885 citations · 983 across the 9 of their papers we have counts for
14 papers
Looped Transformers for Length Generalization
Ying Fan, Yilun Du, Kannan Ramchandran +1
Recent work has shown that Transformers trained from scratch can successfully solve various arithmetic and algorithmic tasks, such as adding numbers and computing parity. While the…
Equal Improvability: A New Fairness Notion Considering the Long-term Impact
Ozgur Guldogan, Yuchen Zeng, Jy-yong Sohn +2
Devising a fair classifier that does not discriminate against different groups is an important problem in machine learning. Although researchers have proposed various ways of defin…
Hypergraph Spectral Clustering in the Weighted Stochastic Block Model
Kwangjun Ahn, Kangwook Lee, Changho Suh
Spectral clustering is a celebrated algorithm that partitions objects based on pairwise similarity information. While this approach has been successfully applied to a variety of do…
Hierarchical Coding for Distributed Computing
Hyegyeong Park, Kangwook Lee, Jy-yong Sohn +2
Coding for distributed computing supports low-latency computation by relieving the burden of straggling workers. While most existing works assume a simple master-worker model, we c…
Simulating outcomes of interventions using a multipurpose simulation program based on the Evolutionary Causal Matrices and Markov Chain
Hyemin Han, Kangwook Lee, Firat Soylu
Predicting long-term outcomes of interventions is necessary for educational and social policy-making processes that might widely influence our society for the long-term. However, p…
Community Recovery in Hypergraphs
Kwangjun Ahn, Kangwook Lee, Changho Suh
Community recovery is a central problem that arises in a wide variety of applications such as network clustering, motion segmentation, face clustering and protein complex detection…
Predicting Long-term Outcomes of Educational Interventions Using the Evolutionary Causal Matrices and Markov Chain Based on Educational Neuroscience
Hyemin Han, Kangwook Lee, Firat Soylu
We developed a prediction model based on the evolutionary causal matrices (ECM) and the Markov Chain to predict long-term influences of educational interventions on adolescents dev…
Fast and Robust Compressive Phase Retrieval with Sparse-Graph Codes
Dong Yin, Kangwook Lee, Ramtin Pedarsani +1
In this paper, we tackle the compressive phase retrieval problem in the presence of noise. The noisy compressive phase retrieval problem is to recover a -sparse complex signal $…
Speeding Up Distributed Machine Learning Using Codes
Kangwook Lee, Maximilian Lam, Ramtin Pedarsani +2
Codes are widely used in many engineering applications to offer robustness against noise. In large-scale systems there are several types of noise that can affect the performance of…
SAFFRON: A Fast, Efficient, and Robust Framework for Group Testing based on Sparse-Graph Codes
Kangwook Lee, Ramtin Pedarsani, Kannan Ramchandran
Group testing tackles the problem of identifying a population of defective items from a set of items by pooling groups of items efficiently in order to cut down the number…
Capacity-Approaching PhaseCode for Low-Complexity Compressive Phase Retrieval
Ramtin Pedarsani, Kangwook Lee, Kannan Ramchandran
In this paper, we tackle the general compressive phase retrieval problem. The problem is to recover a K-sparse complex vector of length n, , from the magnitudes…
PhaseCode: Fast and Efficient Compressive Phase Retrieval based on Sparse-Graph-Codes
Ramtin Pedarsani, Dong Yin, Kangwook Lee +1
We consider the problem of recovering a -sparse complex signal from intensity measurements. We propose the PhaseCode algorithm, and show that in the noiseless case, Phas…
When Do Redundant Requests Reduce Latency ?
Nihar B. Shah, Kangwook Lee, Kannan Ramchandran
Several systems possess the flexibility to serve requests in more than one way. For instance, a distributed storage system storing multiple replicas of the data can serve a request…
The MDS Queue: Analysing the Latency Performance of Erasure Codes
Nihar B. Shah, Kangwook Lee, Kannan Ramchandran
In order to scale economically, data centers are increasingly evolving their data storage methods from the use of simple data replication to the use of more powerful erasure codes,…