Francis Bach, NRIA, ENS, and PSL Paris Abstract: The representation of non-negative functions as sums of squares has become an important tool in many modeling and optimization tasks. Traditionally applied to polynomial functions, it requires rich tools from algebraic geometry that led to many developments in the last twenty years. In this talk, I will […]
Mert Pilanci, Stanford University Abstract: Since deep neural network training problems are inherently non-convex, their recent dramatic success largely relies on non-convex optimization heuristics and experimental findings. Despite significant advancements, the non-convex nature of neural network training poses two central challenges: first, understanding the underlying mechanisms that contribute to model performance, and second, achieving efficient […]
Ramya Korlakai Vinayak, Assistant Professor, University of Wisconsin–Madison Abstract: Machine learning (ML) algorithms are becoming ubiquitous in various application domains such as public health, genomics, psychology, and social sciences. In these domains, data is often obtained from populations that are diverse, e.g., varying demographics, phenotypes, preferences etc. Many ML algorithms focus on learning model parameters […]
The TILOS Ethics and Early Career Committee invites you to an upcoming round table discussion on AI Ethics. This will take place virtually through Zoom on Friday, June 2, 2023 at 9am Pacific / 11am Central / Noon Eastern. Please join Dr. Nisheeth Vishnoi from Yale, Dr. David Danks from UC San Diego, and Dr. […]
Masashi Sugiyama, University of Tokyo and RIKEN Abstract: In statistical inference and machine learning, we face a variety of uncertainties such as training data with insufficient information, label noise, and bias. In this talk, I will give an overview of our research on reliable machine learning, including weakly supervised classification (positive unlabeled classification, positive confidence classification, […]
The first TILOS Fireside Chat of Fall 2023 will be a conversation about theory in the age of modern AI led by TILOS members Nisheeth Vishnoi, Tara Javidi, Misha Belkin, and Arya Mazumdar (moderator). This will be a great opportunity to discuss implications of AI and roles of theory (especially with the recent development in […]
Michael Galkin, Research Scientist, Intel AI Lab Abstract: Foundation models in graph learning are hard to design due to the lack of common invariances that transfer across different structures and domains. In this talk, I will give an overview of the two main tracks of my research at Intel AI: creating foundation models for knowledge […]
Aadirupa Saha, Research Scientist, Apple Abstract: Customer statistics collected in several real-world systems have reflected that users often prefer eliciting their liking for a given pair of items, say (A,B), in terms of relative queries like: “Do you prefer Item A over B?”, rather than their absolute counterparts: “How much do you score items A […]
TILOS is a sponsor of Boston Symmetry Day, a meeting of symmetry-minded folks in the Boston area. It is the largest event on symmetry and machine learning in the United States. Registration is free for all who would like to attend, subject to space constraints.
Marco Mondelli, Institute of Science and Technology Austria Abstract: A recent line of work has analyzed the properties of deep over-parameterized neural networks through the lens of the Neural Tangent Kernel (NTK). In this talk, I will show how concentration bounds on the NTK (and, specifically, on its smallest eigenvalue) provide insights on (i) the […]
