Zobrazeno 1 - 10
of 1 273
pro vyhledávání: '"Lee-Sunwoo"'
Autor:
Ahn, Hojae, Briegel, Florian, Han, Jimin, Jeon, Mingyu, Herbst, Thomas M., Lee, Sumin, Park, Woojin, Lee, Sunwoo, Jung, Inhwan, Ji, Tae-Geun, Kim, Changgon, Kim, Geon Hee, Gaessler, Wolfgang, Kuhlberg, Markus, Park, Hyun Chul, Pak, Soojong, Konidaris, Nicholas P., Drory, Niv, Sánchez-Gallego, José R., Froning, Cynthia S., Ramirez, Solange, Kollmeier, Juna A.
The fifth Sloan Digital Sky Survey (SDSS-V) Local Volume Mapper (LVM) is a wide-field integral field unit (IFU) survey that uses an array of four 160 mm fixed telescopes with siderostats to minimize the number of moving parts. Individual telescope ob
Externí odkaz:
http://arxiv.org/abs/2407.08319
Publikováno v:
IEEE Transactions on Mobile Computing, Early Access, (2024)
In Federated Learning (FL), clients may have weak devices that cannot train the full model or even hold it in their memory space. To implement large-scale FL applications, thus, it is crucial to develop a distributed learning method that enables the
Externí odkaz:
http://arxiv.org/abs/2406.15125
Autor:
Daudlin, Stuart, Rizzo, Anthony, Lee, Sunwoo, Khilwani, Devesh, Ou, Christine, Wang, Songli, Novick, Asher, Gopal, Vignesh, Cullen, Michael, Parsons, Robert, Molnar, Alyosha, Bergman, Keren
Artificial intelligence (AI) hardware is positioned to unlock revolutionary computational abilities across diverse fields ranging from fundamental science [1] to medicine [2] and environmental science [3] by leveraging advanced semiconductor chips in
Externí odkaz:
http://arxiv.org/abs/2310.01615
Recently, deep multi-agent reinforcement learning (MARL) has gained significant popularity due to its success in various cooperative multi-agent tasks. However, exploration still remains a challenging problem in MARL due to the partial observability
Externí odkaz:
http://arxiv.org/abs/2308.11272
Quasi-Newton methods still face significant challenges in training large-scale neural networks due to additional compute costs in the Hessian related computations and instability issues in stochastic training. A well-known method, L-BFGS that efficie
Externí odkaz:
http://arxiv.org/abs/2307.13744
This paper presents a method for building a personalized open-domain dialogue system to address the WWH (WHAT, WHEN, and HOW) problem for natural response generation in a commercial setting, where personalized dialogue responses are heavily interleav
Externí odkaz:
http://arxiv.org/abs/2306.03361
Autor:
Zhang, Tuo, Feng, Tiantian, Alam, Samiul, Dimitriadis, Dimitrios, Lee, Sunwoo, Zhang, Mi, Narayanan, Shrikanth S., Avestimehr, Salman
In this work, we propose GPT-FL, a generative pre-trained model-assisted federated learning (FL) framework. At its core, GPT-FL leverages generative pre-trained models to generate diversified synthetic data. These generated data are used to train a d
Externí odkaz:
http://arxiv.org/abs/2306.02210
Publikováno v:
CVPR 2023 FedVision Workshop
In cross-device Federated Learning (FL) environments, scaling synchronous FL methods is challenging as stragglers hinder the training process. Moreover, the availability of each client to join the training is highly variable over time due to system h
Externí odkaz:
http://arxiv.org/abs/2304.06947
Autor:
Tang, Zhenheng, Chu, Xiaowen, Ran, Ryan Yide, Lee, Sunwoo, Shi, Shaohuai, Zhang, Yonggang, Wang, Yuxin, Liang, Alex Qiaozhong, Avestimehr, Salman, He, Chaoyang
Federated Learning (FL) enables collaborations among clients for train machine learning models while protecting their data privacy. Existing FL simulation platforms that are designed from the perspectives of traditional distributed training, suffer f
Externí odkaz:
http://arxiv.org/abs/2303.01778
Autor:
Zhang, Tuo, Feng, Tiantian, Alam, Samiul, Lee, Sunwoo, Zhang, Mi, Narayanan, Shrikanth S., Avestimehr, Salman
Federated learning (FL) has gained substantial attention in recent years due to the data privacy concerns related to the pervasiveness of consumer devices that continuously collect data from users. While a number of FL benchmarks have been developed
Externí odkaz:
http://arxiv.org/abs/2210.15707