Ming Jin

Distributed Optimization and Distributed Learning: A Paradigm Shift for Power Systems

Ahmad Al-Tawaha, Elson Cibaku, SangWoo Park, Javad Lavaei et autres

This article provides a comprehensive overview of recent advances in distributed optimization and machine learning for power systems, particularly focusing on optimal power flow (OPF) problems. We cover distributed algorithms for convex relaxations and nonconvex optimization, highlighting key algorithmic ingredients, and practical …

us (code pays fourni par la source)

Distribution Grid Critical Load Restoration under Uncertain Topology Changes via a Hierarchical Multi-Agent Reinforcement Learning Approach

Vanshaj Khattar, Yiyun Yao, Fei Ding, Ming Jin

Extreme weather events and/or cyber-attacks can significantly disrupt the power generation of a power grid, leading to catastrophic consequences. In this paper, the critical load restoration (CLR) problem in the community distribution grid is addressed. Existing approaches for CLR rely on the …

Monte Carlo Grid Dynamic Programming: Almost Sure Convergence and Probability Constraints

Mohammad S. Ramadan, Ahmad Al-Tawaha, Mohamed Gamal Shouman, Ahmed M. Atallah et autres

Dynamic Programming suffers from the well-known "curse of dimensionality", further exacerbated by expectations in stochastic systems. This paper presents a Monte Carlo-based sampling approach of the state and input spaces and an interpolation procedure for the resulting value function in a "self-approximating" …

us, jp (code pays fourni par la source)

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning

Mahavir Dabas, Si Chen, C. A. Fleming, Ming Jin

Safety alignment is crucial for large language models (LLMs) to resist malicious instructions but often results in over-refusals, where benign prompts are unnecessarily rejected, impairing user experience and model utility. We introduce ACTOR (Activation-Based Training for Over-Refusal Reduction), a robust and compute- …

The Differential Role of Human Capital in Generative AI’s Impact on Creative Tasks

Huang Meiling, Ming Jin, Ning Li

Generative AI is rapidly reshaping creative work, raising critical questions about its beneficiaries and societal implications. This study challenges prevailing assumptions by exploring how generative AI interacts with diverse forms of human capital in creative tasks. Through two random controlled experiments in …

cn (code pays fourni par la source)

A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks

Zain ul Abdeen, Vassilis Kekatos, Ming Jin

Certified robustness is a critical property for deploying neural networks (NN) in safety-critical applications. A principle approach to achieving such guarantees is to constrain the global Lipschitz constant of the network. However, accurate methods for Lipschitz-constrained training often suffer from non-convex formulations …

Model Residuals as Shields: A Two-Level Formulation to Defend Smart Grids From Poisoning Attacks

Tung-Wei Lin, Padmaksha Roy, Yi Zeng, Ming Jin et autres

The advancement of smart grids presents both vast opportunities and heightened cybersecurity risks. Data-driven defense mechanisms, though designed as a shield against these threats, can fall prey to poisoning attacks. We delve into regression settings, underscoring the imperative to fortify defenses against …

us (code pays fourni par la source)

Backtracking for Safety

Bilgehan Sel, Dingcheng Li, Phillip Wallis, Vaishakh Keshava et autres

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks, but ensuring their safety and alignment with human values remains crucial. Current safety alignment methods, such as supervised fine-tuning and reinforcement learning-based approaches, can exhibit vulnerabilities to adversarial attacks and often …

Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning

Shangding Gu, Laixi Shi, Muning Wen, Ming Jin et autres

Driven by inherent uncertainty and the sim-to-real gap, robust reinforcement learning (RL) seeks to improve resilience against the complexity and variability in agent-environment sequential interactions. Despite the existence of a large number of RL benchmarks, there is a lack of standardized benchmarks …

Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning

Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang et autres

In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints. To tackle this issue, we propose a primal-based framework that orchestrates policy optimization between multi-objective learning and constraint …

de, us, cn (code pays fourni par la source)

Noise-Robust and Sector-Aware Representation Learning for Natural Gas Demand Forecasting

Xinxing Zhou, Jiaqi Ye, Shubao Zhao, Ming Jin et autres

cn, au (code pays fourni par la source)

Augmenting Minds or Automating Skills: The Differential Role of Human Capital in Generative AI's Impact on Creative Tasks

Huang Meiling, Ming Jin, Ning Li

Generative AI is rapidly reshaping creative work, raising critical questions about its beneficiaries and societal implications. This study challenges prevailing assumptions by exploring how generative AI interacts with diverse forms of human capital in creative tasks. Through two random controlled experiments in …