PyTorchKR Papers

최신 논문

총 3,273편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2505.16329

Better Rates for Private Linear Regression in the Proportional Regime via Aggressive Clipping

Differentially private (DP) linear regression has received significant attention in the recent theoretical literature, with several works aimed at obtaining improved error rates. A common approach is to set the clipping constant much larger than the expected norm of the per-sample gradients. While simplifying the analysis, this is however in sharp contrast with what empirical evidence suggests to optimize performance. Our work bridges this gap between theory and practice: we provide sharper rates for DP stochastic gradient descent (DP-SGD) by crucially operating in a regime where clipping happens frequently. Specifically, we consider the setting where the data is multivariate Gaussian, the number of training samples $n$ is proportional to the input dimension $d$, and the algorithm guarantees constant-order zero concentrated DP. Our method relies on establishing a deterministic equivalent for the trajectory of DP-SGD in terms of a family of ordinary differential equations (ODEs). As a consequence, the risk of DP-SGD is bounded between two ODEs, with upper and lower bounds matching for isotropic data. By studying these ODEs when $n / d$ is large enough, we demonstrate the optimality of aggressive clipping, and we uncover the benefits of decaying learning rate and private noise scheduling.

arXiv:2505.15378

On the Relevance of Clinical Assessment Tasks for the Automatic Detection of Parkinson's Disease Medication State from Speech

The automatic identification of medication states of Parkinson's disease (PD) patients can assist clinicians in monitoring and scheduling personalized treatments, as well as studying the effects of medication in alleviating the motor symptoms that characterize the disease. This paper explores speech as a non-invasive and accessible biomarker for identifying PD medication states, introducing a novel approach that addresses this task from a speaker-independent perspective. While traditional machine learning models achieve competitive results, self-supervised speech representations prove essential for optimal performance, significantly surpassing knowledge-based acoustic descriptors. Experiments across diverse speech assessment tasks highlight the relevance of prosody and continuous speech in distinguishing medication states, reaching an F1-score of 88.2%. These findings may streamline clinicians' work and reduce patient effort in voice recordings.

arXiv:2505.14709공식 코드 · Papers with Code

FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge

Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike image generation, video generation requires a substantially larger number of tokens to produce coherent temporal frames, resulting in significant overhead during the decoding phase. Our key observations are: (i) MLP modules in the decode phase dominate the inference latency, and (ii) there exists high temporal redundancy in MLP outputs of adjacent frames. In this paper, we propose the \textbf{FastCar} framework to accelerate the decode phase for the AR video generation by exploring the temporal redundancy. The Temporal Attention Score (TAS) is proposed to determine whether to apply the replay strategy (\textit{i.e.}, reusing cached MLP outputs from the previous frame to reduce redundant computations) with detailed theoretical analysis and justification. Also, we develop a hardware accelerator on FPGA with Dynamic Resource Scheduling (DRS) based on TAS to enable better resource utilization and faster inference. Experimental results demonstrate the effectiveness of our method, which outperforms traditional sparse attention approaches with more than 2.1x decoding speedup and higher energy efficiency on the edge. Furthermore, by combining FastCar and sparse attention, FastCar can boost the performance of sparse attention with alleviated drifting, demonstrating our unique advantages for high-resolution and long-duration video generation. Code: https://github.com/shawnricecake/fast-car

arXiv:2505.15213공식 코드 · Papers with Code

KernelOracle: Predicting the Linux Scheduler's Next Move with Deep Learning

Efficient task scheduling is paramount in the Linux kernel, where the Completely Fair Scheduler (CFS) meticulously manages CPU resources to balance high utilization with interactive responsiveness. This research pioneers the use of deep learning techniques to predict the sequence of tasks selected by CFS, aiming to evaluate the feasibility of a more generalized and potentially more adaptive task scheduler for diverse workloads. Our core contributions are twofold: first, the systematic generation and curation of a novel scheduling dataset from a running Linux kernel, capturing real-world CFS behavior; and second, the development, training, and evaluation of a Long Short-Term Memory (LSTM) network designed to accurately forecast the next task to be scheduled. This paper further discusses the practical pathways and implications of integrating such a predictive model into the kernel's scheduling framework. The findings and methodologies presented herein open avenues for data-driven advancements in kernel scheduling, with the full source code provided for reproducibility and further exploration.

arXiv:2505.14530공식 코드 · Papers with Code

Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs

We show that large language models (LLMs) exhibit an $\textit{internal chain-of-thought}$: they sequentially decompose and execute composite tasks layer-by-layer. Two claims ground our study: (i) distinct subtasks are learned at different network depths, and (ii) these subtasks are executed sequentially across layers. On a benchmark of 15 two-step composite tasks, we employ layer-from context-masking and propose a novel cross-task patching method, confirming (i). To examine claim (ii), we apply LogitLens to decode hidden states, revealing a consistent layerwise execution pattern. We further replicate our analysis on the real-world $\text{TRACE}$ benchmark, observing the same stepwise dynamics. Together, our results enhance LLMs transparency by showing their capacity to internally plan and execute subtasks (or instructions), opening avenues for fine-grained, instruction-level activation steering.

arXiv:2505.13554

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation

Large language model (LLM) shows promising performances in a variety of downstream tasks, such as machine translation (MT). However, using LLMs for translation suffers from high computational costs and significant latency. Based on our evaluation, in most cases, translations using LLMs are comparable to that generated by neural machine translation (NMT) systems. Only in particular scenarios, LLM and NMT models show respective advantages. As a result, integrating NMT and LLM for translation and using LLM only when necessary seems to be a sound solution. A scheduling policy that optimizes translation result while ensuring fast speed and as little LLM usage as possible is thereby required. We compare several scheduling policies and propose a novel and straightforward decider that leverages source sentence features. We conduct extensive experiments on multilingual test sets and the result shows that we can achieve optimal translation performance with minimal LLM usage, demonstrating effectiveness of our decider.

arXiv:2505.12190

UAV-Enabled Joint Sensing, Communication, Powering and Backhaul Transmission in Maritime Monitoring Networks

This paper addresses the challenge of energy-constrained maritime monitoring networks by proposing an unmanned aerial vehicle (UAV)-enabled integrated sensing, communication, powering and backhaul transmission scheme with a tailored time-division duplex frame structure. Within each time slot, the UAV sequentially implements sensing, wireless charging and uplink receiving with buoys, and lastly forwards part of collected data to the central ship via backhaul links. Considering the tight coupling among these functions, we jointly optimize time allocation, UAV trajectory, UAV-buoy association, and power scheduling to maximize the performance of data collection, with the practical consideration of sea clutter effects during UAV sensing. A novel optimization framework combining alternating optimization, quadratic transform and augmented first-order Taylor approximation is developed, which demonstrates good convergence behavior and robustness. Simulation results show that under sensing quality-of-service constraint, buoys are able to achieve an average data rate over 22bps/Hz using around 2mW harvested power per active time slot, validating the scheme's effectiveness for open-sea monitoring. Additionally, it is found that under the influence of sea clutters, the optimal UAV trajectory always keeps a certain distance with buoys to strike a balance between sensing and other multi-functional transmissions.

arXiv:2505.11526

Code Retrieval for MILP Instance Generation

Mixed-Integer Linear Programming (MILP) is widely used in fields such as scheduling, logistics, and planning. Enhancing the performance of MILP solvers, particularly learning-based solvers, requires substantial amounts of high-quality data. However, existing methods for MILP instance generation typically necessitate training a separate model for each problem class and are computationally intensive when generating new instances. To address these limitations, we reformulate the MILP Instance Generation task as MILP Code Generation task, enabling efficient, flexible, and interpretable instance generation through code. Since MILP instances generated from code can vary significantly in scale, we introduce MILP-EmbedSim, a new similarity metric that accurately measures the similarity between instances of varying sizes within the same problem class. Leveraging this metric, we propose MILP-Retrieval, a pipeline that retrieves generation code from library to produce MILP instances highly similar to target instance. MILP-Retrieval outperforms baselines in both MILP Code Generation and Instance Generation tasks, provides a novel perspective on MILP instance generation and opens new possibilities for learning-based solvers.

arXiv:2505.12862

Scheduling of Flexible Manufacturing Systems Based on Place-Timed Petri Nets and Basis Reachability Graphs

Scheduling is a key decision-making process to improve the performance of flexible manufacturing systems. Place-timed Petri nets provide a formal method for graphically modeling and analyzing such systems. By generating reachability graphs and combining intelligent search algorithms, operation sequences from the initial state to the target state can be found for the underlying system. However, the reachability graph grows exponentially with the system size increases, which is the main challenge of existing methods for scheduling large systems. To this end, we develop an efficient improved beam search algorithm to optimize the makespan based on a compact representation of reachability graph called basis reachability graph. The key idea behind the proposed method is to form a state together with the basis markings and its corresponding transition sequences, and evaluate the cost of the state based on the resource idle time. Experimental results are conducted on several benchmark systems which show that the developed method improves the search efficiency while ensuring the quality of the solution compared with existing methods.

논문 ID: 0838.37008

PDPTW-DB: MILP-Based Offline Route Planning for PDPTW with Driver Breaks

The Pickup and Delivery Problem with Time Windows (PDPTW) involves optimizing routes for vehicles to meet pickup and delivery requests within specific time constraints, a challenge commonly faced in logistics and transportation. Microtransit, a flexible and demand-responsive service using smaller vehicles within defined zones, can be effectively modeled as a PDPTW. Yet, the need for driver breaks—a key human constraint—is frequently overlooked in PDPTW solutions, despite being necessary for regulatory compliance. This study presents a novel mixed-integer linear programming formulation for the Pickup and Delivery Problem with Time Windows and Driver Breaks (PDPTW-DB). To the best of our knowledge this formulation is the first to consider mandatory periodic driver breaks within optimized Microtransit routes. The proposed model incorporates regulatory compliant break scheduling directly within the vehicle routing optimization framework. By considering driver break requirements as an integral component of the optimization process, rather than as a post-processing step, the model enables the generation of routes that respect hours of service regulations while minimizing operational costs. This integrated approach facilitates the generation of schedules that are operationally efficient and prioritize driver welfare through driver breaks. We work with a public transit agency from the southern USA, and highlight the specific nuances of driver break optimization, and present a Pickup and Delivery Problem with Time Windows formulation for optimizing Microtransit operations and scheduling driver breaks. We validate our approach using real-world data from the transit agency. Our results validate our formulation in producing cost-effective, and regulation-compliant solutions.

arXiv:2505.12710

Confidence-Regulated Generative Diffusion Models for Reliable AI Agent Migration in Vehicular Metaverses

Vehicular metaverses are an emerging paradigm that merges intelligent transportation systems with virtual spaces, leveraging advanced digital twin and Artificial Intelligence (AI) technologies to seamlessly integrate vehicles, users, and digital environments. In this paradigm, vehicular AI agents are endowed with environment perception, decision-making, and action execution capabilities, enabling real-time processing and analysis of multi-modal data to provide users with customized interactive services. Since vehicular AI agents require substantial resources for real-time decision-making, given vehicle mobility and network dynamics conditions, the AI agents are deployed in RoadSide Units (RSUs) with sufficient resources and dynamically migrated among them. However, AI agent migration requires frequent data exchanges, which may expose vehicular metaverses to potential cyber attacks. To this end, we propose a reliable vehicular AI agent migration framework, achieving reliable dynamic migration and efficient resource scheduling through cooperation between vehicles and RSUs. Additionally, we design a trust evaluation model based on the theory of planned behavior to dynamically quantify the reputation of RSUs, thereby better accommodating the personalized trust preferences of users. We then model the vehicular AI agent migration process as a partially observable markov decision process and develop a Confidence-regulated Generative Diffusion Model (CGDM) to efficiently generate AI agent migration decisions. Numerical results demonstrate that the CGDM algorithm significantly outperforms baseline methods in reducing system latency and enhancing robustness against cyber attacks.

arXiv:2505.13169

RIFLES: Resource-effIcient Federated LEarning via Scheduling

Federated Learning (FL) is a privacy-preserving machine learning technique that allows decentralized collaborative model training across a set of distributed clients, by avoiding raw data exchange. A fundamental component of FL is the selection of a subset of clients in each round for model training by a central server. Current selection strategies are myopic in nature in that they are based on past or current interactions, often leading to inefficiency issues such as straggling clients. In this paper, we address this serious shortcoming by proposing the RIFLES approach that builds a novel availability forecasting layer to support the client selection process. We make the following contributions: (i) we formalise the sequential selection problem and reduce it to a scheduling problem and show that the problem is NP-complete, (ii) leveraging heartbeat messages from clients, RIFLES build an availability prediction layer to support (long term) selection decisions, (iii) we propose a novel adaptive selection strategy to support efficient learning and resource usage. To circumvent the inherent exponential complexity, we present RIFLES, a heuristic that leverages clients' historical availability data by using a CNN-LSTM time series forecasting model, allowing the server to predict the optimal participation times of clients, thereby enabling informed selection decisions. By comparing against other FL techniques, we show that RIFLES provide significant improvement by between 10%-50% on a variety of metrics such as accuracy and test loss. To the best of our knowledge, it is the first work to investigate FL as a scheduling problem.

arXiv:2505.12355공식 코드 · Papers with Code

GATES: Cost-aware Dynamic Workflow Scheduling via Graph Attention Networks and Evolution Strategy

Cost-aware Dynamic Workflow Scheduling (CADWS) is a key challenge in cloud computing, focusing on devising an effective scheduling policy to efficiently schedule dynamically arriving workflow tasks, represented as Directed Acyclic Graphs (DAG), to suitable virtual machines (VMs). Deep reinforcement learning (DRL) has been widely employed for automated scheduling policy design. However, the performance of DRL is heavily influenced by the design of the problem-tailored policy network and is highly sensitive to hyperparameters and the design of reward feedback. Considering the above-mentioned issues, this study proposes a novel DRL method combining Graph Attention Networks-based policy network and Evolution Strategy, referred to as GATES. The contributions of GATES are summarized as follows: (1) GATES can capture the impact of current task scheduling on subsequent tasks by learning the topological relationships between tasks in a DAG. (2) GATES can assess the importance of each VM to the ready task, enabling it to adapt to dynamically changing VM resources. (3) Utilizing Evolution Strategy's robustness, exploratory nature, and tolerance for delayed rewards, GATES achieves stable policy learning in CADWS. Extensive experimental results demonstrate the superiority of the proposed GATES in CADWS, outperforming several state-of-the-art algorithms. The source code is available at: https://github.com/YaShen998/GATES.

arXiv:2505.12065공식 코드 · Papers with Code

Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents

Large Language Model (LLM)-based search agents have shown remarkable capabilities in solving complex tasks by dynamically decomposing problems and addressing them through interleaved reasoning and retrieval. However, this interleaved paradigm introduces substantial efficiency bottlenecks. First, we observe that both highly accurate and overly approximate retrieval methods degrade system efficiency: exact search incurs significant retrieval overhead, while coarse retrieval requires additional reasoning steps during generation. Second, we identify inefficiencies in system design, including improper scheduling and frequent retrieval stalls, which lead to cascading latency -- where even minor delays in retrieval amplify end-to-end inference time. To address these challenges, we introduce SearchAgent-X, a high-efficiency inference framework for LLM-based search agents. SearchAgent-X leverages high-recall approximate retrieval and incorporates two key techniques: priority-aware scheduling and non-stall retrieval. Extensive experiments demonstrate that SearchAgent-X consistently outperforms state-of-the-art systems such as vLLM and HNSW-based retrieval across diverse tasks, achieving up to 3.4$\times$ higher throughput and 5$\times$ lower latency, without compromising generation quality. SearchAgent-X is available at https://github.com/tiannuo-yang/SearchAgent-X.

arXiv:2505.12815

Learning in Chaos: Efficient Autoscaling and Self-healing for Distributed Training at the Edge

Frequent node and link changes in edge AI clusters disrupt distributed training, while traditional checkpoint-based recovery and cloud-centric autoscaling are too slow for scale-out and ill-suited to chaotic and self-governed edge. This paper proposes Chaos, a resilient and scalable edge distributed training system with built-in self-healing and autoscaling. It speeds up scale-out by using multi-neighbor replication with fast shard scheduling, allowing a new node to pull the latest training state from nearby neighbors in parallel while balancing the traffic load between them. It also uses a cluster monitor to track resource and topology changes to assist scheduler decisions, and handles scaling events through peer negotiation protocols, enabling fully self-governed autoscaling without a central admin. Extensive experiments show that Chaos consistently achieves much lower scale-out delays than Pollux, EDL, and Autoscaling, and handles scale-in, connect-link, and disconnect-link events within 1 millisecond, making it smoother to handle node joins, exits, and failures. It also delivers the lowest idle time, showing superior resource use and scalability as the cluster grows.

arXiv:2505.12501

ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planning

Large language models (LLMs) excel at rapid generation of text and multimodal content, yet they falter on transaction-style planning that demands ACID-like guarantees and real-time disruption recovery. We present Adaptive LLM Agent System (ALAS), a framework that tackles four fundamental LLM deficits: (i) absence of self-verification, (ii) context erosion, (iii) next-token myopia, and (iv) lack of persistent state. ALAS decomposes each plan into role-specialized agents, equips them with automatic state tracking, and coordinates them through a lightweight protocol. When disruptions arise, agents apply history-aware local compensation, avoiding costly global replanning and containing cascade effects. On real-world, large-scale job-shop scheduling benchmarks, ALAS sets new best results for static sequential planning and excels in dynamic reactive scenarios with unexpected disruptions. These gains show that principled modularization plus targeted compensation can unlock scalable and resilient planning with LLMs.

arXiv:2505.11135

Scalability of Reinforcement Learning Methods for Dispatching in Semiconductor Frontend Fabs: A Comparison of Open-Source Models with Real Industry Datasets

Benchmark datasets are crucial for evaluating approaches to scheduling or dispatching in the semiconductor industry during the development and deployment phases. However, commonly used benchmark datasets like the Minifab or SMT2020 lack the complex details and constraints found in real-world scenarios. To mitigate this shortcoming, we compare open-source simulation models with a real industry dataset to evaluate how optimization methods scale with different levels of complexity. Specifically, we focus on Reinforcement Learning methods, performing optimization based on policy-gradient and Evolution Strategies. Our research provides insights into the effectiveness of these optimization methods and their applicability to realistic semiconductor frontend fab simulations. We show that our proposed Evolution Strategies-based method scales much better than a comparable policy-gradient-based approach. Moreover, we identify the selection and combination of relevant bottleneck tools to control by the agent as crucial for an efficient optimization. For the generalization across different loading scenarios and stochastic tool failure patterns, we achieve advantages when utilizing a diverse training dataset. While the overall approach is computationally expensive, it manages to scale well with the number of CPU cores used for training. For the real industry dataset, we achieve an improvement of up to 4% regarding tardiness and up to 1% regarding throughput. For the less complex open-source models Minifab and SMT2020, we observe double-digit percentage improvement in tardiness and single digit percentage improvement in throughput by use of Evolution Strategies.

arXiv:2504.05258

Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models

Large Language Models (LLMs) have emerged as powerful tools for generating coherent text, understanding context, and performing reasoning tasks. However, they struggle with temporal reasoning, which requires processing time-related information such as event sequencing, durations, and inter-temporal relationships. These capabilities are critical for applications including question answering, scheduling, and historical analysis. In this paper, we introduce TISER, a novel framework that enhances the temporal reasoning abilities of LLMs through a multi-stage process that combines timeline construction with iterative self-reflection. Our approach leverages test-time scaling to extend the length of reasoning traces, enabling models to capture complex temporal dependencies more effectively. This strategy not only boosts reasoning accuracy but also improves the traceability of the inference process. Experimental results demonstrate state-of-the-art performance across multiple benchmarks, including out-of-distribution test sets, and reveal that TISER enables smaller open-source models to surpass larger closed-weight models on challenging temporal reasoning tasks.

arXiv:2505.10296

Optimizing Electric Bus Charging Scheduling with Uncertainties Using Hierarchical Deep Reinforcement Learning

The growing adoption of Electric Buses (EBs) represents a significant step toward sustainable development. By utilizing Internet of Things (IoT) systems, charging stations can autonomously determine charging schedules based on real-time data. However, optimizing EB charging schedules remains a critical challenge due to uncertainties in travel time, energy consumption, and fluctuating electricity prices. Moreover, to address real-world complexities, charging policies must make decisions efficiently across multiple time scales and remain scalable for large EB fleets. In this paper, we propose a Hierarchical Deep Reinforcement Learning (HDRL) approach that reformulates the original Markov Decision Process (MDP) into two augmented MDPs. To solve these MDPs and enable multi-timescale decision-making, we introduce a novel HDRL algorithm, namely Double Actor-Critic Multi-Agent Proximal Policy Optimization Enhancement (DAC-MAPPO-E). Scalability challenges of the Double Actor-Critic (DAC) algorithm for large-scale EB fleets are addressed through enhancements at both decision levels. At the high level, we redesign the decentralized actor network and integrate an attention mechanism to extract relevant global state information for each EB, decreasing the size of neural networks. At the low level, the Multi-Agent Proximal Policy Optimization (MAPPO) algorithm is incorporated into the DAC framework, enabling decentralized and coordinated charging power decisions, reducing computational complexity and enhancing convergence speed. Extensive experiments with real-world data demonstrate the superior performance and scalability of DAC-MAPPO-E in optimizing EB fleet charging schedules.

arXiv:2505.10262

Electric Bus Charging Schedules Relying on Real Data-Driven Targets Based on Hierarchical Deep Reinforcement Learning

The charging scheduling problem of Electric Buses (EBs) is investigated based on Deep Reinforcement Learning (DRL). A Markov Decision Process (MDP) is conceived, where the time horizon includes multiple charging and operating periods in a day, while each period is further divided into multiple time steps. To overcome the challenge of long-range multi-phase planning with sparse reward, we conceive Hierarchical DRL (HDRL) for decoupling the original MDP into a high-level Semi-MDP (SMDP) and multiple low-level MDPs. The Hierarchical Double Deep Q-Network (HDDQN)-Hindsight Experience Replay (HER) algorithm is proposed for simultaneously solving the decision problems arising at different temporal resolutions. As a result, the high-level agent learns an effective policy for prescribing the charging targets for every charging period, while the low-level agent learns an optimal policy for setting the charging power of every time step within a single charging period, with the aim of minimizing the charging costs while meeting the charging target. It is proved that the flat policy constructed by superimposing the optimal high-level policy and the optimal low-level policy performs as well as the optimal policy of the original MDP. Since jointly learning both levels of policies is challenging due to the non-stationarity of the high-level agent and the sampling inefficiency of the low-level agent, we divide the joint learning process into two phases and exploit our new HER algorithm to manipulate the experience replay buffers for both levels of agents. Numerical experiments are performed with the aid of real-world data to evaluate the performance of the proposed algorithm.