6 papers
Displaced tracks as a signal of dark matter co-annihilation: a case study using inert doublet model at collider
Hrishikesh Deka, Subhaditya Bhattacharya, Amir Subba +1
Dark sector containing heavy (charged) particles with small mass splitting with dark matter (DM) can co-annihilate and produce correct relic density, evading direct detection bound…
Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation
Hao Qin, Chicheng Zhang
We study the contextual combinatorial semi-bandit (CCSB) problem with general reward function approximation. At each round, the learner observes a context, selects a combinatorial…
Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits
Hao Qin, Chicheng Zhang
We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that efficiently reduces contextual bandit learning with general reward function approximation to offli…
Physics-Informed Parametric Bandits for Beam Alignment in mmWave Communications
Hao Qin, Thang Duong, Ming F. Li +1
In millimeter wave (mmWave) communications, beam alignment and tracking are crucial to combat the significant path loss. As scanning the entire directional space is inefficient, de…
Achieving adaptivity and optimality for multi-armed bandits using Exponential-Kullback Leibler Maillard Sampling
Hao Qin, Kwang-Sung Jun, Chicheng Zhang
We study the problem of -armed bandits with reward distributions belonging to a one-parameter exponential distribution family. In the literature, several criteria have been prop…
Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
Hao Qin, Kwang-Sung Jun, Chicheng Zhang
We study -armed bandit problems where the reward distributions of the arms are all supported on the interval. It has been a challenge to design regret-efficient randomiz…