Xiaoyan Hu

Yulai Zhao, Wenhao Zhan, Xiaoyan Hu et al. · princeton

We study risk-sensitive Reinforcement Learning (RL), where we aim to maximize the Conditional Value at Risk (CVaR) with a fixed risk tolerance $τ$. Prior theoretical work studying risk-sensitive RL focuses on the tabular Markov Decision Processes (MDPs) setting. To extend CVaR RL to settings where state space is large, function approximation must be deployed. We study CVaR RL in low-rank MDPs with nonlinear function approximation. Low-rank MDPs assume the underlying transition kernel admits a low-rank decomposition, but unlike prior linear models, low-rank MDPs do not assume the feature or state-action representation is known. We propose a novel Upper Confidence Bound (UCB) bonus-driven algorithm to carefully balance the interplay between exploration, exploitation, and representation learning in CVaR RL. We prove that our algorithm achieves a sample complexity of $\tilde{O}\left(\frac{H^7 A^2 d^4}{τ^2 ε^2}\right)$ to yield an $ε$-optimal CVaR, where $H$ is the length of each episode, $A$ is the capacity of action space, and $d$ is the dimension of representations. Computational-wise, we design a novel discretized Least-Squares Value Iteration (LSVI) algorithm for the CVaR objective as the planning oracle and show that we can find the near-optimal policy in a polynomial running time with a Maximum Likelihood Estimation oracle. To our knowledge, this is the first provably efficient CVaR RL algorithm in low-rank MDPs.

Xiaoyan Hu, Ho-fung Leung, Farzan Farnia

Selecting a sample generation scheme from multiple prompt-based generative models, including large language models (LLMs) and prompt-guided image and video generation models, is typically addressed by choosing the model that maximizes an averaged evaluation score. However, this score-based selection overlooks the possibility that different models achieve the best generation performance for different types of text prompts. An online identification of the best generation model for various input prompts can reduce the costs associated with querying sub-optimal models. In this work, we explore the possibility of varying rankings of text-based generative models for different text prompts and propose an online learning framework to predict the best data generation model for a given input prompt. The proposed PAK-UCB algorithm addresses a contextual bandit (CB) setting with shared context variables across the arms, utilizing the generated data to update kernel-based functions that predict the score of each model available for unseen text prompts. Additionally, we leverage random Fourier features (RFF) to accelerate the online learning process of PAK-UCB. Our numerical experiments on real and simulated text-to-image and image-to-text generative models show that RFF-UCB performs successfully in identifying the best generation model across different sample types. The code is available at: github.com/yannxiaoyanhu/dgm-online-select.

Xiaoyan Hu, Lauren Pick, Ho-fung Leung et al.

The rapid advancement of generative AI has provided users with a wide range of well-trained models to address diverse prompts. When selecting a model for a given prompt, users should weigh not only its performance but also its service cost. However, existing model-selection methods typically emphasize performance while overlooking cost differences. In this paper, we introduce PromptWise, an online learning framework that assigns prompts to generative models in a cost-aware manner. PromptWise estimates prompt-model compatibility to select the least expensive model expected to deliver satisfactory outputs. Unlike standard contextual bandits that make a one-shot decision per prompt, PromptWise employs a cost-aware bandit structure that allows sequential model assignments per prompt to reduce total service cost. Through numerical experiments on tasks such as code generation and translation, we demonstrate that PromptWise can achieve performance comparable to baseline selection methods while incurring substantially lower costs. The code is available at: github.com/yannxiaoyanhu/PromptWise.

Xiaoyan Hu, Ho-fung Leung, Farzan Farnia

Existing frameworks for evaluating and comparing generative models consider an offline setting, where the evaluator has access to large batches of data produced by the models. However, in practical scenarios, the goal is often to identify and select the best model using the fewest possible generated samples to minimize the costs of querying data from the sub-optimal models. In this work, we propose an online evaluation and selection framework to find the generative model that maximizes a standard assessment score among a group of available models. We view the task as a multi-armed bandit (MAB) and propose upper confidence bound (UCB) bandit algorithms to identify the model producing data with the best evaluation score that quantifies the quality and diversity of generated data. Specifically, we develop the MAB-based selection of generative models considering the Fréchet Distance (FD) and Inception Score (IS) metrics, resulting in the FD-UCB and IS-UCB algorithms. We prove regret bounds for these algorithms and present numerical results on standard image datasets. Our empirical results suggest the efficacy of MAB approaches for the sample-efficient evaluation and selection of deep generative models. The project code is available at https://github.com/yannxiaoyanhu/dgm-online-eval.

Xiaoyan Hu, Farzan Farnia, Ho-fung Leung

Reinforcement learning (RL) problems where the learner attempts to infer an unobserved reward from some feedback variables have been studied in several recent papers. The setting of Interaction-Grounded Learning (IGL) is an example of such feedback-based RL tasks where the learner optimizes the return by inferring latent binary rewards from the interaction with the environment. In the IGL setting, a relevant assumption used in the RL literature is that the feedback variable $Y$ is conditionally independent of the context-action $(X,A)$ given the latent reward $R$. In this work, we propose Variational Information-based IGL (VI-IGL) as an information-theoretic method to enforce the conditional independence assumption in the IGL-based RL problem. The VI-IGL framework learns a reward decoder using an information-based objective based on the conditional mutual information (MI) between $(X,A)$ and $Y$. To estimate and optimize the information-based terms for the continuous random variables in the RL problem, VI-IGL leverages the variational representation of mutual information to obtain a min-max optimization problem. Also, we extend the VI-IGL framework to general $f$-Information measures leading to the generalized $f$-VI-IGL framework for the IGL-based RL problems. We present numerical results on several reinforcement learning settings indicating an improved performance compared to the existing IGL-based RL algorithm.