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 fixed optimizer memory order with a nested family of gradient-integral controllers. Training begins with a first-order update and activates additional accumulated-gradient states only after an exponentially smoothed residual fails to decrease for several decision intervals; newly activated gains are ramped from zero, so the parameter update remains continuous and previously learned states are preserved. The optimizer should use little memory on easy problems and acquire longer memory…
Introduce an effective learning-rate, gain, or regularization parameter that follows the commanded target with a finite implementation rate, and compensate for its predictable threshold-crossing lag. The scheduler estimates the network's current spectral instability boundary and commands the target parameter to cross that boundary early enough that the effective parameter crosses it at the desired time, avoiding overshoot caused by optimizer or hardware smoothing.
Construct a residual network from independently attachable modules, but permit only a number of modules whose aggregate feedback gain lies inside a delay-dependent admissible interval. Estimate deployed end-to-end latency and each module's local Jacobian gain, then reject or bypass additional modules when the predicted delayed-loop stability boundary is crossed. This turns variable-width or depth scaling into a falsifiable control problem rather than an empirical choice.
Replace the dense hidden-state trajectory of a continuous-depth or recurrent neural block by a rank-r factorization F(t) = X(t) S(t) V(t)^T, and evolve the factors with a reversible projector-splitting integrator. During backpropagation, reconstruct earlier hidden states by reversing the factor updates rather than storing all activations.
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.
Turn an iterative optimization or equilibrium computation inside a neural network into a differentiable layer whose backward pass solves the implicit adjoint system with conjugate gradients or GMRES using only automatic-differentiation matrix-vector products. This avoids storing unrolled iterations and avoids explicit Hessian or Jacobian construction, enabling longer solver horizons and lower-memory implicit architectures.
Replace Euler-Maruyama in a reverse diffusion sampler with an interval transition that freezes the neural posterior-mean prediction but integrates the known linear drift and Gaussian noise exactly. The resulting exponential integrator should tolerate larger timesteps, particularly when the reverse dynamics are stiff in high-noise or strongly anisotropic directions.
Replace unrolled autodiff through an ordered block-implicit neural layer with a custom reverse sweep that solves one small transposed local system per forward block update. The backward computes the exact gradient of the executed finite-depth solver while avoiding a global Jacobian and retaining only compact block information.
Use a second-order Runge-Kutta integrator satisfying the chain-tree condition b^T A c = 1/6 when the neural ODE output is an event threshold or separatrix crossing. The method remains only second order for general trajectories, but the paper predicts cancellation of the leading discretization bias in this nonlinear observable, potentially allowing larger inference steps at fixed threshold accuracy.
Use a full primal-dual optimization solve in the forward pass, but backpropagate only through the last r iterations starting from a detached warm-start iterate. This avoids storing the full solver trajectory while preserving the forward solution, and provides a tunable bias-versus-memory tradeoff: r=0 is a cheap surrogate gradient, while increasing r should converge toward the implicit equilibrium gradient.
Train a neural model through a sequence of progressively harder objectives, analogous to descending temperature from the exactly solvable infinite-temperature heat kernel. At stage k, initialize from the parameters learned at the previous stage and increase the continuation parameter only when the current residual and sampling diagnostics are stable. This should reduce optimization shocks and avoid repeatedly entering poor basins.
Build a forward-mode second-order jet interpreter for the PINN and evaluate the entire PDE residual in one compiled graph. Each intermediate carries its value, first derivative, and Hessian with respect to the collocation coordinates, avoiding repeated nested reverse-mode autodiff calls for every residual component.
Replace the uniform or power-law convolution in a recurrent or state-space layer by a Gaussian q-binomial fractional kernel with learnable order alpha and deformation q. The parameter q controls a concrete memory-localization transition: q close to 1 gives classical fractional power-law memory, whereas q<1 produces exponentially localized memory and should reduce long-horizon gradient interference and truncation cost.
Train a neural trial function for an elliptic PDE using a very-weak residual in which all derivatives act on fixed smooth test functions rather than on the neural network. This eliminates second-order reverse-mode or forward-mode automatic differentiation and allows low-regularity activations while retaining a least-squares objective over many test functions.
Replace uniform collocation for a fixed random-feature neural PDE solver with sampling from the leverage-score density of the operator-applied features. Whiten the retained residual feature space before solving for output coefficients, so the sampled least-squares matrix has an identity-like expected Gram rather than inheriting severe anisotropy from the differential operator. The same construction can be used for a linearized neural network by treating Jacobian features as the trial functions.
Replace an unconstrained Neural ODE vector field with nonnegative production and destruction networks and discretize the resulting dynamics by an NSFD rational update. The update remains nonnegative for every step size, allowing stable coarse-step training and inference without clipping, projection, or tiny adaptive solver steps.
Replace the standard CFG guidance multiplier in each DDIM step by a coefficient obtained from the terminal guided exponent. Given unconditional and conditional denoiser-derived states D_u and D_c, use r^{1+w}-r instead of w(r-1) on the guidance direction D_u-D_c; this preserves the same two denoiser calls and costs no additional NFE while suppressing low-noise residual blow-up at high guidance.
Replace the standard squared pointwise PDE residual in an elliptic PINN by its discrete $H^{-1}$ norm. The residual is passed through an inverse Dirichlet Laplacian, reducing the dominance of rapidly varying residual modes and acting as a mathematically specified preconditioner for the PINN training gradients.
Replace the final sequence of diffusion-sampler steps below a positive switching noise scale a with a single analytic normal-mode completion map. Run the existing solver only on [a, sigma_max], then use the denoiser at scale a to extrapolate to the requested terminal floor epsilon. This prevents the step count from growing like log(sigma_max/epsilon) and should preserve the base solver's order when a is coupled to the discretization size.
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.
Run an adaptive neural ODE solver once to determine accepted step sizes, then train using a regular fixed-length replay of those steps rather than differentiating through adaptive accept/reject logic. The replay can be fused across a batch of trajectories and differentiated with an ordinary reverse sweep, giving the exact discrete gradient of the replayed solver and predictable GPU work.
Replace random Fourier or random NTK features by a weighted deterministic quadrature rule for the kernel's feature integral. The resulting feature map uses the same linear-model interface as random features but can approximate the leading Gram-matrix eigenvalues substantially better at the same feature count, improving conditioning and reducing the width required for a target kernel approximation.
Replace the raw HJB residual loss of a neural PDE solver with a parametrix-preconditioned fixed-point target. At each local space-time patch, analytically propagate terminal values and source terms through a Gaussian kernel whose covariance uses a frozen diffusion matrix, while asking the network to learn only the variable-coefficient correction. This should reduce the burden on the network to represent stiff high-frequency diffusion dynamics and improve short-horizon convergence.