activity
20162024
most citedGraph-Based Active Learning: A New Look at Expected Error Minimization

8 citations · 11 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2024

Better-than-KL PAC-Bayes Bounds

Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu +2

Let be a sequence of random elements, where is a fixed scalar function, are independent random variables (data), and i…

cs.LG2023

Graph Sparsifications using Neural Network Assisted Monte Carlo Tree Search

Alvin Chiu, Mithun Ghosh, Reyan Ahmed +3

Graph neural networks have been successful for machine learning, as well as for combinatorial and graph problems such as the Subgraph Isomorphism Problem and the Traveling Salesman…

cs.LG20231 cited

Nearly Optimal Steiner Trees using Graph Neural Network Assisted Monte Carlo Tree Search

Reyan Ahmed, Mithun Ghosh, Kwang-Sung Jun +1

Graph neural networks are useful for learning problems, as well as for combinatorial and graph problems such as the Subgraph Isomorphism Problem and the Traveling Salesman Problem.…

cs.LG20232 cited

Tighter PAC-Bayes Bounds Through Coin-Betting

Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij +1

We consider the problem of estimating the mean of a sequence of random elements where is a fixed scalar function, ar…

stat.ML2022

Norm-Agnostic Linear Bandits

Spencer, Gales, Sunder Sethuraman +1

Linear bandits have a wide variety of applications including recommendation systems yet they make one strong assumption: the algorithms must know an upper bound on the norm of…

stat.ML20168 cited

Graph-Based Active Learning: A New Look at Expected Error Minimization

Kwang-Sung Jun, Robert Nowak

In graph-based active learning, algorithms based on expected error minimization (EEM) have been popular and yield good empirical performance. The exact computation of EEM optimally…