72 citations · 74 across the 8 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Making Analog Training Scale: Co-Designing Mapping, Optimizer, and Converters
Zhaoxian Wu, Tayfun Gokmen, Omobayode Fagbohungbe +2
Analog in-memory computing (AIMC) offers an alternative for model training by executing matrix operations directly where weights are stored. However, scaling AIMC to train modern d…
cs.LG2026
Incorruptible Neural Networks: Training Models that can Generalize to Large Internal Perturbations
Philip Jacobson, Ben Feinberg, Suhas Kumar +3
Flat regions of the neural network loss landscape have long been hypothesized to correlate with better generalization properties. A closely related but distinct problem is training…