no code implementations • 22 Mar 2024 • Kun Sun, Rong Wang, Haitao Liu, Anders Søgaard
Evaluations have revealed that factors such as scaling, training types, architectures and other factors profoundly impact the performance of LLMs.
no code implementations • 6 Nov 2023 • Huifa Li, Jie Fu, Zhili Chen, Xiaomin Yang, Haitao Liu, XinPeng Ling
Recently, deep learning has facilitated the analysis of high-dimensional single-cell data.
no code implementations • 21 Aug 2023 • XinPeng Ling, Jie Fu, Kuncan Wang, Haitao Liu, Zhili Chen
Federated Learning (FL) is a distributed machine learning technique that allows model training among multiple devices or organizations by sharing training parameters instead of raw data.
no code implementations • 24 Aug 2022 • Yugeng Huang, Haitao Liu, Tian Huang
We also provide a novel strategy for determining the kernel width which ensures that our method can efficiently exploit information redundancy supplied by relative motions in the presence of many outliers.
no code implementations • 25 Feb 2022 • Haitao Liu, Kai Wu, Yew-Soon Ong, Chao Bian, Xiaomo Jiang, Xiaofang Wang
Multi-task Gaussian process (MTGP) is a well-known non-parametric Bayesian model for learning correlated tasks effectively by transferring knowledge across tasks.
no code implementations • 20 Sep 2021 • Haitao Liu, Jiaqi Ding, Xinyu Xie, Xiaomo Jiang, Yusong Zhao, Xiaofang Wang
Multi-task regression attempts to exploit the task similarity in order to achieve knowledge transfer across related tasks for performance improvement.
no code implementations • 3 Jun 2021 • Haitao Liu, Changjun Liu, Xiaomo Jiang, Xudong Chen, Shuhua Yang, Xiaofang Wang
Thereafter, we first investigate the methodological characteristics of the proposed deep probabilistic sequence model on toy cases, and then comprehensively demonstrate the superiority of our model against existing deep probabilistic SSM models through extensive numerical experiments on eight system identification benchmarks from various dynamic systems.
no code implementations • 1 Dec 2020 • Shuiyuan Yu, Chunshan Xu, Haitao Liu
Traditional linguistic theories have largely regard language as a formal system composed of rigid rules.
1 code implementation • 29 Aug 2020 • Haitao Liu, Yew-Soon Ong, Xiaomo Jiang, Xiaofang Wang
For a learning task, Gaussian process (GP) is interested in learning the statistical relationship between inputs and outputs, since it offers not only the prediction mean but also the associated variability.
1 code implementation • 18 May 2020 • Haitao Liu, Yew-Soon Ong, Xiaomo Jiang, Xiaofang Wang
Deep kernel learning (DKL) leverages the connection between Gaussian process (GP) and neural networks (NN) to build an end-to-end, hybrid model.
1 code implementation • 14 Sep 2019 • Haitao Liu, Yew-Soon Ong, Ziwei Yu, Jianfei Cai, Xiaobo Shen
Gaussian process classification (GPC) provides a flexible and powerful statistical framework describing joint distributions over function space.
1 code implementation • 10 Nov 2018 • Haitao Liu, Randy C. Paffenroth, Jian Zou, Chong Zhou
Accordingly, we propose a novel optimization problem that is similar in spirit to Robust Principal Component Analysis (RPCA) and splits the sample covariance matrix $M$ into two parts, $M=F+S$, where $F$ is the cleaned sample covariance whose inverse is sparse and computable by Graphical Lasso, and $S$ contains the outliers in $M$.
no code implementations • 3 Nov 2018 • Haitao Liu, Jianfei Cai, Yew-Soon Ong, Yi Wang
This paper devotes to investigating the methodological characteristics and performance of representative global and local scalable GPs including sparse approximations and local aggregations from four main perspectives: scalability, capability, controllability and robustness.
no code implementations • 3 Nov 2018 • Haitao Liu, Yew-Soon Ong, Jianfei Cai
To improve the scalability, we first develop a variational sparse inference algorithm, named VSHGP, to handle large-scale datasets.
no code implementations • 5 Jul 2018 • Shuiyuan Yu, Chunshan Xu, Haitao Liu
A computer simulation based on the dual-process theory yields Zipf's law with the same structural pattern, suggesting that Zipf's law of natural languages are motivated by common cognitive mechanisms.
no code implementations • 3 Jul 2018 • Haitao Liu, Yew-Soon Ong, Xiaobo Shen, Jianfei Cai
The review of scalable GPs in the GP community is timely and important due to the explosion of data size.
1 code implementation • ICML 2018 • Haitao Liu, Jianfei Cai, Yi Wang, Yew-Soon Ong
In order to scale standard Gaussian process (GP) regression to large-scale datasets, aggregation models employ factorized training process and then combine predictions from distributed experts.
no code implementations • 24 Sep 2016 • Shuiyuan Yu, Junying Liang, Haitao Liu
The power law is ubiquitous in natural and social phenomena, and is considered as a universal relationship between the frequency and its rank for diverse social systems.
no code implementations • 24 Sep 2016 • Shuiyuan Yu, Jin Cong, Junying Liang, Haitao Liu
Sentence is a basic linguistic unit, however, little is known about how information content is distributed across different positions of a sentence.
no code implementations • 15 Sep 2015 • Haitao Liu, Chunshan Xu, Junying Liang
In the recent issue of PNAS, Futrell et al. claims that their study of 37 languages gives the first large scale cross-language evidence for Dependency Length Minimization, which is an overstatement that ignores similar previous researches.
no code implementations • 3 Sep 2015 • Qian Lu, Chunshan Xu, Haitao Liu
These results suggest that chunking may play a vital role in the minimization of dependency distance, and a somewhat contributing role in the rarity of dependency crossing.
no code implementations • 13 Apr 2013 • Ramon Ferrer-i-Cancho, Haitao Liu
However, the empirical distribution of dependency lengths of sentences of the same length differs from that of sentences of varying length and the distribution of dependency lengths depends on sentence length for real sentences and also under the null hypothesis that dependencies connect vertices located in random positions of the sequence.