3 papers
cs.LG2026
Hamiltonian Metric Learning and Energy-Based Training: A Dissipative Geometric Framework for Optimization
Sparsho Chakraborty, Mohammad Alamgir, Nishanth M +3
Optimization in machine learning is usually expressed through iterative rules that update model parameters using information from the loss landscape. In this work, we study an alte…
cs.CV2026
Positive Pair Geometry Matters: Optimal Transport for Contrastive Learning of Visual Representations
Akshit Nanda, Shahzad Ahmad, Ram Prasad Padhy
Contrastive self-supervised learning has achieved strong performance by learning representations from multiple augmented views of the same image. However, most existing methods con…
physics.flu-dyn2026
Symmetry-Constrained Exact Coherent Structures in Plane Poiseuille Flow
Akshit Nanda, Ritabrata Thakur
Turbulence in wall-bounded shear flows is increasingly understood through exact coherent structures (ECS) -- invariant solutions of the Navier-Stokes equations that act as organisi…