Zobrazeno 1 - 10
of 260
pro vyhledávání: '"IOANNIDIS, STRATIS"'
Ou et al. (2022) introduce the problem of learning set functions from data generated by a so-called optimal subset oracle. Their approach approximates the underlying utility function with an energy-based model, whose parameters are estimated via mean
Externí odkaz:
http://arxiv.org/abs/2412.11239
Autor:
Zhan, Zheng, Kong, Zhenglun, Gong, Yifan, Wu, Yushu, Meng, Zichong, Zheng, Hangyu, Shen, Xuan, Ioannidis, Stratis, Niu, Wei, Zhao, Pu, Wang, Yanzhi
State Space Models (SSMs) have the advantage of keeping linear computational complexity compared to attention modules in transformers, and have been applied to vision tasks as a new type of powerful vision foundation model. Inspired by the observatio
Externí odkaz:
http://arxiv.org/abs/2409.18962
Addressing intermittent client availability is critical for the real-world deployment of federated learning algorithms. Most prior work either overlooks the potential non-stationarity in the dynamics of client unavailability or requires substantial m
Externí odkaz:
http://arxiv.org/abs/2409.17446
Autor:
Chee, Jerry, Kalyanaraman, Shankar, Ernala, Sindhu Kiranmai, Weinsberg, Udi, Dean, Sarah, Ioannidis, Stratis
We consider a recommender system that takes into account the interplay between recommendations, the evolution of user interests, and harmful content. We model the impact of recommendations on user behavior, particularly the tendency to consume harmfu
Externí odkaz:
http://arxiv.org/abs/2406.09882
Autor:
Siew, Marie, Zhang, Haoran, Park, Jong-Ik, Liu, Yuezhou, Ruan, Yichen, Su, Lili, Ioannidis, Stratis, Yeh, Edmund, Joe-Wong, Carlee
Federated learning (FL) enables collaborative learning across multiple clients. In most FL work, all clients train a single learning task. However, the recent proliferation of FL applications may increasingly require multiple FL tasks to be trained s
Externí odkaz:
http://arxiv.org/abs/2404.13841
Federated learning is a popular distributed learning approach for training a machine learning model without disclosing raw data. It consists of a parameter server and a possibly large collection of clients (e.g., in cross-device federated learning) t
Externí odkaz:
http://arxiv.org/abs/2404.10091
As edge computing capabilities increase, model learning deployments in diverse edge environments have emerged. In experimental design networks, introduced recently, network routing and rate allocation are designed to aid the transfer of data from sen
Externí odkaz:
http://arxiv.org/abs/2401.04996
Autor:
Belgiovine, Mauro, Groen, Joshua, Sirera, Miquel, Tassie, Chinenye, Yıldız, Ayberk Yarkın, Trudeau, Sage, Ioannidis, Stratis, Chowdhury, Kaushik
Spectrum sharing allows different protocols of the same standard (e.g., 802.11 family) or different standards (e.g., LTE and DVB) to coexist in overlapping frequency bands. As this paradigm continues to spread, wireless systems must also evolve to id
Externí odkaz:
http://arxiv.org/abs/2401.04837
Several recent methods for interpretability model feature interactions by looking at the Hessian of a neural network. This poses a challenge for ReLU networks, which are piecewise-linear and thus have a zero Hessian almost everywhere. We propose Smoo
Externí odkaz:
http://arxiv.org/abs/2311.00858
We study monotone submodular maximization under general matroid constraints in the online setting. We prove that online optimization of a large class of submodular functions, namely, weighted threshold potential functions, reduces to online convex op
Externí odkaz:
http://arxiv.org/abs/2309.04339