1 citations · 1 across the 4 of their papers we have counts for
3 papers · 1 filter
Percolation Dynamics in Optimization: Variance Cascades and Nested Symmetry
Sai Niranjan Ramachandran, Suvrit Sra
We study the dynamics of Stochastic Gradient Descent (SGD), which is known to steer deep neural networks toward invariant sets that correspond to simpler subnetworks. How this stee…
Trees to Flows and Back: Unifying Decision Trees and Diffusion Models
Sai Niranjan Ramachandran, Suvrit Sra
Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work unifies the two by establishi…
Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models
Sai Niranjan Ramachandran, Manish Krishan Lal, Suvrit Sra
We analyse how the sampling dynamics of distributions evolve in score-based diffusion models using cross-fluctuations, a centered-moment statistic from statistical physics. Specifi…