, a strict enforcement of heuristic actions may also restrict the policy from exploring superior actions, thereby leading to overall lower performance. We analyze the effects of action masking based on three problems with different characteristics, namely, paint shop scheduling, peak load management, and inventory management. Our findings demonstrate that incorporating human knowledge through action masking can achieve substantial improvements over policies trained without action masking. In addition, we find that action masking is crucial for learning effective policies in constrained action spaces, where certain actions can only be performed a limited number of times. Finally, we highlight the potential for suboptimal outcomes when action masks are overly restrictive.