1 code implementation • 4 Apr 2024 • Harmon Bhasin, Timothy Ossowski, Yiqiao Zhong, Junjie Hu
Large language models (LLM) have recently shown the extraordinary ability to perform unseen tasks based on few-shot examples provided as text, also known as in-context learning (ICL).
1 code implementation • 7 Oct 2023 • Jiajun Song, Yiqiao Zhong
Given embedding vector $\boldsymbol{h}_{c, t} \in \mathbb{R}^d$ at sequence position $t \le T$ in a sequence (or context) $c \le C$, extracting the mean effects yields the decomposition \[ \boldsymbol{h}_{c, t} = \boldsymbol{\mu} + \mathbf{pos}_t + \mathbf{ctx}_c + \mathbf{resid}_{c, t} \] where $\boldsymbol{\mu}$ is the global mean vector, $\mathbf{pos}_t$ and $\mathbf{ctx}_c$ are the mean vectors across contexts and across positions respectively, and $\mathbf{resid}_{c, t}$ is the residual vector.
no code implementations • 6 Jun 2023 • Yu Gui, Cong Ma, Yiqiao Zhong
Firstly, through empirical and theoretical analysis, we identify two crucial effects -- expansion and shrinkage -- induced by the contrastive loss on the projectors.
no code implementations • 28 Oct 2021 • Andrea Montanari, Yiqiao Zhong, Kangjie Zhou
In the negative perceptron problem we are given $n$ data points $({\boldsymbol x}_i, y_i)$, where ${\boldsymbol x}_i$ is a $d$-dimensional vector and $y_i\in\{+1,-1\}$ is a binary label.
no code implementations • 25 Jul 2020 • Andrea Montanari, Yiqiao Zhong
We assume that both the sample size $n$ and the dimension $d$ are large, and they are polynomially related.
no code implementations • 10 Apr 2019 • Jianqing Fan, Cong Ma, Yiqiao Zhong
Deep learning has arguably achieved tremendous success in recent years.
no code implementations • 12 Aug 2018 • Jianqing Fan, Kaizheng Wang, Yiqiao Zhong, Ziwei Zhu
Factor models are a class of powerful statistical models that have been widely used to deal with dependent measurements that arise frequently from various applications from genomics and neuroscience to economics and finance.
no code implementations • 6 Jan 2014 • Chi Jin, Ziteng Wang, Junliang Huang, Yiqiao Zhong, Li-Wei Wang
We develop an $\epsilon$-differentially private mechanism for the class of $K$-smooth queries.