Tom Jacobs

Hyperbolic Aware Minimization: Implicit Bias for Sparsity

Never Saddle for Reparameterized Steepest Descent as Mirror Flow

The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

Pay Attention to Small Weights

Sign-In to the Lottery: Reparameterizing Sparse Training

Mask in the Mirror: Implicit Sparsification

Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?

Memory Savings by Sharing One Source: Insights into Subsetsum Approximation

Time-Dependent Mirror Flows and Where to Find Them