Related papers: Provably Efficient Online Hyperparameter Optimizat…

Population-based learning paradigms, including evolutionary strategies, Population-Based Training (PBT), and recent model-merging methods, combine fast within-model optimisation with slower population-level adaptation. Despite their…

The performance of reinforcement learning (RL) algorithms is sensitive to the choice of hyperparameters, with the learning rate being particularly influential. RL algorithms fail to reach convergence or demand an extensive number of samples…

The rapid advancement in large language models (LLMs) has brought forth a diverse range of models with varying capabilities that excel in different tasks and domains. However, selecting the optimal LLM for user queries often involves a…

The primary goal of my Ph.D. study is to develop provably efficient and practical algorithms for data-driven sequential decision-making under uncertainty. My work focuses on reinforcement learning (RL), multi-armed bandits, and their…

This paper studies model-based bandit and reinforcement learning (RL) with nonlinear function approximations. We propose to study convergence to approximate local maxima because we show that global convergence is statistically intractable…

Contextual bandits often provide simple and effective personalization in decision making problems, making them popular tools to deliver personalized interventions in mobile health as well as other health applications. However, when bandits…

In modern ML Ops environments, model deployment is a critical process that traditionally relies on static heuristics such as validation error comparisons and A/B testing. However, these methods require human intervention to adapt to…

We consider the problem of fitting a reinforcement learning (RL) model to some given behavioral data under a multi-armed bandit environment. These models have received much attention in recent years for characterizing human and animal…

Users can be supported to adopt healthy behaviors, such as regular physical activity, via relevant and timely suggestions on their mobile devices. Recently, reinforcement learning algorithms have been found to be effective for learning the…

Contextual bandits algorithms have become essential in real-world user interaction problems in recent years. However, these algorithms rely on context as attribute value representation, which makes them unfeasible for real-world domains…

Ensemble learning plays a crucial role in practical applications of online learning due to its enhanced classification performance and adaptable adjustment mechanisms. However, most weight allocation strategies in ensemble learning are…

Sequential decision-making algorithms such as multi-armed bandits can find optimal personalized decisions, but are notoriously sample-hungry. In personalized medicine, for example, training a bandit from scratch for every patient is…

In this work we revisit two classic high-dimensional online learning problems, namely linear regression and contextual bandits, from the perspective of adversarial robustness. Existing works in algorithmic robust statistics make strong…

Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments. However, training deep RL model is challenging in real world applications such as production-scale health-care or recommender systems because…

Contextual bandit algorithms are commonly used in digital health to recommend personalized treatments. However, to ensure the effectiveness of the treatments, patients are often requested to take actions that have no immediate benefit to…

Meta-learning models, or models that learn to learn, have been a long-desired target for their ability to quickly solve new tasks. Traditional meta-learning methods can require expensive inner and outer loops, thus there is demand for…

Automated algorithm selection and hyperparameter tuning facilitates the application of machine learning. Traditional multi-armed bandit strategies look to the history of observed rewards to identify the most promising arms for optimizing…

Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback over the selected arms for the past contexts. However,…

Model-based Reinforcement Learning (MBRL) is a promising framework for learning control in a data-efficient manner. MBRL algorithms can be fairly complex due to the separate dynamics modeling and the subsequent planning algorithm, and as a…

Effective solving of constraint problems often requires choosing good or specific search heuristics. However, choosing or designing a good search heuristic is non-trivial and is often a manual process. In this paper, rather than manually…