Pacific Northwest Seminar on Topology, Algebra, and Geometry in Data Science
Pacific Northwest Seminar on Topology, Algebra, and Geometry in Data Science
Past Events
- Graph Metanetworks for Processing Diverse Neural Architectures (Derek Lim (MIT)) -
- Generalization and universality in deep learning (Florentin Guth (NYU)) -
- Machine learning, toric Fano varieties, and terminal singularities (Sara Veneziale (Imperial College London)) -
- Global optimization of analytic functions over compact domain (Georgy Scholten, Sorbonne Université) -
- Towards a deeper theoretical understanding of neural networks (Lechao Xiao, Google Brain) -
- A gradient sampling method with complexity guarantees for Lipschitz functions in high and low dimensions (Swati Padmanabhan, UW) -
- What can adversarial examples tell us about similarities between neural networks? (Jacob Springer, Carnegie Mellon University) -
- Computing Representations for Lie Algebraic Networks (Noah Shutty, Google) -
- projUNN: efficient method for training deep networks with unitary matrices (Bobak Kiani (MIT)) -
- Neural Networks with Learned Coarsening for Simplicial Complexes (Sarah McGuire (Michigan State University)) -
- The Intrinsic Manifolds of Radiological Images and Their Role in Deep Learning (Nick Konz (Duke)) -
- Groups and Symmetries in Statistical Models (Anna Seigal (Harvard)) -
- How to choose informative representations of topological features in persistent homology (Gregory Henselman-Petrusek (PNNL)) -
- Approximate vector bundles and fiberwise dimensionality reduction (Luis Scoccola (Northeastern)) -
- Modeling Many-to-Many Maps (Lizzy Coda (PNNL)) -
- Riemannian Geometry in Machine Learning (Isay Katsman (Cornell)) -
- Towards Mechanics of Learning in Neural Networks (Daniel Kunin (Stanford) and Hidenori Tanaka (NTT Physics & Informatics Laboratories)) -
- Machine Learning Beyond Accuracy (Shibani Santurkar (Stanford)) -
- Functional dimension of feedforward ReLU neural networks (Kathryn Lindsey, (Boston College)) -
- Applications of Group Symmetry (Emily King, (Colorado State University)) -
- DNA: Dynamic Network Augmentation (Scott Mahan (University of California, San Diego)) -
- A tool for deep learning model interpretability (Davis Brown (Pacific Northwest National Laboratory)) -
- From Zigzags to Networks: Topological Tools for Time Series Analysis (Sarah Tymochko (Michigan State University)) -
- Private AI: Machine Learning on Encrypted Data (Kristin Lauter, Facebook AI Research (FAIR)) -
- TBA (Mitchell Wortsman, UW CSE) -
- Chirality in Vision (Rekha Thomas, UW Math) -
- Detecting Short-lasting Topics Using Nonnegative Tensor Decomposition ( Lara Kassab, Colorado State University) -
- Using the linear geometry of ReLU neural networks to detect out-of-distribution inputs (Grayson Jorgenson, Pacific Northwest National Lab) -
- Studying relations geometrically and topologically (Michael Robinson, American University) -
- A Polynomial Time Algorithm for Constructing Equivariant Neural Networks (Marc Finzi, NYU) -
- Topic Models, Methods, and Medicine (Jamie Haddock, Harvey Mudd College) -