no code implementations • 8 Apr 2024 • Chao GAO, Sai Qian Zhang
Due to the scale of LLM, PEFT operations are usually executed in the public environment (e. g., cloud server).
no code implementations • 21 Mar 2024 • Zeyu Han, Chao GAO, Jinyang Liu, Jeff Zhang, Sai Qian Zhang
In addition to the algorithmic perspective, we overview various real-world system designs to investigate the implementation costs associated with different PEFT algorithms.
no code implementations • 27 Feb 2024 • Le Cheng, Peican Zhu, Keke Tang, Chao GAO, Zhen Wang
In this paper, we address a more challenging task, rumor source detection with incomplete user data, and propose a novel framework, i. e., Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion (GIN-SD), to tackle this challenge.
1 code implementation • 18 Dec 2023 • Farnaz Kohankhaki, Kiarash Aghakasiri, Hongming Zhang, Ting-Han Wei, Chao GAO, Martin Müller
We study and improve MCTS in the context where the environment model is given but imperfect.
no code implementations • 10 Dec 2023 • Shu Yin, Chao GAO, Zhen Wang
With the rise of social media, the spread of fake news has become a significant concern, potentially misleading public perceptions and impacting social stability.
no code implementations • 6 Dec 2023 • Peiji Song, Zhouyi Hu, Yizhan Dai, YuAn Liu, Chao GAO, Chun-Kit Chan
Faster-than-Nyquist non-orthogonal frequency-division multiplexing (FTN-NOFDM) is robust against the steep frequency roll-off by saving signal bandwidth.
no code implementations • 30 Aug 2023 • Yuetian Luo, Chao GAO
From the statistical perspective, the minimax error rate of graphon estimation has been established by Gao et al (2015) for both stochastic block model (SBM) and nonparametric graphon estimation.
no code implementations • 28 Jun 2023 • Dongpeng Hou, Zhen Wang, Chao GAO, Xuelong Li
Snapshot observation based source localization has been widely studied due to its accessibility and low cost.
no code implementations • 19 Apr 2023 • Subhodh Kotekal, Chao GAO
Sparse additive models are an attractive choice in circumstances calling for modelling flexibility in the face of high dimensionality.
no code implementations • ICCV 2023 • Xin Deng, Chao GAO, Mai Xu
In this paper, we propose a novel method namely PIRNet, which operates privacy-preserving image restoration in the steganographic domain.
no code implementations • 8 Oct 2021 • Chao GAO, Yandi Shen, Anderson Y. Zhang
The Bradley-Terry-Luce (BTL) model is a benchmark model for pairwise comparisons between individuals.
no code implementations • 28 Sep 2021 • Chao GAO, Anderson Y. Zhang
We study the statistical estimation problem of orthogonal group synchronization and rotation group synchronization.
no code implementations • 12 Jul 2021 • Yiming Li, Chao GAO, Mark S. Leeson, Xiaofeng Li
This paper investigates the asymptotic BER performance of coherent optical wireless communication systems in Gamma-Gamma turbulence when applying the V-BLAST MIMO scheme.
no code implementations • 9 Jul 2021 • Yue Jin, Tianqing Zheng, Chao GAO, Guoqiang Xu
Analyzing human affect is vital for human-computer interaction systems.
no code implementations • 30 Mar 2021 • Chao GAO
We discuss the interconnections between AO*, adversarial game-searching algorithms, e. g., proof number search and minimax search.
no code implementations • 8 Feb 2021 • Chao GAO
We point out that the computation of true \emph{proof} and \emph{disproof} numbers for proof number search in arbitrary directed acyclic graphs is NP-hard, an important theoretical result for proof number search.
no code implementations • 21 Jan 2021 • Pinhan Chen, Chao GAO, Anderson Y. Zhang
We consider the problem of ranking $n$ players from partial pairwise comparison data under the Bradley-Terry-Luce model.
no code implementations • 7 Jan 2021 • Chao GAO, Anderson Y. Zhang
We study the phase synchronization problem with noisy measurements $Y=z^*z^{*H}+\sigma W\in\mathbb{C}^{n\times n}$, where $z^*$ is an $n$-dimensional complex unit-modulus vector and $W$ is a complex-valued Gaussian random matrix.
no code implementations • 24 Dec 2020 • Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei zhang, Weimin Li, Xiongjun Pi, Jujie He, Chao GAO, Haitao Long, Quan Yuan
In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.
no code implementations • 22 Dec 2020 • Ye-Ming Meng, Jing Zhang, Peng Zhang, Chao GAO, Shi-Ju Ran
Tensor network, which originates from quantum physics, is emerging as an efficient tool for classical and quantum machine learning.
no code implementations • 8 Sep 2020 • Fengshuo Zhang, Chao GAO
We study the convergence rates of empirical Bayes posterior distributions for nonparametric and high-dimensional inference.
no code implementations • 30 Jun 2020 • Pinhan Chen, Chao GAO, Anderson Y. Zhang
We also derive the optimal signal to noise ratio condition for the exact recovery of the top-$k$ set.
no code implementations • 20 May 2020 • Chao Gao, John Lafferty
A new type of robust estimation problem is introduced where the goal is to recover a statistical model that has been corrupted after it has been estimated from data.
no code implementations • 4 Nov 2019 • Chao Gao, Anderson Y. Zhang
We propose a general modeling and algorithmic framework for discrete structure recovery that can be applied to a wide range of problems.
no code implementations • 25 Sep 2019 • Chao GAO, Martin Mueller, Ryan Hayward, Hengshuai Yao, Shangling Jui
A three-head network architecture has been recently proposed that can learn a third action-value head on a fixed dataset the same as for two-head net.
no code implementations • 17 Aug 2019 • Yang Liu, Jianpeng Zhang, Chao GAO, Jinghua Qu, Lixin Ji
In this paper, we investigate the effect of different hyperparameters as well as different combinations of hyperparameters settings on the performance of the Attention-Gated Convolutional Neural Networks (AGCNNs), e. g., the kernel window size, the number of feature maps, the keep rate of the dropout layer, and the activation function.
no code implementations • 10 Aug 2019 • Yang Liu, Jianpeng Zhang, Chao GAO, Jinghua Qu, Lixin Ji
Activation functions play a key role in providing remarkable performance in deep neural networks, and the rectified linear unit (ReLU) is one of the most widely used activation functions.
no code implementations • 26 Jul 2019 • Chao Gao, Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor
In this paper, we illuminate reasons behind this failure by providing a thorough analysis on the hardness of random exploration in Pommerman.
no code implementations • ICLR 2019 • Chao GAO, jiyi LIU, Yuan YAO, Weizhi Zhu
In particular, we show that a JS-GAN that uses a neural network discriminator with at least one hidden layer is able to achieve the minimax rate of robust mean estimation under Huber's $\epsilon$-contamination model.
1 code implementation • 20 Apr 2019 • Chao Gao, Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor
The Pommerman Team Environment is a recently proposed benchmark which involves a multi-agent domain with challenges such as partial observability, decentralized execution (without communication), and very sparse and delayed rewards.
no code implementations • 10 Apr 2019 • Bilal Kartal, Pablo Hernandez-Leal, Chao GAO, Matthew E. Taylor
In this paper, we shed light into the reasons behind this failure by exemplifying and analyzing the high rate of catastrophic events (i. e., suicides) that happen under random exploration in this domain.
1 code implementation • 5 Mar 2019 • Chao Gao, Yuan YAO, Weizhi Zhu
Robust scatter estimation is a fundamental task in statistics.
no code implementations • 18 Dec 2018 • Peng Peng, Liang Pang, Yufeng Yuan, Chao GAO
We show in the experiments that Pommerman is a perfect environment for studying continual learning, and the agent can improve its performance by continually learning new skills without forgetting the old ones.
no code implementations • 14 Nov 2018 • Chao Gao, Zongming Ma
This paper surveys some recent developments in fundamental limits and optimal algorithms for network analysis.
2 code implementations • 4 Oct 2018 • Chao Gao, jiyi LIU, Yuan YAO, Weizhi Zhu
Similar to the derivation of $f$-GANs, we show that these depth functions that lead to statistically optimal robust estimators can all be viewed as variational lower bounds of the total variation distance in the framework of $f$-Learning.
2 code implementations • 22 Aug 2018 • Yang Liu, Lixin Ji, Ruiyang Huang, Tuosiyu Ming, Chao GAO, Jianpeng Zhang
The classification of sentences is very challenging, since sentences contain the limited contextual information.
no code implementations • 15 May 2018 • Zhen Ling, Kaizheng Liu, Yiling Xu, Chao GAO, Yier Jin, Cliff Zou, Xinwen Fu, Wei Zhao
The work in this paper raises the alarm again for the IoT device manufacturers to better secure their products in order to prevent malware attacks like Mirai.
Cryptography and Security
no code implementations • 23 Apr 2018 • Yang Liu, Qiang Qu, Chao GAO
Finally, we replicate this new block into n copies and concatenate them as the input to the FC layer.
no code implementations • ICLR 2018 • Chao Gao, Martin Mueller, Ryan Hayward
As policy gradient method is a kind of generalized policy iteration, we show how these differences in policy iteration are reflected in policy gradient for AMGs.
no code implementations • 7 Dec 2017 • Fengshuo Zhang, Chao GAO
For a class of priors that admit the structure of a mixture of product measures, we propose a novel prior mass condition, under which the variational approximation error of the mean-field class is dominated by convergence rate of the true posterior.
no code implementations • 30 Nov 2017 • Chao Gao
We study the problem of approximate ranking from observations of pairwise interactions.
no code implementations • 2 Oct 2017 • Chao Gao, John Lafferty
We study the problem of testing for community structure in networks using relations between the observed frequencies of small subgraphs.
Methodology Social and Information Networks Statistics Theory Applications Statistics Theory
no code implementations • 21 Feb 2017 • Chao Gao, Dan Garber, Nathan Srebro, Jialei Wang, Weiran Wang
We study the sample complexity of canonical correlation analysis (CCA), \ie, the number of samples needed to estimate the population canonical correlation and directions up to arbitrarily small error.
no code implementations • 15 Feb 2017 • Chao Gao
This paper studies robust regression in the settings of Huber's $\epsilon$-contamination models.
no code implementations • 24 Jul 2016 • Chao Gao, Zongming Ma, Anderson Y. Zhang, Harrison H. Zhou
Community detection is a central problem of network data analysis.
no code implementations • 25 May 2016 • Chao Gao, Yu Lu, Dengyong Zhou
In many machine learning applications, crowdsourcing has become the primary means for label collection.
no code implementations • 1 Dec 2015 • Chao Gao, Yu Lu, Zongming Ma, Harrison H. Zhou
Biclustering structures in data matrices were first formalized in a seminal paper by John Hartigan (1972) where one seeks to cluster cases and variables simultaneously.
no code implementations • 14 May 2015 • Chao Gao, Zongming Ma, Anderson Y. Zhang, Harrison H. Zhou
Community detection is a fundamental statistical problem in network data analysis.
no code implementations • 24 Nov 2013 • Mengjie Chen, Chao GAO, Zhao Ren, Harrison H. Zhou
Sparse Canonical Correlation Analysis (CCA) has received considerable attention in high-dimensional data analysis to study the relationship between two sets of random variables.
no code implementations • 22 Oct 2013 • Chao Gao, Dengyong Zhou
Crowdsourcing has become a primary means for label collection in many real-world machine learning applications.
no code implementations • 31 Jul 2013 • Mengjie Chen, Chao GAO, Hongyu Zhao
The Indian buffet process (IBP) is such an example that can be used to define a prior distribution on infinite binary features, where the exchangeability among subjects is assumed.