13 papers
Learning While Scheduling Jobs under Context-Dependent Service Rates: An Anytime Rate-Optimal Algorithm
Seoungbin Bae, Dabeen Lee
We study contextual queueing bandits, where a learner schedules jobs while learning unknown service rates modeled by logistic functions of job-server features. Performance is measu…
Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation
Kihyun Yu, Seoungbin Bae, Dabeen Lee
We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Existing high-probability guarantees for this sett…
Nonpreemptive Scheduling While Learning Context-Dependent Service Rates
Wansoo Choi, Seoungbin Bae, Dabeen Lee
We study nonpreemptive contextual queueing bandits in a single-server system. Each job is represented by a -dimensional context vector; in each round, a job may arrive with its…
Constrained Online Convex Optimization without Slater's Condition
Kihyun Yu, Junehee Lee, Dabeen Lee
We study constrained online convex optimization with adversarial losses and stochastic or adversarial constraints. For stochastic constraints, existing algorithms that achieve near…
Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret
Seoungbin Bae, Dabeen Lee
Contextual queueing bandits provide a framework for learning to schedule heterogeneous jobs under unknown context-dependent service rates. Under stochastic contexts, existing algor…
Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret
Kihyun Yu, Beomhan Baek, Dabeen Lee
We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Our contributions are twofold. First, we establish…
Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses
Kihyun Yu, Seoungbin Bae, Dabeen Lee
Existing work on linear constrained Markov decision processes (CMDPs) has primarily focused on stochastic settings, where the losses and costs are either fixed or drawn from fixed…
Chebyshev Center-Based Direction Selection for Multi-Objective Optimization and Training PINNs
Hoyeol Yoon, Seoungbin Bae, Nam Ho-Nguyen +1
Physics-informed neural networks (PINNs) are a promising approach for solving partial differential equations (PDEs). Their training, however, is often difficult because multiple lo…
Logistic Bandits with Regret without Context Diversity Assumptions
Seoungbin Bae, Dabeen Lee
We study the -armed logistic bandit problem, where at each round, the agent observes feature vectors associated with actions. Existing approaches that achieve a rate-opt…
Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards
Kihyun Yu, Seoungbin Bae, Dabeen Lee
We study safe reinforcement learning in finite-horizon linear mixture constrained Markov decision processes (CMDPs) with adversarial rewards under full-information feedback and an…
Learning to Route and Schedule LLMs from User Retrials via Contextual Queueing Bandits
Seoungbin Bae, Junyoung Son, Dabeen Lee
Explosive demands for LLMs often cause user queries to accumulate in server queues, requiring efficient routing (query-LLM matching) and scheduling (query prioritization) mechanism…
Queue Length Regret Bounds for Contextual Queueing Bandits
Seoungbin Bae, Garyeong Kang, Dabeen Lee
We introduce contextual queueing bandits, a new context-aware framework for scheduling while simultaneously learning unknown service rates. Individual jobs carry heterogeneous cont…
Neural Logistic Bandits
Seoungbin Bae, Dabeen Lee
We study the problem of neural logistic bandits, where the main task is to learn an unknown reward function within a logistic link function using a neural network. Existing approac…