activity
20222026
most citedMemorization and Optimization in Deep Neural Networks with Minimum Over-parameterization

2 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.LG2026

On Reparameterizing the Score Function

Mohammad Hossein Amani, Leonardo Bocchieri, Maxime Peyrard +2

Policy gradients for autoregressive sequence models differentiate each token's log-probability while holding the conditioning history fixed. This discards information about how ear…