115 citations · 117 across the 6 of their papers we have counts for
8 papers
The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits
Sepehr Assadi, Chen Wang
We give a near-optimal sample-pass trade-off for pure exploration in multi-armed bandits (MABs) via multi-pass streaming algorithms: any streaming algorithm with sublinear memory t…
Evaluating Stability in Massive Social Networks: Efficient Streaming Algorithms for Structural Balance
Vikrant Ashvinkumar, Sepehr Assadi, Chengyuan Deng +2
Structural balance theory studies stability in networks. Given a -vertex complete graph whose edges are labeled positive or negative, the graph is considered \emph{bal…
Differentially Private Range Query on Shortest Paths
Chengyuan Deng, Jie Gao, Jalaj Upadhyay +1
We consider differentially private range queries on a graph where query ranges are defined as the set of edges on a shortest path of the graph. Edges in the graph carry sensitive a…
Sublinear Time and Space Algorithms for Correlation Clustering via Sparse-Dense Decompositions
Sepehr Assadi, Chen Wang
We present a new approach for solving (minimum disagreement) correlation clustering that results in sublinear algorithms with highly efficient time and space complexity for this pr…
On the Global Self-attention Mechanism for Graph Convolutional Networks
Chen Wang, Chengyuan Deng
Applying Global Self-attention (GSA) mechanism over features has achieved remarkable success on Convolutional Neural Networks (CNNs). However, it is not clear if Graph Convolutiona…
Supervised Contrastive Learning
Prannay Khosla, Piotr Teterwak, Chen Wang +6
Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training…
Exploration with Limited Memory: Streaming Algorithms for Coin Tossing, Noisy Comparisons, and Multi-Armed Bandits
Sepehr Assadi, Chen Wang
Consider the following abstract coin tossing problem: Given a set of coins with unknown biases, find the most biased coin using a minimal number of coin tosses. This is a commo…
SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations
Chen Wang, Chengyuan Deng, Vladimir Ivanov
Variational Autoencoders (VAEs) are powerful in data representation inference, but it cannot learn relations between features with its vanilla form and common variations. The abili…