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 Cox-de Boor evaluation of each cubic B-spline edge activation with its fixed truncated-power expansion. Normalize each scalar edge input to a bounded knot coordinate, evaluate the five shifted cubic positive-part terms in parallel, and contract them with the learned spline coefficients inside one fused kernel.
Replace a first-order optimizer update by an extrapolation point followed by one damped Newton or Newton-CG solve, while selecting the acceleration weight from an explicit cubic Hessian-Lipschitz budget. Use a displacement-based safeguard in place of the unavailable distance to the optimum, turning the proof condition into a practical trust-region-like rule that limits unstable momentum.
Train a primal state network and a dual flux network jointly, using the convex primal-dual gap as the main loss and as an a posteriori certificate of state error. Unlike a strong residual, the certificate is based on monotonicity and convex duality, so it can remain informative even when differentiating rapidly oscillatory coefficients would amplify noise by $1/\varepsilon$.
Replace a full neural-network Gauss–Newton solve with a damped solve in an adaptively constructed low-dimensional parameter subspace. The subspace contains the current gradient, recent accepted updates, Krylov curvature directions, and randomized Jacobian-curvature probes, and is enlarged whenever its projected gradient fails to capture enough descent information.
Replace an unconstrained continuous-depth neural update with a constrained implicit Runge–Kutta step whose internal stages and final state are required to remain in a convex feasible set. For box-constrained latent states, this prevents exploding or negative states while retaining the high-order structure of Radau or Gauss integration and avoiding the order-destroying behavior of post-step clipping.
Replace a trainable shallow MLP hidden layer by a frozen bank of smooth sigmoid ridge functions and train only a linear output head. Choose the feature count and parameter sampling regime using the theorem's explicit dependence on input dimension d, target regularity k, evaluation norm m, and confidence delta. The construction is especially appropriate for smooth regression, scientific surrogate models, and PINNs, where derivatives of the network output are part of the loss.
Replace Lorentz-hyperboloid tensors with proper-velocity tensors whose spatial coordinates can be transformed by standard Euclidean affine layers and activations. Reconstruct the Lorentz time coordinate only at manifold boundaries, preserving the hyperbolic representation while avoiding repeated projection, normalization, or fragile exponential-map calculations.
Use Adam normally, but periodically estimate the spectrum of the Adam-preconditioned Hessian and add a damped low-rank Newton correction when the preconditioned curvature is strongly ill-conditioned or the gradient is concentrated in flat directions. The correction is computed only in a small Lanczos subspace, so the method targets cross-coupled ill-conditioning without materializing or inverting the full Hessian.
Replace a large dense layer whose input and output dimensions factor into multiple modes by a TT-matrix whose parameters are stored as a chain of small cores. Periodically apply TT-SVD rounding to remove weak singular directions and keep the representation within a prescribed approximation error. This transfers the paper's central computational principle—perform tensor-product contractions directly in compressed form—to neural network layers.
Replace an unpreconditioned conjugate-gradient solve for a damped Gauss–Newton step with a two-level algebraic preconditioner derived from local Jacobian-row supports. Use overlapping local parameter blocks as Schwarz subdomains and a coarse basis containing low-energy local modes, so the optimizer can correct both localized and globally coupled parameter errors.
Replace a dense weight matrix by a cross approximation built from selected rows and columns rather than by a conventional truncated SVD. Periodically refresh the selected indices using residual leverage scores, warm-starting from the previous factorization so that the compressed layer can track weight changes during fine-tuning.
Represent every mesh interface degree of freedom by one feature copy per incident cell, and apply local neural blocks directly to these cell tensors. Enforce inter-cell consistency with valence-weighted averaging only after selected layers or hierarchy transitions, avoiding repeated construction of a global sparse graph or assembled feature vector. This is suited to adaptive quadtrees, octrees, and finite-element neural operators.
Bootstrap the optimizer curvature scale from a deliberately nondegenerate pair of gradient queries, then perform steepest descent in lp geometry with a local secant backtracking rule. The method does not require a supplied learning rate, smoothness constant L, initial distance R, or optimum value f*, and it automatically uses the dual norm associated with p.
Replace scalar neural activations by pairs of nonnegative channels whose ratio represents the signed or unsigned activation. Implement multiplication and addition through pair algebra, and renormalize each pair because the representation is invariant under multiplying both rails by the same positive scalar. This creates an explicitly bounded, cancellation-aware arithmetic layer for deep multiplicative MLPs, rational networks, and neural fields.
Replace dense grid tokens or global spectral features with coefficients of compactly supported kernels centered on a nested hierarchy of spatial points. Encode an input field into coarse-to-fine coefficients, apply a neural map to those coefficients, and decode the predicted coefficients at arbitrary query locations; the contribution from each level provides an explicit multiscale output decomposition.