Zobrazeno 1 - 10
of 74
pro vyhledávání: '"Rostamizadeh, Afshin"'
Autor:
Ye, Ke, Jiang, Heinrich, Rostamizadeh, Afshin, Chakrabarti, Ayan, DeSalvo, Giulia, Kagy, Jean-François, Karydas, Lazaros, Citovsky, Gui, Kumar, Sanjiv
Pre-training large language models is known to be extremely resource intensive and often times inefficient, under-utilizing the information encapsulated in the training text sequences. In this paper, we present SpacTor, a new training procedure consi
Externí odkaz:
http://arxiv.org/abs/2401.13160
Autor:
Zhou, Yongchao, Lyu, Kaifeng, Rawat, Ankit Singh, Menon, Aditya Krishna, Rostamizadeh, Afshin, Kumar, Sanjiv, Kagy, Jean-François, Agarwal, Rishabh
Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens, which are then verified in parallel by the larger target model, resulting in the text generated according to the ta
Externí odkaz:
http://arxiv.org/abs/2310.08461
Autor:
Citovsky, Gui, DeSalvo, Giulia, Kumar, Sanjiv, Ramalingam, Srikumar, Rostamizadeh, Afshin, Wang, Yunjuan
We present a subset selection algorithm designed to work with arbitrary model families in a practical batch setting. In such a setting, an algorithm can sample examples one at a time but, in order to limit overhead costs, is only able to update its s
Externí odkaz:
http://arxiv.org/abs/2301.12052
Given a labeled training set and a collection of unlabeled data, the goal of active learning (AL) is to identify the best unlabeled points to label. In this comprehensive study, we analyze the performance of a variety of AL algorithms on deep neural
Externí odkaz:
http://arxiv.org/abs/2210.03822
Autor:
Citovsky, Gui, DeSalvo, Giulia, Gentile, Claudio, Karydas, Lazaros, Rajagopalan, Anand, Rostamizadeh, Afshin, Kumar, Sanjiv
The ability to train complex and highly effective models often requires an abundance of training data, which can easily become a bottleneck in cost, time, and computational resources. Batch active learning, which adaptively issues batched queries to
Externí odkaz:
http://arxiv.org/abs/2107.14263
Publikováno v:
ICLR 2022
In real-world systems, models are frequently updated as more data becomes available, and in addition to achieving high accuracy, the goal is to also maintain a low difference in predictions compared to the base model (i.e. predictive "churn"). If mod
Externí odkaz:
http://arxiv.org/abs/2106.02654
Autor:
Jiang, Heinrich, Rostamizadeh, Afshin
We analyze the problem of active covering, where the learner is given an unlabeled dataset and can sequentially label query examples. The objective is to label query all of the positive examples in the fewest number of total label queries. We show un
Externí odkaz:
http://arxiv.org/abs/2106.02552
Federated learning is typically approached as an optimization problem, where the goal is to minimize a global loss function by distributing computation across client devices that possess local data and specify different parts of the global objective.
Externí odkaz:
http://arxiv.org/abs/2010.05273
Autor:
Levinson, Jake, Esteves, Carlos, Chen, Kefan, Snavely, Noah, Kanazawa, Angjoo, Rostamizadeh, Afshin, Makadia, Ameesh
Symmetric orthogonalization via SVD, and closely related procedures, are well-known techniques for projecting matrices onto $O(n)$ or $SO(n)$. These tools have long been used for applications in computer vision, for example optimal 3D alignment probl
Externí odkaz:
http://arxiv.org/abs/2006.14616
We propose using active learning based techniques to further improve the state-of-the-art semi-supervised learning MixMatch algorithm. We provide a thorough empirical evaluation of several active-learning and baseline methods, which successfully demo
Externí odkaz:
http://arxiv.org/abs/1912.00594