Speakers

We are honored to have several leading experts who will provide keynote presentations. Each speaker brings unique insights into machine learning theory, weight space analysis, and neural network synthesis.

Stella X. Yu

Stella X. Yu
Talk Title TBD
Talk Abstract TBD
Affiliation University of Michigan
Biography Stella X. Yu is a professor of computer science at the University of Michigan, where she focuses on research in computer vision and machine learning. Prior to joining the University of Michigan, she was the Director of the Vision Group at the International Computer Science Institute (ICSI) in Berkeley and held various academic roles at UC Berkeley, including positions in computer science, vision science, and cognitive sciences. Stella earned her Ph.D. from Carnegie Mellon University, where she specialized in robotics and vision science. Her research explores visual perception through multiple lenses of representation learning aiming to develop models that can exceed human capabilities. She is particularly focused on actionable representation learning and structure-aware models, emphasizing that structure in visual data should naturally emerge or be reflected in the model structures.
   

Michael W. Mahoney

Michael W. Mahoney
Talk Title TBD
Talk Abstract TBD
Affiliation UC Berkeley, ICSI, LBNL, Amazon
Biography Michael W. Mahoney is a professor at the University of California at Berkeley in the Department of Statistics and at the International Computer Science Institute (ICSI). He is also an Amazon Scholar as well as head of the Machine Learning and Analytics Group at the Lawrence Berkeley National Laboratory. He works on algorithmic and statistical aspects of modern large-scale data analysis. Much of his recent research has focused on large-scale machine learning, including randomized matrix algorithms and randomized numerical linear algebra, scientific machine learning, scalable stochastic optimization, geometric network analysis tools for structure extraction in large informatics graphs, scalable implicit regularization methods, computational methods for neural network analysis, physics informed machine learning, and applications in genetics, astronomy, medical imaging, social network analysis, and internet data analysis. He received his PhD from Yale University with a dissertation in computational statistical mechanics, and he has worked and taught at Yale University in the mathematics department, at Yahoo Research, and at Stanford University in the mathematics department.

Boris Knyazev

Boris Knyazev
Talk Title TBD
Talk Abstract TBD
Affiliation Samsung - SAIT AI Lab
Biography Boris Knyazev is a Research Scientist at Samsung - SAIT AI Lab, Montreal, Canada. He completed his PhD at the Machine Learning Research Group, University of Guelph and Vector Institute under supervision of Graham Taylor in 2022. His research interests lie at the intersection of graph neural networks (GNNs), computer vision and meta-learning. In the past, he interned at Facebook AI Research (FAIR) working with Adriana Romero and Michal Drozdal on parameter prediction for neural networks. He also interned at Mila working with Eugene Belilovsky and Aaron Courville on visual compositional generalization. He also interned at SRI International with Mohamed Amer, where he worked on training GNNs on image superpixels. Before starting his PhD, he worked on unsupervised learning and pretraining of neural networks, face, emotion and facial attributes recognition, and video recognition.

Naomi Saphra

Naomi Saphra
Talk Title TBD
Talk Abstract TBD
Affiliation Harvard University
Biography Naomi Saphra is a research fellow at the Kempner Institute at Harvard University. She is interested in NLP training dynamics: how models learn to encode linguistic patterns or other structure and how we can encode useful inductive biases into the training process. Naomi has earned a PhD from the University of Edinburgh on Training Dynamics of Neural Language Models; worked at NYU, Google and Facebook; and attended Johns Hopkins and Carnegie Mellon University. Outside of research, she plays roller derby under the name Gaussian Retribution, perform standup comedy, and shepherd disabled programmers into the world of code dictation.