WA6a: Compression and sparsity in deep learning optimization
Wed, 28 Oct, 08:15 - 09:55 PT (UTC -7)
Location: Room 6
Session Type: Lecture
Session Chair: Laura Balzano, University of Michigan, United States
Track: Adaptive Systems, Machine Learning, and Data Analytics
Wed, 28 Oct, 08:15 - 08:40 PT (UTC -7)

WA6a.1: Gradient-based dimension reduction for Bayesian models
Ricardo Baptista, University of Toronto, Canada
Wed, 28 Oct, 08:40 - 09:05 PT (UTC -7)

WA6a.2: Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
Can Yaras, Laura Balzano, University of Michigan, United States; Peng Wang, University of Macau, United States; Qing Qu, University of Michigan, United States
Wed, 28 Oct, 09:05 - 09:30 PT (UTC -7)

WA6a.3: Zero-Shot Inference-time Structured Approximation of Softmax Attention
Wed, 28 Oct, 09:30 - 09:55 PT (UTC -7)

WA6a.4: Neuron Pursuit: A Parsimony-Driven Iterative Greedy Algorithm for Building Neural Networks
Akshay Kumar, Jarvis Haupt, University of Minnesota, United States