77 citations · 158 across the 13 of their papers we have counts for
4 papers · 1 filter
Common-Mode Collapse and Recovery in Direct Feedback Alignment
Varun Reddy, Bernardo L. Sabatini, Houman Safaai
Direct feedback alignment (DFA) trains hidden layers through fixed random projections of output error. With tanh hidden units and independent sigmoid outputs, plain stochastic grad…
Conditioned Direct Feedback Alignment via Activity and Error Geometry
Houman Safaai, Varun Reddy, Bernardo L. Sabatini
Direct feedback alignment (DFA) trains hidden layers with fixed random projections of the output error. Even when this feedback provides useful credit, unequal scales across activi…
Supernodes and Halos: Loss-Critical Hubs in LLM Feed-Forward Layers
Audrey Cherilyn, Houman Safaai
We study the organization of channel-level importance in transformer feed-forward networks (FFNs). Using a Fisher-style loss proxy (LP) based on activation-gradient second moments,…
Amortized Vine Copulas for High-Dimensional Density and Information Estimation
Houman Safaai
Modeling high-dimensional dependencies while keeping likelihoods tractable remains challenging. Classical vine-copula pipelines are interpretable but can be expensive, while many n…