Publications (24)
Block-Normalized Gradient Method: An Empirical Study for Training Deep Neural Network
Adams Wei Yu, Lei Huang, Qihang Lin +2
In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization. The technique essentially contains two consecutive steps in e…
Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks
Lei Huang, Xianglong Liu, Bo Lang +3
Orthogonal matrix has shown advantages in training Recurrent Neural Networks (RNNs), but such matrix is limited to be square for the hidden-to-hidden transformation in RNNs. In thi…
An Improved Gap-Dependency Analysis of the Noisy Power Method
Maria Florina Balcan, Simon S. Du, Yining Wang +1
We consider the noisy power method algorithm, which has wide applications in machine learning and statistics, especially those related to principal component analysis (PCA) under r…
Efficient Structured Matrix Rank Minimization
Adams Wei Yu, Wanli Ma, Yaoliang Yu +2
We study the problem of finding structured low-rank matrices using nuclear norm regularization where the structure is encoded by a linear map. In contrast to most known approaches…
Large Language Models Cannot Self-Correct Reasoning Yet
Jie Huang, Xinyun Chen, Swaroop Mishra +4
Large Language Models (LLMs) have emerged as a groundbreaking technology with their unparalleled text generation capabilities across various applications. Nevertheless, concerns pe…
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
Zirui Wang, Jiahui Yu, Adams Wei Yu +3
With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream ta…