no code implementations • 17 Feb 2024 • Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun
Assuming access to the distribution of the covariates, we propose a novel low-rank matrix estimation method called LowPopArt and provide its recovery guarantee that depends on a novel quantity denoted by B(Q) that characterizes the hardness of the problem, where Q is the covariance matrix of the measurement distribution.
no code implementations • 14 Feb 2024 • Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona
In this paper, we consider the problem of proving concentration inequalities to estimate the mean of the sequence.
no code implementations • 12 Feb 2024 • Kwang-Sung Jun, Jungtaek Kim
First, we propose a novel confidence set that is `semi-adaptive' to the unknown sub-Gaussian parameter $\sigma_*^2$ in the sense that the (normalized) confidence width scales with $\sqrt{d\sigma_*^2 + \sigma_0^2}$ where $d$ is the dimension and $\sigma_0^2$ is the specified sub-Gaussian parameter (known) that can be much larger than $\sigma_*^2$.
1 code implementation • 17 Nov 2023 • Alvin Chiu, Mithun Ghosh, Reyan Ahmed, Kwang-Sung Jun, Stephen Kobourov, Michael T. Goodrich
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 Problem.
2 code implementations • 28 Oct 2023 • Junghyun Lee, Se-Young Yun, Kwang-Sung Jun
Logistic bandit is a ubiquitous framework of modeling users' choices, e. g., click vs. no click for advertisement recommender system.
1 code implementation • 30 Apr 2023 • Reyan Ahmed, Mithun Ghosh, Kwang-Sung Jun, Stephen Kobourov
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.
1 code implementation • NeurIPS 2023 • Hao Qin, Kwang-Sung Jun, Chicheng Zhang
Maillard sampling \cite{maillard13apprentissage}, an attractive alternative to Thompson sampling, has recently been shown to achieve competitive regret guarantees in the sub-Gaussian reward setting \cite{bian2022maillard} while maintaining closed-form action probabilities, which is useful for offline policy evaluation.
no code implementations • 12 Feb 2023 • Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona
We consider the problem of estimating the mean of a sequence of random elements $f(X_1, \theta)$ $, \ldots, $ $f(X_n, \theta)$ where $f$ is a fixed scalar function, $S=(X_1, \ldots, X_n)$ are independent random variables, and $\theta$ is a possibly $S$-dependent parameter.
no code implementations • 30 Oct 2022 • Yao Zhao, Connor James Stephens, Csaba Szepesvári, Kwang-Sung Jun
Simple regret is a natural and parameter-free performance criterion for pure exploration in multi-armed bandits yet is less popular than the probability of missing the best arm or an $\epsilon$-good arm, perhaps due to lack of easy ways to characterize it.
1 code implementation • 25 Oct 2022 • Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun
In this paper, we propose a simple and computationally efficient sparse linear estimation method called PopArt that enjoys a tighter $\ell_1$ recovery guarantee compared to Lasso (Tibshirani, 1996) in many problems.
no code implementations • 3 May 2022 • Spencer, Gales, Sunder Sethuraman, Kwang-Sung Jun
For the latter, we do not pay any price in the regret for now knowing $S$.
no code implementations • 4 Feb 2022 • Blake Mason, Kwang-Sung Jun, Lalit Jain
Finally, we discuss the impact of the bias of the MLE on the logistic bandit problem, providing an example where $d^2$ lower order regret (cf., it is $d$ for linear bandits) may not be improved as long as the MLE is used and how bias-corrected estimators may be used to make it closer to $d$.
2 code implementations • 6 Jan 2022 • Louis Faury, Marc Abeille, Kwang-Sung Jun, Clément Calauzènes
Logistic Bandits have recently undergone careful scrutiny by virtue of their combined theoretical and practical relevance.
no code implementations • 5 Nov 2021 • Jie Bian, Kwang-Sung Jun
This less-known algorithm, which we call Maillard sampling (MS), computes the probability of choosing each arm in a \textit{closed form}, which is not true for Thompson sampling, a widely-adopted bandit algorithm in the industry.
no code implementations • 5 Nov 2021 • Yeoneung Kim, Insoon Yang, Kwang-Sung Jun
For linear bandits, we achieve $\tilde O(\min\{d\sqrt{K}, d^{1. 5}\sqrt{\sum_{k=1}^K \sigma_k^2}\} + d^2)$ where $d$ is the dimension of the features, $K$ is the time horizon, and $\sigma_k^2$ is the noise variance at time step $k$, and $\tilde O$ ignores polylogarithmic dependence, which is a factor of $d^3$ improvement.
1 code implementation • 27 Oct 2021 • Francesco Orabona, Kwang-Sung Jun
A classic problem in statistics is the estimation of the expectation of random variables from samples.
no code implementations • 4 Feb 2021 • Hyejin Park, Seiyun Shin, Kwang-Sung Jun, Jungseul Ok
To cope with the latent structural parameter, we consider a transfer learning setting in which an agent must learn to transfer the structural information from the prior tasks to the next task, which is inspired by practical problems such as rate adaptation in wireless link.
no code implementations • 1 Jan 2021 • Soyoung Kang, Ganghyeon Park, Kwang-Sung Jun, Noseong Park
Because it is not the case that every input requires the advanced integrator, we design an auxiliary neural network to choose an appropriate integrator given input to decrease the overall inference time without significantly sacrificing accuracy.
no code implementations • 23 Nov 2020 • Kwang-Sung Jun, Lalit Jain, Blake Mason, Houssam Nassif
Specifically, our confidence bound avoids a direct dependence on $1/\kappa$, where $\kappa$ is the minimal variance over all arms' reward distributions.
no code implementations • NeurIPS 2020 • Kwang-Sung Jun, Chicheng Zhang
In this paper, we focus on the finite hypothesis case and ask if one can achieve the asymptotic optimality while enjoying bounded regret whenever possible.
no code implementations • 21 Nov 2019 • Kwang-Sung Jun, Francesco Orabona
We consider the problem of minimizing a convex risk with stochastic subgradients guaranteeing $\epsilon$-locally differentially private ($\epsilon$-LDP).
no code implementations • NeurIPS 2019 • Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona
In this paper, we consider the nonparametric least square regression in a Reproducing Kernel Hilbert Space (RKHS).
no code implementations • 5 Feb 2019 • Kwang-Sung Jun, Francesco Orabona
We show that BANCO achieves the optimal regret rate in our problem.
no code implementations • 8 Jan 2019 • Kwang-Sung Jun, Rebecca Willett, Stephen Wright, Robert Nowak
We introduce the bilinear bandit problem with low-rank structure in which an action takes the form of a pair of arms from two different entity types, and the reward is a bilinear function of the known feature vectors of the arms.
no code implementations • NeurIPS 2018 • Kwang-Sung Jun, Lihong Li, Yuzhe ma, Xiaojin Zhu
We study adversarial attacks that manipulate the reward signals to control the actions chosen by a stochastic multi-armed bandit algorithm.
no code implementations • 17 Aug 2018 • Yuzhe Ma, Kwang-Sung Jun, Lihong Li, Xiaojin Zhu
We provide a general attack framework based on convex optimization and show that by slightly manipulating rewards in the data, an attacker can force the bandit algorithm to pull a target arm for a target contextual vector.
no code implementations • 6 Nov 2017 • Kwang-Sung Jun, Francesco Orabona, Stephen Wright, Rebecca Willett
A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments.
no code implementations • NeurIPS 2017 • Kwang-Sung Jun, Aniruddha Bhargava, Robert Nowak, Rebecca Willett
Second, for the case where the number $N$ of arms is very large, we propose new algorithms in which each next arm is selected via an inner product search.
no code implementations • 14 Oct 2016 • Kwang-Sung Jun, Francesco Orabona, Rebecca Willett, Stephen Wright
This paper describes a new parameter-free online learning algorithm for changing environments.
no code implementations • 3 Sep 2016 • 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.
no code implementations • NeurIPS 2015 • Kwang-Sung Jun, Jerry Zhu, Timothy T. Rogers, Zhuoran Yang, Ming Yuan
In this paper, we propose the first efficient maximum likelihood estimate (MLE) for INVITE by decomposing the censored output into a series of absorbing random walks.