3 papers
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…
cs.ET2025
Energy Efficient Knapsack Optimization Using Probabilistic Memristor Crossbars
Jinzhan Li, Suhas Kumar, Su-in Yi
Constrained optimization underlies crucial societal problems (for instance, stock trading and bandwidth allocation), but is often computationally hard (complexity grows exponential…
cs.LG2025
Forward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Losses
Nazmus Saadat As-Saquib, A N M Nafiz Abeer, Hung-Ta Chien +3
Training neural networks has traditionally relied on backpropagation (BP), a gradient-based algorithm that, despite its widespread success, suffers from key limitations in both bio…