Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Treat a scalar training control, such as task-mixture weight, weight decay, or sparsity penalty, as a parameter ramped through a sharp optimization transition. If the model starts from a highly correlated pretrained or partially trained state, compensate for the predicted marginal logarithmic memory by slowing the ramp according to a fitted logarithmic factor rather than using a pure power-law schedule.
Use a barycentric rational activation or filter whose interpolation nodes are periodically zoomed into the range of preactivations or eigenvalues actually encountered by the network. Protect the layer from catastrophic poles by monitoring the associated generalized eigenproblem and penalizing poles close to the active input interval. This targets rational networks whose expressivity comes from localized poles but whose training is destabilized by denominator zeros.
For a recurrent, state-space, implicit, or complex-valued neural network, partition the local input-output Jacobian into amplitude and phase channels and penalize excessive sensitivity in either channel. This transfers the paper's voltage-source stiffness mechanism to feature magnitude and phase, producing a stability monitor that can distinguish harmless amplitude sensitivity from destructive phase rotation.
Construct a block of gradient, preconditioned-gradient, or Hessian-vector-product directions without performing full-dimensional Gram-Schmidt. Use a random sketch to orthogonalize the block cheaply, then solve a small generalized eigenproblem using the true parameter-space overlap matrix so the extracted curvature modes are accurate for the generated subspace. Use the selected curvature modes to form a damped or trust-region optimizer step.
Use the complex-conjugate palindromic coefficient that cancels the leading temporal phase defect of oscillatory modes. Implement complex arithmetic directly or use an exactly equivalent doubled-real state, then project the final state to its real component for real-valued prediction tasks.