61 citations · 125 across the 16 of their papers we have counts for
16 papers
MEP: Multiple Kernel Learning Enhancing Relative Positional Encoding Length Extrapolation
Weiguo Gao
When the predicted sequence length exceeds the length seen during training, the transformer's inference accuracy diminishes. Existing relative position encoding methods, such as th…
Weighted Trace-Penalty Minimization for Full Configuration Interaction
Weiguo Gao, Yingzhou Li, Hanxiang Shen
A novel unconstrained optimization model named weighted trace-penalty minimization (WTPM) is proposed to address the extreme eigenvalue problem arising from the Full Configuration…
A More Stable Accelerated Gradient Method Inspired by Continuous-Time Perspective
Yasong Feng, Weiguo Gao
Nesterov's accelerated gradient method (NAG) is widely used in problems with machine learning background including deep learning, and is corresponding to a continuous-time differen…
SOFT: Softmax-free Transformer with Linear Complexity
Jiachen Lu, Jinghan Yao, Junge Zhang +6
Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employmen…
Global Convergence of Triangularized Orthogonalization-free Method
Weiguo Gao, Yingzhou Li, Bichen Lu
This paper proves the global convergence of a triangularized orthogonalization-free method (TriOFM). TriOFM, in general, applies a triangularization idea to the gradient of an obje…
A Diversity-Enhanced and Constraints-Relaxed Augmentation for Low-Resource Classification
Guang Liu, Hailong Huang, Yuzhao Mao +3
Data augmentation (DA) aims to generate constrained and diversified data to improve classifiers in Low-Resource Classification (LRC). Previous studies mostly use a fine-tuned Langu…
Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup
Guang Liu, Yuzhao Mao, Hailong Huang +2
Mixup is a recent regularizer for current deep classification networks. Through training a neural network on convex combinations of pairs of examples and their labels, it imposes l…
Blind super-resolution of point sources via fast iterative hard thresholding
Zengying Zhu, Jinchi Chen, Weiguo Gao
In this work, we develop a provable fast algorithm for blind super-resolution based on the low rank structure of vectorized Hankel matrix associated with the target matrix. Theoret…
Stability and Super-resolution of MUSIC and ESPRIT for Multi-snapshot Spectral Estimation
Weilin Li, Zengying Zhu, Weiguo Gao +1
This paper studies the spectral estimation problem of estimating the locations of a fixed number of point sources given multiple snapshots of Fourier measurements collected by a un…
DialogueTRM: Exploring the Intra- and Inter-Modal Emotional Behaviors in the Conversation
Yuzhao Mao, Qi Sun, Guang Liu +4
Emotion Recognition in Conversations (ERC) is essential for building empathetic human-machine systems. Existing studies on ERC primarily focus on summarizing the context informatio…
A Partial Regularization Method for Network Compression
E Zhenqian, Gao Weiguo
Deep Neural Networks have achieved remarkable success relying on the developing availability of GPUs and large-scale datasets with increasing network depth and width. However, due…
Vectorized Hankel Lift: A Convex Approach for Blind Super-Resolution of Point Sources
Jinchi Chen, Weiguo Gao, Sihan Mao +1
We consider the problem of resolving point sources from samples at the low end of the spectrum when point spread functions (PSFs) are not known. Assuming that the spectrum…
Triangularized Orthogonalization-free Method for Solving Extreme Eigenvalue Problems
Weiguo Gao, Yingzhou Li, Bichen Lu
A novel orthogonalization-free method together with two specific algorithms are proposed to solve extreme eigenvalue problems. On top of gradient-based algorithms, the proposed alg…
Hierarchical Context Enhanced Multi-Domain Dialogue System for Multi-domain Task Completion
Jingyuan Yang, Guang Liu, Yuzhao Mao +5
Task 1 of the DSTC8-track1 challenge aims to develop an end-to-end multi-domain dialogue system to accomplish complex users' goals under tourist information desk settings. This pap…
An Improving Framework of regularization for Network Compression
E Zhenqian, Gao Weiguo
Deep Neural Networks have achieved remarkable success relying on the developing high computation capability of GPUs and large-scale datasets with increasing network depth and width…
Exact matrix completion based on low rank Hankel structure in the Fourier domain
Jinchi Chen, Weiguo Gao, Ke Wei
Matrix completion is about recovering a matrix from its partial revealed entries, and it can often be achieved by exploiting the inherent simplicity or low dimensional structure of…