Výsledky vyhledávání - theory of computation theory and algorithms for applications domains machinery learning theory

Structured Learning with Parsimony in Measurements and Computations: Theory, Algorithms, and Applications Autor Li, Xingguo

“…In modern “Big Data” applications, structured learning is the most widely employed methodology…”
Získat plný text

Multi-Label Active Learning Algorithms for Image Classification: Overview and Future Promise Autor Wu, Jian, Sheng, Victor S, Zhang, Jing, Li, Hua, Dadakova, Tetiana, Swisher, Christine Leon, Cui, Zhiming, Zhao, Pengpeng

“… Accordingly, multi-label active learning is becoming an important research direction. In this work, we first review existing multi-label active learning algorithms for image classification…”
Zjistit podrobnosti o přístupu

Multi-Structural Games and Number of Quantifiers Autor Fagin, Ronald, Lenchner, Jonathan, Regan, Kenneth W., Vyas, Nikhil

“… to distinguish linear orders of different sizes, and develop machinery for analyzing structures beyond linear orders…”
Získat plný text

SLIM: a Scalable and Interpretable Light-weight Fault Localization Algorithm for Imbalanced Data in Microservice Autor Ren, Rui, Yang, Jingbang, Yang, Linxiao, Gu, Xinyue, Sun, Liang

“…) approach to select rules iteratively, maximizing a non-monotone submodular lower bound. Compared with existing fault localization algorithms, our algorithm can adapt…”
Získat plný text

Accelerating Decision-Tree-Based Inference Through Adaptive Parallelization Autor Van Lunteren, Jan

“…Gradient-boosted trees and random forests are among the most popular machine learning algorithms…”
Získat plný text

AutoDW: Automatic Data Wrangling Leveraging Large Language Models Autor Liu, Lei, Hasegawa, So, Sampat, Shailaja Keyur, Xenochristou, Maria, Chen, Wei-Peng, Kato, Takashi, Kakibuchi, Taisei, Asai, Tatsuya

“…Data wrangling is a critical yet often labor-intensive process, essential for transforming raw data into formats suitable for downstream tasks such as machine learning or data analysis…”
Získat plný text

Activation Sequence Caching: High-Throughput and Memory-Efficient Generative Inference with a Single GPU Autor Kim, Sowoong, Sim, Eunyeong, Shin, Youngsam, Cho, YeonGon, Baek, Woongki

“… To bridge this gap, this work presents an in-depth characterization study of KVC, which demonstrates that KVC makes a suboptimal trade-off between computations and communications…”
Získat plný text

Self-Supervised Representation Learning and Temporal-Spectral Feature Fusion for Bed Occupancy Detection Autor Song, Yingjian, Pitafi, Zaid Farooq, Dou, Fei, Sun, Jin, Zhang, Xiang, Phillips, Bradley G, Song, Wenzhan

“… This paper introduces SeismoDot, which consists of a self-supervised learning module and a spectral-temporal feature fusion module for bed occupancy detection…”
Zjistit podrobnosti o přístupu

MDLoader: A Hybrid Model-Driven Data Loader for Distributed Graph Neural Network Training Autor Bae, Jonghyun, Choi, Jong Youl, Pasini, Massimiliano Lupo, Mehta, Kshitij, Zhang, Pei, Ibrahim, Khaled Z.

“…Scalable data management is essential for processing large scientific dataset on HPC platforms for distributed deep learning…”
Získat plný text

ALISE: Accelerating Large Language Model Serving with Speculative Scheduling Autor Zhao, Youpeng, Wang, Jun

“…). As exemplified by ChatGPT, LLM-based applications necessitate minimal response latency and maximal throughput for inference serving…”
Získat plný text

Bayesian synthesis of probabilistic programs for automatic data modeling Autor Saad, Feras A., Cusumano-Towner, Marco F., Schaechtle, Ulrich, Rinard, Martin C., Mansinghka, Vikash K.

“… We also derive a general class of synthesis algorithms for domain-specific languages specified by probabilistic context-free grammars and establish the soundness of our approach for these languages…”
Získat plný text

Local Higher-Order Graph Clustering Autor Yin, Hao, Benson, Austin R, Leskovec, Jure, Gleich, David F

“…Local graph clustering methods aim to find a cluster of nodes by exploring a small region of the graph. These methods are attractive because they enable…”
Zjistit podrobnosti o přístupu

Distinguishing Hidden Markov Chains Autor Kiefer, Stefan, Sistla, A. Prasad

“… Motivated by applications in stochastic runtime verification, we consider the problem of distinguishing two given HMCs based on a single observation sequence that one of the HMCs generates…”
Získat plný text

Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methods Autor Poulain, Raphael, Tarek, Mirza Farhan Bin, Beheshti, Rahmatollah

“…Developing AI tools that preserve fairness is of critical importance, specifically in high-stakes applications such as those in healthcare…”
Zjistit podrobnosti o přístupu

Linear Scheduling of Big Data Streams on Multiprocessor Sets in the Cloud Autor Tantalaki, Nicoleta, Souravlas, Stavros, Roumeliotis, Manos, Katsavounis, Stefanos

“… (dynamically or not) and route streaming data between them. Efficient scheduling of processing tasks of data flows can reduce application latencies and eliminate network congestion…”
Získat plný text

A Memory-Efficient Markov Decision Process Computation Framework Using BDD-based Sampling Representation Autor Zhou, He, Hu, Jiang, Khatri, Sunil P., Liu, Frank

“…* Theory of computation \rightarrow Data compression; Parallel algorithms; Sequential decision making; * Mathematics of computing \rightarrowBayesian computation;…”
Získat plný text

RL-Fill: Timing-Aware Fill Insertion Using Reinforcement Learning Autor Cho, Jinoh, Park, Seonghyeon, Lee, Jakang, Lee, Sung-Yun, Ahn, Jinmo, Kang, Seokhyeong

“…We introduce RL-Fill, a novel reinforcement learning framework for timing-aware fill insertion…”
Získat plný text

Robust Implementation of Retrieval-Augmented Generation on Edge-Based Computing-in-Memory Architectures Autor Qin, Ruiyang, Yan, Zheyu, Zeng, Dewen, Jia, Zhenge, Liu, Dancheng, Liu, Jianbo, Abbasi, Ahmed, Zheng, Zhi, Cao, Ningyuan, Ni, Kai, Xiong, Jinjun, Shi, Yiyu

“… Although such learning methods can be optimized to reduce resource utilization, the overall required resources remain a heavy burden on edge devices…”
Získat plný text

Laminar 2.0: Serverless Stream Processing with Enhanced Code Search and Recommendations Autor Rotchford, Daniel, Evans, Samuel, Filgueira, Rosa

“… Building on Laminar 1.0, this version introduces improved dependency management, client-server functionality, and advanced deep learning models for semantic search…”
Získat plný text

MelissaDL x Breed: Towards Data-Efficient On-line Supervised Training of Multi-parametric Surrogates with Active Learning Autor Dymchenko, Sofya, Purandare, Abhishek, Raffin, Bruno

“… In this paper we introduce a new active learning method to enhance data-efficiency for on-line surrogate training…”
Získat plný text