Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Replace a fixed momentum and learning-rate schedule with a batch-aware stability controller derived from the paper's critical-learning-rate scalings. Polyak learning rates should scale approximately with B(1-rho), whereas Nesterov learning rates can scale as B^beta(1-rho) until reaching the base stability ceiling; this may allow larger batches without crossing the instability boundary.
Use a local chaining complexity computed from an empirical input metric to predict stochastic output error for each individual input. Easy, locally concentrated inputs can use fewer dropout, ensemble, or diffusion samples, while high-complexity inputs receive additional computation; unlike a global confidence threshold, the allocation varies with the input.
Attach a calibrated risk monitor to intermediate diffusion states and terminate mutations that are likely to violate hard architecture or performance constraints before full decoding and training. This transfers the paper's separation between proposal generation and authoritative external evaluation into an early-stopping controller for expensive neural architecture trials.
Replace a globally chosen constant learning rate with a blockwise rate calibrated to the local flatness exponent of the objective. If the local Hessian decays like \(\|x-x_\star\|^{m-2}\), choose the rate so that the predicted stationary parameter radius \(\alpha^{1/m}\) matches a prescribed exploration or optimization radius, rather than incorrectly using the quadratic rule \(\sqrt{\alpha}\).
Construct a sparse attention layer by sampling backward token histories as a continuous-time branching process rather than allowing every query to attend to every key. Each active ancestor either dies or branches into a bounded number of candidate ancestors, with branching probability controlled by a small parameter. The branch-out penalty predicts exponentially small probability of long, highly branching histories, providing a direct knob for receptive-field size and attention FLOPs.
Use an online estimate of the target distribution's remaining coordinate dependence to choose diffusion step sizes instead of using a uniform timestep grid. Take large jumps when the current state is nearly coordinate-factorized and shorten the step when the denoiser detects strong cross-coordinate dependence, targeting the paper's dependence-adaptive discretization scaling.
Replace iid dropout or iid activation noise on spatial tokens with fluctuations generated by a conserved diffusing density. Each token receives a positive mass variable whose total mass is preserved, while Poissonian stochastic flux produces correlated perturbations that explore coherent local patterns rather than independently corrupting every feature. The density is autonomous and detached from autograd, so the regularizer adds little computational overhead.
Replace a flat stochastic MoE router by a two-level continuous-time routing model: experts within a group communicate rapidly, while transitions between groups occur slowly. Use the effective class-level stationary distribution as a soft load-balancing prior, reducing routing oscillation while preserving expert specialization.