160 citations · 1.5k across the 122 of their papers we have counts for
6 papers · 2 filters
Randomized Exploration for Non-Stationary Stochastic Linear Bandits
Baekjin Kim, Ambuj Tewari
We investigate two perturbation approaches to overcome conservatism that optimism based algorithms chronically suffer from in practice. The first approach replaces optimism with a…
Not All are Made Equal: Consistency of Weighted Averaging Estimators Under Active Learning
Jack Goetz, Ambuj Tewari
Active learning seeks to build the best possible model with a budget of labelled data by sequentially selecting the next point to label. However the training set is no longer \text…
Online Boosting for Multilabel Ranking with Top-k Feedback
Vinod Raman, Daniel T. Zhang, Young Hun Jung +1
We present online boosting algorithms for multilabel ranking with top-k feedback, where the learner only receives information about the top k items from the ranking it provides. We…
What You See May Not Be What You Get: UCB Bandit Algorithms Robust to ε-Contamination
Laura Niss, Ambuj Tewari
Motivated by applications of bandit algorithms in education, we consider a stochastic multi-armed bandit problem with -contaminated rewards. We allow an adversary to g…
Regret Analysis of Bandit Problems with Causal Background Knowledge
Yangyi Lu, Amirhossein Meisami, Ambuj Tewari +1
We study how to learn optimal interventions sequentially given causal information represented as a causal graph along with associated conditional distributions. Causal modeling is…
On the Optimality of Perturbations in Stochastic and Adversarial Multi-armed Bandit Problems
Baekjin Kim, Ambuj Tewari
We investigate the optimality of perturbation based algorithms in the stochastic and adversarial multi-armed bandit problems. For the stochastic case, we provide a unified regret a…