Solves: Training

Machine-learning ideas tagged Training in the Solves taxonomy of the Math2NN corpus.

2 ideas found

Unverified 2026

Boundary-normal trust-region flow

Replace the assumption that strong convexity keeps optimization inside a valid parameter chart with an explicit viability condition on the chart boundary. For Lie-group neural-network parameters or bounded latent coordinates, modify each update so its velocity has nonpositive outward radial component, using either a radial barrier or projection onto the tangent cone.

Useful6/10

Difficulty4/10

Novelty6/10

Dynamics Stability Training Optimizer

Paper: Geodesic strong convexity does not imply forward invariance under gradient flow on SO(3): a certified counterexample arXiv:2608.28976

Unverified 2026

Perturbation-Resilient Relaxed Projection Stack

Use relaxed affine-projection layers as a stable iterative stack with an explicit perturbation monitor. The monitor estimates approximation error from quantization, dropout, stochastic evaluation, or low-rank projection and reduces the relaxation parameter when accumulated perturbations become large.

Useful5/10

Difficulty4/10

Novelty7/10

Training Stability Training Generalization

Paper: On the boundedness of infinite products of relaxed projections: perturbations resilience and dynamic string-averaging arXiv:2607.25797