Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective
Guy Smorodinsky, Sveta Gimpleson, Itay Safran
We study the convergence dynamics of Gradient Descent (GD) in a minimal binary classification setting, consisting of a two-neuron ReLU network and two training instances. We prove…
cs.LG2025
No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
Yehonatan Refael, Guy Smorodinsky, Ofir Lindenbaum +1
The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the traini…
cs.LG2025
SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
Yehonathan Refael, Guy Smorodinsky, Tom Tirer +1
Low-rank gradient-based optimization methods have significantly improved memory efficiency during the training of large language models (LLMs), enabling operations within constrain…