30 citations · 123 across the 18 of their papers we have counts for
18 papers
Learning Optimal Deterministic Auctions with Correlated Valuation Distributions
Da Huo, Zhilin Zhang, Zhenzhe Zheng +3
In mechanism design, it is challenging to design the optimal auction with correlated values in general settings. Although value distribution can be further exploited to improve rev…
Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning
Chengfei Lv, Chaoyue Niu, Renjie Gu +17
To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system,…
On-Device Learning with Cloud-Coordinated Data Augmentation for Extreme Model Personalization in Recommender Systems
Renjie Gu, Chaoyue Niu, Yikai Yan +5
Data heterogeneity is an intrinsic property of recommender systems, making models trained over the global data on the cloud, which is the mainstream in industry, non-optimal to eac…
On Designing a Two-stage Auction for Online Advertising
Yiqing Wang, Xiangyu Liu, Zhenzhe Zheng +4
For the scalability of industrial online advertising systems, a two-stage auction architecture is widely used to enable efficient ad allocation on a large set of corpus within a li…
Normal Learning in Videos with Attention Prototype Network
Chao Hu, Fan Wu, Weijie Wu +2
Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection. With models trained on the normal data, the reconstructio…
Nearly Minimax-Optimal Rates for Noisy Sparse Phase Retrieval via Early-Stopped Mirror Descent
Fan Wu, Patrick Rebeschini
This paper studies early-stopped mirror descent applied to noisy sparse phase retrieval, which is the problem of recovering a -sparse signal fr…
Implicit Regularization in Matrix Sensing via Mirror Descent
Fan Wu, Patrick Rebeschini
We study discrete-time mirror descent applied to the unregularized empirical risk in matrix sensing. In both the general case of rectangular matrices and the particular case of pos…
A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval
Fan Wu, Patrick Rebeschini
We analyze continuous-time mirror descent applied to sparse phase retrieval, which is the problem of recovering sparse signals from a set of magnitude-only measurements. We apply m…
Retrieve Synonymous keywords for Frequent Queries in Sponsored Search in a Data Augmentation Way
Yijiang Lian, Zhenjun You, Fan Wu +2
In sponsored search, retrieving synonymous keywords is of great importance for accurately targeted advertising. The semantic gap between queries and keywords and the extremely high…
Hadamard Wirtinger Flow for Sparse Phase Retrieval
Fan Wu, Patrick Rebeschini
We consider the problem of reconstructing an -dimensional -sparse signal from a set of noiseless magnitude-only measurements. Formulating the problem as an unregularized empi…
Secure Federated Submodel Learning
Chaoyue Niu, Fan Wu, Shaojie Tang +5
Federated learning was proposed with an intriguing vision of achieving collaborative machine learning among numerous clients without uploading their private data to a cloud server.…
Accurate Protein Structure Prediction by Embeddings and Deep Learning Representations
Iddo Drori, Darshan Thaker, Arjun Srivatsa +15
Proteins are the major building blocks of life, and actuators of almost all chemical and biophysical events in living organisms. Their native structures in turn enable their biolog…
Visual Natural Language Query Auto-Completion for Estimating Instance Probabilities
Samuel Sharpe, Jin Yan, Fan Wu +1
We present a new task of query auto-completion for estimating instance probabilities. We complete a user query prefix conditioned upon an image. Given the complete query, we fine t…
DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image
Pengfei Yao, Zheng Fang, Fan Wu +2
Recovering 3D human body shape and pose from 2D images is a challenging task due to high complexity and flexibility of human body, and relatively less 3D labeled data. Previous met…
Global Semantic Consistency for Zero-Shot Learning
Fan Wu, Kai Tian, Jihong Guan +1
In image recognition, there are many cases where training samples cannot cover all target classes. Zero-shot learning (ZSL) utilizes the class semantic information to classify samp…
An End-to-End Approach to Natural Language Object Retrieval via Context-Aware Deep Reinforcement Learning
Fan Wu, Zhongwen Xu, Yi Yang
We propose an end-to-end approach to the natural language object retrieval task, which localizes an object within an image according to a natural language description, i.e., referr…
Flip-Rotate-Pooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification
Fa Wu, Peijun Hu, Dexing Kong
This paper presents a new version of Dropout called Split Dropout (sDropout) and rotational convolution techniques to improve CNNs' performance on image classification. The widely…
PRINCE: Privacy-Preserving Mechanisms for Influence Diffusion in Online Social Networks
Ruihao Zhu, Dongxin Liu, Fan Wu +1
This paper has been withdrawn by the author due to a crucial sign error in equation 1. With the advance of online social networks, there has been extensive research on how to sprea…