Search Results for author: Aonan Zhang

Found 13 papers, 4 papers with code

Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training

1 code implementation23 May 2024 Xianzhi Du, Tom Gunter, Xiang Kong, Mark Lee, ZiRui Wang, Aonan Zhang, Nan Du, Ruoming Pang

In this work, we revisit the settings by adopting step time as a more accurate measure of model complexity, and by determining the total compute budget under the Chinchilla compute-optimal settings.

GSM8K

Recurrent Drafter for Fast Speculative Decoding in Large Language Models

1 code implementation14 Mar 2024 Aonan Zhang, Chong Wang, Yi Wang, Xuanyu Zhang, Yunfei Cheng

In this paper, we introduce an improved approach of speculative decoding aimed at enhancing the efficiency of serving large language models.

Divide-or-Conquer? Which Part Should You Distill Your LLM?

no code implementations22 Feb 2024 Zhuofeng Wu, He Bai, Aonan Zhang, Jiatao Gu, VG Vinod Vydiswaran, Navdeep Jaitly, Yizhe Zhang

Recent methods have demonstrated that Large Language Models (LLMs) can solve reasoning tasks better when they are encouraged to solve subtasks of the main task first.

Problem Decomposition

Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems

no code implementations25 May 2023 Xiaohui Chen, Jiankai Sun, Taiqing Wang, Ruocheng Guo, Li-Ping Liu, Aonan Zhang

Most subsampling methods are model-based and often require a pre-trained pilot model to measure data importance via e. g. sample hardness.

Recommendation Systems

NVDiff: Graph Generation through the Diffusion of Node Vectors

no code implementations19 Nov 2022 Xiaohui Chen, Yukun Li, Aonan Zhang, Li-Ping Liu

Learning to generate graphs is challenging as a graph is a set of pairwise connected, unordered nodes encoding complex combinatorial structures.

Graph Generation

Collaborative Anomaly Detection

no code implementations20 Sep 2022 Ke Bai, Aonan Zhang, Zhizhong Li, Ricardo Heano, Chong Wang, Lawrence Carin

In recommendation systems, items are likely to be exposed to various users and we would like to learn about the familiarity of a new user with an existing item.

Anomaly Detection Density Estimation +1

Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data

no code implementations NeurIPS 2021 Haiying Wang, Aonan Zhang, Chong Wang

We first prove that, with imbalanced data, the available information about unknown parameters is only tied to the relatively small number of positive instances, which justifies the usage of negative sampling.

Vertical Federated Learning without Revealing Intersection Membership

no code implementations10 Jun 2021 Jiankai Sun, Xin Yang, Yuanshun Yao, Aonan Zhang, Weihao Gao, Junyuan Xie, Chong Wang

In this paper, we propose a vFL framework based on Private Set Union (PSU) that allows each party to keep sensitive membership information to itself.

Vertical Federated Learning

Random Function Priors for Correlation Modeling

1 code implementation9 May 2019 Aonan Zhang, John Paisley

The likelihood model of high dimensional data $X_n$ can often be expressed as $p(X_n|Z_n,\theta)$, where $\theta\mathrel{\mathop:}=(\theta_k)_{k\in[K]}$ is a collection of hidden features shared across objects, indexed by $n$, and $Z_n$ is a non-negative factor loading vector with $K$ entries where $Z_{nk}$ indicates the strength of $\theta_k$ used to express $X_n$.

Variational Inference

Fully Supervised Speaker Diarization

1 code implementation10 Oct 2018 Aonan Zhang, Quan Wang, Zhenyao Zhu, John Paisley, Chong Wang

In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN).

Clustering speaker-diarization +1

Deep Bayesian Nonparametric Tracking

no code implementations ICML 2018 Aonan Zhang, John Paisley

Time-series data often exhibit irregular behavior, making them hard to analyze and explain with a simple dynamic model.

Time Series Time Series Analysis

Stochastic Annealing for Variational Inference

no code implementations25 May 2015 San Gultekin, Aonan Zhang, John Paisley

We empirically evaluate a stochastic annealing strategy for Bayesian posterior optimization with variational inference.

Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.