10 papers
LoRSA: Toward Generalizable Parameter-Efficient Fine-Tuning for Biomedical Downstream Tasks
Saed Moradi, Benyamin Ghojogh, M. Hadi Sepanj +2
Parameter-efficient fine-tuning enables the adaptation of vision foundation models to biomedical tasks under limited computational resources, but a single low-rank update can const…
Data Evolution by Wittgenstein's Rule Following
Aydin Ghojogh, Benyamin Ghojogh
This paper introduces Wittgenstein's Rule Following (WRF) data evolution, a framework in philomatics for evolving or generating a new dataset from a sequence of previously observed…
Self-Supervised Learning by Curvature Alignment
Benyamin Ghojogh, M. Hadi Sepanj, Paul Fieguth
Self-supervised learning (SSL) has recently advanced through non-contrastive methods that couple an invariance term with variance, covariance, or redundancy-reduction penalties. Wh…
Foundations of Riemannian Geometry for Riemannian Optimization: A Monograph with Detailed Derivations
Benyamin Ghojogh
Riemannian geometry provides the fundamental framework for optimization on nonlinear spaces such as matrix manifolds, which arise in machine learning, signal processing, and roboti…
Kernel VICReg for Self-Supervised Learning in Reproducing Kernel Hilbert Space
M. Hadi Sepanj, Benyamin Ghojogh, Saed Moradi +1
Self-supervised learning (SSL) has emerged as a powerful paradigm for representation learning by optimizing geometric objectives, such as invariance to augmentations, variance pres…
Similarity Algebra: A Framework for Approximate Algebraic and Lie Structures with Collapse to Classical Algebra
Benyamin Ghojogh, Golbahar Amanpour
Classical algebraic structures require exact satisfaction of their defining axioms. We propose similarity algebra, a framework extending algebraic and Lie structures to settings wh…