Ai4opt Seminar Series An Algorithm

Abstract: Crowdsourcing is a popular method used to estimate ground-truth labels by collecting noisy labels from workers. In this ... Abstract: We discuss the role of learning in optimal network control, with focus on network stability in networks with uncooperative ... Abstract: Graph Neural Networks (GNNs) have become a popular tool for learning algorithmic tasks, related to combinatorial ... Abstract: Semidefinite programs (SDPs) have been used as a tractable relaxation for many NP-hard problems that naturally arise ... Abstract: Federated Learning has emerged as an important paradigm in modern large-scale machine learning, where the training ... Abstract: Neural network driven applications suffer from hallucination and calibration issues where they confidently provide ...

Abstract: Consider a large number of agents, N, faced with the problem of choosing amongst a large number of options, K. The ... Abstract: The ability to learn and control tail risks, besides being an integral part of quantitative risk management, is central to ... Abstract: The combination of machine learning (for prediction) and optimization (for decision-making) is increasingly used in ... Abstract: Provable neural training is a fundamental challenge in the field of deep-learning theory – and it largely remains an open ... Abstract: Markov decision processes (MDPs) constitute one of the predominant modeling and solution paradigms for dynamic ... Abstract: In many applications of reinforcement learning (RL) and control, policies need to satisfy constraints to ensure feasibility, ...

Abstract: Hidden Markov models (HMMs) are some of the most widely-used tools in statistical sequence modeling; unfortunately ...