Zobrazeno 1 - 10
of 557
pro vyhledávání: '"Yang, Tianbao"'
Existing studies of training state-of-the-art Contrastive Language-Image Pretraining (CLIP) models on large-scale data involve hundreds of or even thousands of GPUs due to the requirement of a large batch size. However, such a large amount of resourc
Externí odkaz:
http://arxiv.org/abs/2407.01445
Implicit graph neural networks have gained popularity in recent years as they capture long-range dependencies while improving predictive performance in static graphs. Despite the tussle between performance degradation due to the oversmoothing of lear
Externí odkaz:
http://arxiv.org/abs/2406.17894
This paper studies learning fair encoders in a self-supervised learning (SSL) setting, in which all data are unlabeled and only a small portion of them are annotated with sensitive attribute. Adversarial fair representation learning is well suited fo
Externí odkaz:
http://arxiv.org/abs/2406.05686
Autor:
Hong, Ilgee, Li, Zichong, Bukharin, Alexander, Li, Yixiao, Jiang, Haoming, Yang, Tianbao, Zhao, Tuo
Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values by learning rewards from human preference data. Due to various reasons, however, such data typically takes the form of rankings over pairs
Externí odkaz:
http://arxiv.org/abs/2406.02764
In this paper, we study a class of non-smooth non-convex problems in the form of $\min_{x}[\max_{y\in Y}\phi(x, y) - \max_{z\in Z}\psi(x, z)]$, where both $\Phi(x) = \max_{y\in Y}\phi(x, y)$ and $\Psi(x)=\max_{z\in Z}\psi(x, z)$ are weakly convex fun
Externí odkaz:
http://arxiv.org/abs/2405.18577
The temperature parameter plays a profound role during training and/or inference with large foundation models (LFMs) such as large language models (LLMs) and CLIP models. Particularly, it adjusts the logits in the softmax function in LLMs, which is c
Externí odkaz:
http://arxiv.org/abs/2404.04575
Regression is a fundamental task in machine learning that has garnered extensive attention over the past decades. The conventional approach for regression involves employing loss functions that primarily concentrate on aligning model prediction with
Externí odkaz:
http://arxiv.org/abs/2402.06104
Within the intensive care unit (ICU), a wealth of patient data, including clinical measurements and clinical notes, is readily available. This data is a valuable resource for comprehending patient health and informing medical decisions, but it also c
Externí odkaz:
http://arxiv.org/abs/2312.06855
Autor:
Wang, Bokun, Yang, Tianbao
This paper revisits a class of convex Finite-Sum Coupled Compositional Stochastic Optimization (cFCCO) problems with many applications, including group distributionally robust optimization (GDRO), learning with imbalanced data, reinforcement learning
Externí odkaz:
http://arxiv.org/abs/2312.02277
While deep AUC maximization (DAM) has shown remarkable success on imbalanced medical tasks, e.g., chest X-rays classification and skin lesions classification, it could suffer from severe overfitting when applied to small datasets due to its aggressiv
Externí odkaz:
http://arxiv.org/abs/2310.11693