1 code implementation • 6 May 2024 • Honghao Li, Yiwen Zhang, Yi Zhang, Lei Sang, Yun Yang
Specifically, the framework employs the SSEM at the bottom of the model to differentiate between samples, thereby assigning a more suitable encoder for each sample.
Ranked #1 on Click-Through Rate Prediction on Frappe
no code implementations • 25 Apr 2024 • Chenyang Wang, Yun Yang
This work introduces a new method for selecting the number of components in finite mixture models (FMMs) using variational Bayes, inspired by the large-sample properties of the Evidence Lower Bound (ELBO) derived from mean-field (MF) variational approximation.
no code implementations • 8 Jan 2024 • Yun Yang, Zhiping Lu, Ming Li, Rang Liu, Qian Liu
Motivated by this fact, in this paper we first investigate the amplification principle of typical active RIS and propose a more accurate amplification model based on amplifier hardware characteristics.
no code implementations • 17 Dec 2023 • Yangfan Zhang, Yun Yang
This article considers Bayesian model selection via mean-field (MF) variational approximation.
1 code implementation • 15 Jun 2023 • Yifan Chen, Rentian Yao, Yun Yang, Jie Chen
The study includes a set of experiments to support the theory and method, including approximating the GW distance, preserving the graph spectrum, classifying graphs using spectral information, and performing regression using graph convolutional networks.
no code implementations • 1 Jun 2023 • Anirban Bhattacharya, Debdeep Pati, Yun Yang
As a computational alternative to Markov chain Monte Carlo approaches, variational inference (VI) is becoming more and more popular for approximating intractable posterior distributions in large-scale Bayesian models due to its comparable efficacy and superior efficiency.
no code implementations • 30 May 2023 • Yudi Li, Min Tang, Yun Yang, Ruofeng Tong, Shuangcai Yang, Yao Li, Bailin An, Qilong Kou
We present a novel learning method to predict the cloth deformation for skeleton-based characters with a two-stream network.
no code implementations • 29 May 2023 • Yubo Zhuang, Xiaohui Chen, Yun Yang, Richard Y. Zhang
In contrast, nonnegative matrix factorization (NMF) is a simple clustering algorithm widely used by machine learning practitioners, but it lacks a solid statistical underpinning and theoretical guarantees.
2 code implementations • CVPR 2023 • Fei Du, Peng Yang, Qi Jia, Fengtao Nan, Xiaoting Chen, Yun Yang
In this paper, our goal is to design a simple learning paradigm for long-tail visual recognition, which not only improves the robustness of the feature extractor but also alleviates the bias of the classifier towards head classes while reducing the training skills and overhead.
Ranked #1 on Long-tail Learning on CIFAR-10-LT (ρ=10)
no code implementations • 15 Feb 2023 • Zhichao Lu, Chuntao Ding, Felix Juefei-Xu, Vishnu Naresh Boddeti, Shangguang Wang, Yun Yang
The high performance and small number of model parameters and FLOPs of TFormer are attributed to the proposed hybrid layer and the proposed partially connected feed-forward network (PCS-FFN).
no code implementations • 29 Sep 2022 • Yubo Zhuang, Xiaohui Chen, Yun Yang
Clustering is a widely deployed unsupervised learning tool.
1 code implementation • 14 Sep 2022 • Yubo Zhuang, Xiaohui Chen, Yun Yang
Clustering is an important exploratory data analysis technique to group objects based on their similarity.
no code implementations • 17 Jul 2022 • Rentian Yao, Yun Yang
Variational inference, such as the mean-field (MF) approximation, requires certain conjugacy structures for efficient computation.
1 code implementation • 1 Jun 2022 • Yifan Chen, Tianning Xu, Dilek Hakkani-Tur, Di Jin, Yun Yang, Ruoqing Zhu
This paper revisits the approach from a matrix approximation perspective, and identifies two issues in the existing layer-wise sampling methods: suboptimal sampling probabilities and estimation biases induced by sampling without replacement.
1 code implementation • 20 Jan 2022 • Yubo Zhuang, Xiaohui Chen, Yun Yang
Semidefinite programming (SDP) is a powerful tool for tackling a wide range of computationally hard problems such as clustering.
no code implementations • 13 Dec 2021 • Yudi Li, Min Tang, Yun Yang, Zi Huang, Ruofeng Tong, Shuangcai Yang, Yao Li, Dinesh Manocha
We present a novel mesh-based learning approach (N-Cloth) for plausible 3D cloth deformation prediction.
1 code implementation • NAACL 2022 • Yifan Chen, Qi Zeng, Dilek Hakkani-Tur, Di Jin, Heng Ji, Yun Yang
Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules.
1 code implementation • NeurIPS 2021 • Yifan Chen, Qi Zeng, Heng Ji, Yun Yang
Transformers are expensive to train due to the quadratic time and space complexity in the self-attention mechanism.
no code implementations • 8 Oct 2021 • Yinyin Chen, Shishuang He, Yun Yang, Feng Liang
Our theory introduces a new set of geometric conditions for topic model identifiability, conditions that are weaker than conventional separability conditions, which typically rely on the existence of pure topic documents or of anchor words.
no code implementations • 29 Sep 2021 • Yifan Chen, Tianning Xu, Dilek Hakkani-Tur, Di Jin, Yun Yang, Ruoqing Zhu
To accelerate the training of graph convolutional networks (GCN), many sampling-based methods have been developed for approximating the embedding aggregation.
no code implementations • 23 Sep 2021 • Ke Li, Yun Yang, Naveen N. Narisetty
This new lower bound unifies existing regret bound results that have different dependencies on T due to the use of different values of margin parameter $\alpha$ explicitly implied by their assumptions.
1 code implementation • ICCV 2021 • Ranjie Duan, Yuefeng Chen, Dantong Niu, Yun Yang, A. K. Qin, Yuan He
Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e. g. cartoon.
1 code implementation • NeurIPS 2021 • Yifan Chen, Qi Zeng, Heng Ji, Yun Yang
Transformers are expensive to train due to the quadratic time and space complexity in the self-attention mechanism.
no code implementations • 29 Apr 2021 • Dengcheng Yan, Wenxin Xie, Yiwen Zhang, Qiang He, Yun Yang
Network dismantling aims to degrade the connectivity of a network by removing an optimal set of nodes.
1 code implementation • CVPR 2021 • Ranjie Duan, Xiaofeng Mao, A. K. Qin, Yun Yang, Yuefeng Chen, Shaokai Ye, Yuan He
Though it is well known that the performance of deep neural networks (DNNs) degrades under certain light conditions, there exists no study on the threats of light beams emitted from some physical source as adversarial attacker on DNNs in a real-world scenario.
no code implementations • 9 Mar 2021 • Yifan Chen, Yun Yang
Nystr\"om approximation is a fast randomized method that rapidly solves kernel ridge regression (KRR) problems through sub-sampling the n-by-n empirical kernel matrix appearing in the objective function.
no code implementations • 6 Mar 2021 • Yifan Chen, Yun Yang
Building a sketch of an n-by-n empirical kernel matrix is a common approach to accelerate the computation of many kernel methods.
no code implementations • 26 Feb 2021 • Cheng Xie, Ting Zeng, Hongxin Xiang, Keqin Li, Yun Yang, Qing Liu
The approach also applies a semi-supervised learning process to re-train knowledge-to-visual model.
no code implementations • 23 Feb 2021 • Hongxin Xiang, Cheng Xie, Ting Zeng, Yun Yang
Suffering from the semantic insufficiency and domain-shift problems, most of existing state-of-the-art methods fail to achieve satisfactory results for Zero-Shot Learning (ZSL).
no code implementations • 25 Jan 2021 • Cheng Xie, Hongxin Xiang, Ting Zeng, Yun Yang, Beibei Yu, Qing Liu
CKL enables more relevant semantic features to be trained for semantic-to-visual feature embedding in ZSL, while Taxonomy Regularization (TR) significantly improves the intersections with unseen images with more generalized visual features generated from generative network.
no code implementations • 6 Sep 2020 • Po Yang, Jun Qi, Xulong Wang, Yun Yang
The fused sparse group Lasso (FSGL) method allows the simultaneous selection of a common set of country-based factors for multiple time points of COVID-19 epidemic and also enables incorporating temporal smoothness of each factor over the whole early phase period.
no code implementations • 26 Apr 2020 • Xiangdong Zhang, Tengjun Wang, Yun Yang
Because hyperspectral remote sensing images contain a lot of redundant information and the data structure is highly non-linear, leading to low classification accuracy of traditional machine learning methods.
no code implementations • 5 Apr 2020 • Xi Chen, Jason D. Lee, He Li, Yun Yang
To abandon this eigengap assumption, we consider a new route in our analysis: instead of exactly identifying the top-$L$-dim eigenspace, we show that our estimator is able to cover the targeted top-$L$-dim population eigenspace.
1 code implementation • CVPR 2020 • Ranjie Duan, Xingjun Ma, Yisen Wang, James Bailey, A. K. Qin, Yun Yang
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples.
no code implementations • 5 Jan 2020 • Xiaohui Chen, Yun Yang
We determine the information-theoretic cutoff value on separation of cluster centers for exact recovery of cluster labels in a $K$-component Gaussian mixture model with equal cluster sizes.
no code implementations • 4 Nov 2019 • Wei Han, Yun Yang
We conduct non-asymptotic analysis on the mean-field variational inference for approximating posterior distributions in complex Bayesian models that may involve latent variables.
no code implementations • 22 Sep 2019 • Dongwei Li, Shuliang Wang, Nan Gao, Qiang He, Yun Yang
A novel approach is proposed to achieve cost-effective big data clustering in the cloud.
no code implementations • 22 Mar 2019 • Peng Zhao, Yun Yang, Qiao-Chu He
Many statistical estimators for high-dimensional linear regression are M-estimators, formed through minimizing a data-dependent square loss function plus a regularizer.
no code implementations • 11 Mar 2019 • Xiaohui Chen, Yun Yang
We show that exact recovery of the localized diffusion $K$-means is fully adaptive to the local probability density and geometric structures of the underlying submanifolds.
no code implementations • 25 Dec 2017 • Debdeep Pati, Anirban Bhattacharya, Yun Yang
The article addresses a long-standing open problem on the justification of using variational Bayes methods for parameter estimation.
no code implementations • 9 Oct 2017 • Yun Yang, Debdeep Pati, Anirban Bhattacharya
We propose a family of variational approximations to Bayesian posterior distributions, called $\alpha$-VB, with provable statistical guarantees.
no code implementations • 16 Aug 2017 • Yun Yang, Anirban Bhattacharya, Debdeep Pati
By developing a comparison inequality between two GPs, we provide exact characterization of frequentist coverage probabilities of Bayesian point-wise credible intervals and simultaneous credible bands of the regression function.
no code implementations • 17 Apr 2017 • Yun Yang
The proposed estimator, called Constrained Lasso (CLasso) estimator, is obtained by simultaneously solving two estimating equations---one imposing a zero-bias constraint for the low-dimensional parameter and the other forming an $\ell_1$-penalized procedure for the high-dimensional nuisance parameter.
no code implementations • 2 Jan 2017 • Yun Yang, Debdeep Pati
In this article, we investigate large sample properties of model selection procedures in a general Bayesian framework when a closed form expression of the marginal likelihood function is not available or a local asymptotic quadratic approximation of the log-likelihood function does not exist.
no code implementations • 25 May 2016 • Michael. I. Jordan, Jason D. Lee, Yun Yang
CSL provides a communication-efficient surrogate to the global likelihood that can be used for low-dimensional estimation, high-dimensional regularized estimation and Bayesian inference.
no code implementations • 11 Jul 2015 • Yun Yang, Surya Tokdar
In spite of the recent surge of interest in quantile regression, joint estimation of linear quantile planes remains a great challenge in statistics and econometrics.
no code implementations • 29 May 2015 • Yun Yang, Martin J. Wainwright, Michael. I. Jordan
We study the computational complexity of Markov chain Monte Carlo (MCMC) methods for high-dimensional Bayesian linear regression under sparsity constraints.
no code implementations • 25 Jan 2015 • Yun Yang, Mert Pilanci, Martin J. Wainwright
Kernel ridge regression (KRR) is a standard method for performing non-parametric regression over reproducing kernel Hilbert spaces.
no code implementations • 6 Mar 2014 • Yun Yang, David B. Dunson
It is generally believed that ensemble approaches, which combine multiple algorithms or models, can outperform any single algorithm at machine learning tasks, such as prediction.
no code implementations • 22 Apr 2013 • Bruno Cornelis, Yun Yang, Joshua T. Vogelstein, Ann Dooms, Ingrid Daubechies, David Dunson
The preservation of our cultural heritage is of paramount importance.