Literature on Projection based learning
(a) Minimization by gradient descent θk+1 = θk − η∇L(θk)
(b) Feasibility by alternating projections zk+1 = P2(P1(zk))
- Learning without loss (LWL)
- Nonconvex projections arising in bilinear mathematical models
- Machine-learnable Sets
Software extensions of LWL framework (AI assisted)
- Projection-based learning, What is it, and why does it matter? (2024).
- A projection-based framework for gradient-free and parallel learning (2025). ◦ Empirics on Shakespeare dataset.
- Narrowing the Gap Between Projection and Gradient–Based Learning (2026). ◦ Empirics on CIFAR 10 with cyclic projections.
◦ Unique contribution