29 citations · 86 across the 25 of their papers we have counts for
5 papers · 1 filter
Behavioral Capacity Certificates for Quantized Language Models
Arian Eamaz, Mojtaba Soltanalian
Activation and key-value cache precision change what a quantized language model computes without altering its stored weights. Direct weight-code bounds, however, assign identical c…
Training Under Challenge: Executable Certificates and Challenge-Closed Optimality for Neural Networks
Farhang Yeganegi, Arian Eamaz, Mojtaba Soltanalian
A flat training curve does not reveal whether a neural network has reached a global optimum, is locally trapped, is representation-limited, or is mismatched to its trainer. We intr…
Trust, but Verify: Peeling Low-Bit Transformer Networks for Training Monitoring
Arian Eamaz, Farhang Yeganegi, Mojtaba Soltanalian
Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited vis…
Physics-Inspired Binary Neural Networks: Interpretable Compression with Theoretical Guarantees
Arian Eamaz, Farhang Yeganegi, Mojtaba Soltanalian
Why rely on dense neural networks and then blindly sparsify them when prior knowledge about the problem structure is already available? Many inverse problems admit algorithm-unroll…
Data-Aware Training Quality Monitoring and Certification for Reliable Deep Learning
Farhang Yeganegi, Arian Eamaz, Mojtaba Soltanalian
Deep learning models excel at capturing complex representations through sequential layers of linear and non-linear transformations, yet their inherent black-box nature and multi-mo…