9 accepted papers
Hyperparameter Optimization (HPO) is crucial in machine learning, aiming to optimize hyperparameters to enhance model performance. Although existing methods that leverage prior knowledge—drawn from either previous experiments or expert insights—can accelerate optimization, acquiring a correct prior
Interactive preference elicitation (IPE) aims to substantially reduce human effort while acquiring human preferences in wide personalization systems. Dueling bandit (DB) algorithms enable optimal decision-making in IPE building on pairwise comparisons. However, they remain inefficient when human fee
Motivated by practical applications where stable long-term performance is critical—such as robotics, operations research, and healthcare—we study the problem of distributionally robust (DR) average-reward reinforcement learning. We propose two algorithms that achieve near-optimal sample complexity.…
We explore the control of stochastic systems with potentially continuous state and action spaces, characterized by the state dynamics $X_{t+1} = f(X_t, A_t, W_t)$. Here, $X$, $A$, and $W$ represent the state, action, and exogenous random noise processes, respectively, with $f$ denoting a known funct…
Overparameterized stochastic differential equation (SDE) models have achieved remarkable success in various complex environments, such as PDE-constrained optimization, stochastic control and reinforcement learning, financial engineering, and neural SDEs. These models often feature system evolution c…
The partially observable constrained optimization problems (POCOPs) impede data-driven optimization techniques since an infeasible solution of POCOPs can provide little information about the objective as well as the constraints. We endeavor to design an efficient and provable method for expensive PO…
The ultimate goal of multi-objective optimization (MO) is to assist human decision-makers (DMs) in identifying solutions of interest (SOI) that optimally reconcile multiple objectives according to their preferences. Preference-based evolutionary MO (PBEMO) has emerged as a promising framework that p…
We resolve the open question regarding the sample complexity of policy learning for maximizing the long-run average reward associated with a uniformly ergodic Markov decision process (MDP), assuming a generative model. In this context, the existing literature provides a sample complexity upper bound…
We consider a reinforcement learning setting in which the deployment environment is different from the training environment. Applying a robust Markov decision processes formulation, we extend the distributionally robust Q-learning framework studied in [Liu et. al. 2022]. Further, we improve the desi…