Author

V. Reddy

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Jul 2026

Conditioned Direct Feedback Alignment via Activity and Error Geometry

Conditioned DFA (nDFA), a family that adapts established inverse-moment preconditioning to either side of this update, is studied, establishing practical benefits and important limits of conditioning learning with fixed random feedback.

Houman Safaai, V. Reddy, Bernardo L. Sabatini · arXiv.org · 1 citation

#machine learning Preprint Sep 2026

Common-Mode Collapse and Recovery in Direct Feedback Alignment

Direct feedback alignment (DFA) trains hidden layers through fixed random projections of output error. With tanh hidden units and independent sigmoid outputs, plain stochastic gradient descent can stall near the loss of a constant predictor of class frequencies. We trace this stall to the error's common mode, the compo...

V. Reddy, Bernardo L. Sabatini, Houman Safaai · 0 citations