65 citations · 168 across the 18 of their papers we have counts for
5 papers · 1 filter
Draining Fictitious Knots: Restoring Distance-Awareness Guarantees for High-Dimensional Spline Networks
Masoud Ataei, Mohammad Javad Khojasteh, Vikas Dhiman
Kolmogorov-Arnold Networks (KANs) with spline activations have recently shown promise for interpretable function approximation. Distance-Aware Error for Kolmogorov Networks (DAREK)…
ADS-C: Antidistillation Sampling for Classification
Khawaja Abaid Ullah, Mohammad Javad Khojasteh
Knowledge distillation enables an adversary to replicate a proprietary classifier by querying its prediction interface and training a surrogate on the returned probability vectors.…
VINA: Variational Invertible Neural Architectures
Shubhanshu Shekhar, Mohammad Javad Khojasteh, Ananya Acharya +2
The distinctive architectural features of normalizing flows (NFs), notably bijectivity and tractable Jacobians, make them well-suited for generative modeling. Invertible neural net…
Worst-Case Distance-Aware Error Bounds for Neural Networks
Masoud Ataei, Vikas Dhiman, Mohammad Javad Khojasteh
Safety-critical applications of machine learning require uncertainty estimates that support reliable worst-case analysis. Neural networks (NNs) provide expressive function approxim…
ISR: Invertible Symbolic Regression
Tony Tohme, Mohammad Javad Khojasteh, Mohsen Sadr +2
We introduce an Invertible Symbolic Regression (ISR) method. It is a machine learning technique that generates analytical relationships between inputs and outputs of a given datase…