Bandit Algorithms

Classic Linear Bandits

• Improved algorithms for linear stochastic bandits (2011)

• Thompson sampling for contextual bandits with linear payoffs (2013) 

• Linear Thompson sampling revisited (2016)

Upper Confidence Bounds

• Fixed size confidence ellipsoids for linear regression parameters (1966) 

• Using upper confidence bounds for online learning (2000)

• Using confidence bounds for exploitation-exploration trade-offs (2002) 

LASSO Bandits

• Online decision making with high-dimensional covariates (2020) 

Neural Bandits

• Stochastic Bandits with ReLU Neural Networks (2024)