Related papers: Adaptive Data Exploitation in Deep Reinforcement L…

Multi-agent collaborative perception is expected to significantly improve perception performance by overcoming the limitations of single-agent perception through exchanging complementary information. However, training a robust collaborative…

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…

The deep learning-based analysis of medical images suffers from data scarcity because of high annotation costs and privacy concerns. Researchers in this domain have used transfer learning to avoid overfitting when using complex…

The automatic classification of occupational accident reports is pivotal for workplace safety analysis but is persistently hindered by severe class imbalance and data scarcity. In this paper, we propose ABEX-RAT, a resource-efficient…

Empirical risk minimization (ERM) is the workhorse of machine learning, whether for classification and regression or for off-policy policy learning, but its model-agnostic guarantees can fail when we use adaptively collected data, such as…

This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget. While many existing algorithms simplify networks based on the number of MACs or…

Quantifying the value of data is a fundamental problem in machine learning. Data valuation has multiple important use cases: (1) building insights about the learning task, (2) domain adaptation, (3) corrupted sample discovery, and (4)…

We integrate a meta-reinforcement learning algorithm with the DreamerV3 architecture to improve load balancing in operating systems. This approach enables rapid adaptation to dynamic workloads with minimal retraining, outperforming the…

Modern optimization problems in scientific and engineering domains often rely on expensive black-box evaluations, such as those arising in physical simulations or deep learning pipelines, where gradient information is unavailable or…

Deep reinforcement learning (DRL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. We propose two novel data augmentation techniques for DRL in…

Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and…

With the increasing penetration of distributed energy resources, distributed optimization algorithms have attracted significant attention for power systems applications due to their potential for superior scalability, privacy, and…

Asynchronous methods are fundamental for parallelizing computations in distributed machine learning. They aim to accelerate training by fully utilizing all available resources. However, their greedy approach can lead to inefficiencies using…

Reinforcement learning has enjoyed multiple successes in recent years. However, these successes typically require very large amounts of data before an agent achieves acceptable performance. This paper introduces a novel way of combating…

In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a…

Multi-label image classification demands adaptive training strategies to navigate complex, evolving visual-semantic landscapes, yet conventional methods rely on static configurations that falter in dynamic settings. We propose MAT-Agent, a…

Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a…

Distributed multi-party learning provides an effective approach for training a joint model with scattered data under legal and practical constraints. However, due to the quagmire of a skewed distribution of data labels across participants…

Domain-adaptive trajectory imitation is a skill that some predators learn for survival, by mapping dynamic information from one domain (their speed and steering direction) to a different domain (current position of the moving prey). An…

We present a method that lowers the dose required for a ptychographic reconstruction by adaptively scanning the specimen, thereby providing the required spatial information redundancy in the regions of highest importance. The proposed…