Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Valkanas, Antonios"'
Autor:
Glavas, Theodore, Chataoui, Joud, Regol, Florence, Jabbour, Wassim, Valkanas, Antonios, Oreshkin, Boris N., Coates, Mark
The vast size of Large Language Models (LLMs) has prompted a search to optimize inference. One effective approach is dynamic inference, which adapts the architecture to the sample-at-hand to reduce the overall computational cost. We empirically exami
Externí odkaz:
http://arxiv.org/abs/2410.20022
Autor:
Thapaliya, Bishal, Nguyen, Anh, Lu, Yao, Xie, Tian, Grudetskyi, Igor, Lin, Fudong, Valkanas, Antonios, Liu, Jingyu, Chakraborty, Deepayan, Fehri, Bilel
Classifying nodes in a graph is a common problem. The ideal classifier must adapt to any imbalances in the class distribution. It must also use information in the clustering structure of real-world graphs. Existing Graph Neural Networks (GNNs) have n
Externí odkaz:
http://arxiv.org/abs/2410.11765
Online deep learning solves the problem of learning from streams of data, reconciling two opposing objectives: learn fast and learn deep. Existing work focuses almost exclusively on exploring pure deep learning solutions, which are much better suited
Externí odkaz:
http://arxiv.org/abs/2405.18281
Recommender systems have become an integral part of online platforms. Every day the volume of training data is expanding and the number of user interactions is constantly increasing. The exploration of larger and more expressive models has become a n
Externí odkaz:
http://arxiv.org/abs/2403.03993
Adaptive importance sampling (AIS) methods provide a useful alternative to Markov Chain Monte Carlo (MCMC) algorithms for performing inference of intractable distributions. Population Monte Carlo (PMC) algorithms constitute a family of AIS approaches
Externí odkaz:
http://arxiv.org/abs/2312.03857
Autor:
Wang, Yuening, Zhang, Yingxue, Valkanas, Antonios, Tang, Ruiming, Ma, Chen, Hao, Jianye, Coates, Mark
Recommender systems now consume large-scale data and play a significant role in improving user experience. Graph Neural Networks (GNNs) have emerged as one of the most effective recommender system models because they model the rich relational informa
Externí odkaz:
http://arxiv.org/abs/2305.01204
There have been several recent efforts towards developing representations for multivariate time-series in an unsupervised learning framework. Such representations can prove beneficial in tasks such as activity recognition, health monitoring, and anom
Externí odkaz:
http://arxiv.org/abs/2209.10662
Multiple Instance Learning (MIL) is a weakly supervised learning problem where the aim is to assign labels to sets or bags of instances, as opposed to traditional supervised learning where each instance is assumed to be independent and identically di
Externí odkaz:
http://arxiv.org/abs/2202.11132
Autor:
Oreshkin, Boris N., Valkanas, Antonios, Harvey, Félix G., Ménard, Louis-Simon, Bocquelet, Florent, Coates, Mark J.
We show that the task of synthesizing human motion conditioned on a set of key frames can be solved more accurately and effectively if a deep learning based interpolator operates in the delta mode using the spherical linear interpolator as a baseline
Externí odkaz:
http://arxiv.org/abs/2201.06701