6 papers
Bellman-Centric Learning: Near-Optimal Regret for Linear Bandits with Memory
Jingyuan Liu, Huiwen Jia
We study linear bandits with memory, where past actions induce endogenous nonstationarity through an arbitrary known, bounded matrix-valued memory map. To trade off exploration and…
Consideration Circuits: Depth Separation and Universality Beyond a Single Softmax
Junjie Xiao, Huiwen Jia
Most feature-based choice models, classical and deep, score items and apply a single softmax. We introduce consideration circuits (CC), feature-based models of multi-stage choice d…
Ideal Paths for Approximating Logistic Gradient Descent Trajectories at Large Initialization
Junjie Xiao, Huiwen Jia
Modern training on a new task often starts from a previously trained model rather than from scratch, raising the question of how this initialization affects the subsequent training…
Multi-User Contextual Cascading Bandits for Personalized Recommendation
Jiho Park, Huiwen Jia
We introduce a Multi-User Contextual Cascading Bandit model, a new combinatorial bandit framework that captures realistic online advertising scenarios where multiple users interact…
Decentralized Contextual Bandits with Network Adaptivity
Chuyun Deng, Huiwen Jia
We consider contextual linear bandits over networks, a class of sequential decision-making problems where learning occurs simultaneously across multiple locations and the reward di…
Decision-Dependent Distributionally Robust Optimization with Application to Dynamic Pricing
Chengrui Qu, Huiwen Jia, Pengcheng You
We consider decision-making problems under decision-dependent uncertainty (DDU), where the distribution of uncertain parameters depends on the decision variables and is only observ…