Organizers:
The field of robust statistics addresses the challenge of devising estimators that demonstrate reliable performance in situations where the data deviates substantially from the assumed idealized models. Over the past decade, a line of work in computer science has led to significant advances in the algorithmic aspects of this field. This workshop will concentrate on exploring the upcoming research directions in algorithmic robust statistics, emphasizing connections with different privacy and associated concepts of algorithmic stability.
Organizers:
This workshop will explore the challenges in developing machine learning algorithms for adaptive scenarios, where data distribution can be influenced by algorithm choices, adaptive learning from human feedback is essential, and environments are dynamic. The workshop aims to bring together experts to address these challenges in topics such as reinforcement learning from human feedback, multi-agent reinforcement learning, decision-making foundation models, human-robot interaction, and transfer learning in reinforcement learning, fostering discussions on practical algorithms for real-world deployment.
Organizers:
This workshop will explore recent advances in incorporating machine learning heuristics to improve classical algorithmic design through data-driven insights, such as through training data, historical information, or properties of the input distribution. The workshop will focus on both fundamental aspects of designing such algorithms, as well on applications to problems such as data structure design, dynamic algorithm design, graph algorithms, randomized numerical linear algebra, online algorithms, scheduling algorithms, streaming and sketching algorithms, and supervised and unsupervised learning. Invited participants will span a diverse set of research areas from both academia and industry, including theoretical computer science, machine learning, algorithmic game theory, coding theory, databases and systems.
Organizers:
This workshop aims to showcase works that develop new methodologies to enable data-driven decision-making for a variety of applications. The emphasis will be on decisions with sequential aspects (similar to the corresponding Simons Institute program). The workshop will present a diverse set of applications where data-driven decisions play a crucial role. Examples of such applications include but are not limited to: healthcare, criminal justice, refugee resettlement, education, online platforms, sustainability, etc. We will invite participants from both academia and industry.
Organizers:
The 2024 Midwest Computational Biology Workshop will explore emerging topics in the field of computational biology, covering a spectrum of algorithmic and machine learning challenges to address biological questions. The workshop will bring together a wide range of participants from different backgrounds (computer science, biology, medicine) and positions (undergrads, grad students, faculty, industry professionals). By connecting these researchers, the workshop aims to initiate new interdisciplinary interactions and collaborations. The workshop will be organized around three sessions: genomics, immunology and protein structure. Each session will include invited talks about current research and open problems, as well as a discussion period to brainstorm collaborative solutions.