Solves: Speedup

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

644 ideas found

Unverified 2026

Independent-Simplex Hypergraph Router

Use the paper's edge-to-area incidence structure to choose a small set of geometrically independent simplices instead of processing every possible hyperedge. A greedy rank-increasing router retains a triangle only when its Jacobian adds a new direction, reducing higher-order message-passing cost while preserving diverse geometric information.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: On volume vectors determined by hypergraphs in thin subsets of Euclidean space arXiv:2607.00153
Unverified 2026

Inexact High-Order Moreau DC Optimizer

Represent a parameter objective locally as a difference of convex terms, compute approximate proximal points for both terms, and update parameters using the difference of their high-order Moreau-envelope gradients rather than the raw DC gradient. Start with the quadratic case p=2, then test p=4 as a sharper penalty for large proximal residuals; solve each proximal subproblem with a small fixed number of inner steps and decrease the smoothing scale during training.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Difference-of-Convex Optimization via Inexact Smoothing Descent Methods: Difference of High-Order Moreau Envelopes arXiv:2606.30991
Mechanism works 2026

Modular collision-free sparse attention

Replace dense attention between grid-arranged tokens by a deterministic block-sparse pattern generated from modular permutations. In each block, connect row token i to column token p(i)=2i modulo B; because i, i-p(i), and i+p(i) are injective modulo B when gcd(B,6)=1, the pattern avoids repeated horizontal, vertical, and diagonal projections. Use shifted permutations across heads to increase receptive-field coverage while retaining structured sparsity.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: Closing the gap and settling the problem of queens on an $n\times n$ board, each attacking at most one other arXiv:2608.27432
Unverified 2026

KL-Budgeted Poisson-Race Sampling

Replace repeated rejection sampling from a neural proposal P with a Poisson race that selects one proposal candidate with exactly the target distribution Q. Candidate i receives a Poisson arrival time A_i and race score A_i divided by Q(X_i)/P(X_i); the smallest score wins. When Q is close to P in KL divergence, the selected index has low expected logarithmic rank, providing an adaptive compute budget instead of a fixed number of candidates.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: A note on shifting distributions via Poisson races arXiv:2608.26996
Mechanism failed 2026

Secant-Calibrated lp Optimizer

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.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Optimal Parameter-Free Gradient Minimization in $\ell_p$ Geometry arXiv:2608.26688
Unverified 2026

Regret-Balanced Adaptive Context

Choose the retained context length by balancing the statistical complexity of adding lag j against the squared prediction bias from discarding it. Unlike a fixed context window, the rule uses both the remaining-horizon spectrum and the estimated tail energy, allowing a model to expand or shrink its memory online.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Sharp Minimax Regret for Infinite-Memory Logistic Prediction arXiv:2608.26515
Audited (legacy) 2026

Entropy-Budgeted Contiguous KV Pooling

Use the attention probability distribution over an ordered context to choose contiguous token groups whose pooled attention masses have entropy as close as possible to a prescribed upper budget R. Replace the corresponding key/value vectors by one weighted representative per group, preserving token order and reducing the KV-cache length from n to m. Unlike unconstrained token merging, the entropy constraint gives a direct control knob over how concentrated or diffuse the retained attention…

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Constrained Maximum Entropy Contiguous Aggregations arXiv:2608.25533
Unverified 2026

Biclique-free hierarchical attention

Replace dense token-to-token attention by a learned binary relation generated from a small number of hierarchical predicates, while rejecting masks that contain a fixed K_{t,t} biclique. The paper's incidence bound predicts near-linear active edges for these structured relations, giving sparse attention with a measurable worst-case complexity target rather than relying only on average sparsity.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: Almost-linear Zarankiewicz bounds in $1$-semi-equational theories arXiv:2608.25464
Unverified 2026

Cycle-Aware Heavy-Ball Safeguard

Use the paper's heavy-ball recursion as a runtime diagnostic for momentum optimizers. Detect when recent parameter differences form an approximately periodic orbit or when the estimated local two-step transition matrix has spectral radius near or above one, then reduce the learning rate and momentum temporarily. This targets the failure mode proved in the paper: fixed momentum parameters can produce attracting cycles even on smooth potentials with bounded curvature.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Provable Non-Acceleration of Standard Strang Splittings of Kinetic Langevin Dynamics arXiv:2608.25279
Unverified 2026

Truncated-Fourier Domain Pooling

Replace ordinary masked mean pooling with a Fourier-compressed quadrature operator for arbitrary two-dimensional or three-dimensional domains. The geometry is preprocessed once into reusable grid weights, allowing every channel and every training example using the same domain to be pooled without boundary-area bias.

Useful6/10
Difficulty3/10
Novelty7/10
Paper: "Truncated Fourier Filtering" method for fast and high-order evaluation of integrals and convolutions in general domains arXiv:2608.25264
Unverified 2026

Sparse Multiscale Kernel-Frame Operator

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.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: The Frame Kernel Method for Multiscale Operator Learning arXiv:2608.25084
Unverified 2026

Exact energy-preserving activation subsampling

Use the weighted quadrature identity as a training or inference constraint for a compressed activation path: retain only a minimal set of binary evaluations and compute normalization or residual-energy statistics exactly on the modeled Rademacher component. This provides a zero-variance alternative to random activation subsampling for the represented subspace.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: On exact discretization of the $L_2$-norm in the space spanned by the first $N$ Rademacher functions arXiv:2608.25058
Unverified 2026

Finite-Splitting Directional Attention

Construct a directional attention head whose admissible slopes are leaves of an M-adic interval tree with a prescribed finite splitting number. Instead of evaluating all K directions independently at every spatial location, route each query through only the branch decisions of the tree and share feature projections among directions that remain in the same multiscale angular interval.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Directional maximal operators in the plane arXiv:2608.23871
Unverified 2026

Spectral Lookahead Gate

Add a cheap spectral gate to a state-space model or recurrent event detector that decides whether multi-step lookahead can change the threshold decision. If the learned threshold readout is approximately a nonnegative left eigenvector of the transition matrix, use the current state only; otherwise activate predictive heads and search over a small horizon. This avoids unnecessary rollout computation while preserving early-warning behavior in oscillatory or rotating dynamics.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: React or Predict? A Spectral Rule for Wireless Threshold Detection arXiv:2608.22900
Unverified 2026

Jacobian-aligned infill for black-box neural tuning

Add a geometry-guided infill operator to a population optimizer used for black-box neural-network tuning. Fit a local Jacobian from recent parameter perturbations and validation-residual vectors, generate a damped Gauss-Newton candidate for exploitation, and sample exploratory candidates in the same Jacobian-derived metric. The host optimizer retains selection, population survival, covariance adaptation, and its total evaluation budget; only a configurable fraction of new candidates is replaced…

Useful6/10
Difficulty5/10
Novelty7/10
Paper: JANUS: Online Jacobian-Aligned Infill for Black-Box Optimization arXiv:2608.22862
Mechanism confirmed, baseline not beaten 2026

Assignment Tree Attention

Construct a sparse attention support by solving multiple small perturbed assignment problems between query and key embeddings and taking the union of the selected optimal matchings. Use the resulting spanning tree as the only set of cross-token edges, with edge biases determined by empirical assignment frequency.

Useful6/10
Difficulty7/10
Novelty7/10
Paper: Spanning trees in the Assignment Problem: two theorems and two conjectures arXiv:2608.22308
Failed on benchmark 2026

Fourier Replay-Mode Stabilizer

Regularize a circular recurrent kernel by directly controlling the growth rate and phase velocity of its Fourier modes. This converts replay-speed selection into a low-dimensional spectral control problem and can suppress unstable or excessively slow modes without adding recurrent parameters.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Forward and reverse delay-driven hippocampal replay without symmetric plasticity arXiv:2608.21814
Mechanism failed 2026

Spectral-Pole-Tuned Decentralized Optimizer

Choose the consensus gain and gradient-tracking gain in decentralized training from the communication Laplacian spectrum rather than tuning them independently. The gains minimize the worst asymptotic pole radius for the paper's exact quadratic model, providing a principled initialization and a conservative stability safeguard for neural-network optimization.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: Optimal Parameter Design for DIGing on Minimizing Unweighted Sum of Squares arXiv:2607.25463
Unverified 2026

Strongly-regular sparse attention

Use the adjacency matrix of a vertex-transitive strongly regular graph as a fixed sparse attention or token-mixing mask. Every vertex has the same degree, and every pair of vertices has exactly one of two common-neighbor counts, giving predictable two-hop coverage and avoiding the degree and connectivity irregularities of random sparsification.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Vertex-transitive strongly regular graphs in the switching class of doubly transitive two-graphs arXiv:2608.30330
Unverified 2026

Rank-Budgeted Facial Reduction for Binary SDP Layers

Use the constraint matrix rank and nullity to set an explicit upper bound on the number of facial-reduction phases in an SDP layer representing structured binary decisions. Apply those phases before the main primal-dual solve, stopping after the rank–nullity budget and using the reduced face for all subsequent forward and backward computations.

Useful5/10
Difficulty7/10
Novelty8/10
Paper: Sharp Singularity-Degree Bounds for Equality-Generated SDP-RLT Relaxations of Binary Programs arXiv:2608.29945
Unverified 2026

Review-Period Phase Diagram for Frozen Updates

Treat the number K of minibatches between expensive control updates as a review period: the controlled neural dynamics use parameters or decisions computed at time nK and hold them fixed until (n+1)K. Scan K, estimate first and second finite differences of validation loss or episodic return, and use the resulting nonmonotone-to-convex or concave phase diagram to select an update frequency rather than assuming that more frequent updates are always better.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Review-Period Sensitivity in Multiclass Queue Scheduling arXiv:2608.29398
Unverified 2026

Braid-word reversible mixer

Replace a dense token- or channel-mixing matrix with a product of local braid generators acting on adjacent coordinates. Each generator is an exactly invertible 2-by-2 transformation, while the braid and far-commutativity identities give multiple equivalent factorizations of the same global operator. This creates a sparse, reversible mixer with O(kn) cost for a braid word of length k, rather than O(n^2) cost for a dense matrix.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Fox $p$-Colorings as Fixed Points of Braid Representations arXiv:2608.29046
Unverified 2026

Banded Production-Matrix Polynomial Layer

Replace a dense learned polynomial-feature transform with a d-orthogonal recurrence whose production matrix is constrained to a (d+2)-banded lower-Hessenberg form. The layer generates successive features using only local recurrence coefficients, giving O(dN) arithmetic and O(dN) parameters for N basis functions instead of O(N^2) dense mixing.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Riordan array representation of recursive polynomial sequences, orthogonal polynomial sequences, and $d$-orthogonal polynomial sequences arXiv:2608.28834
Unverified 2026

Correlation-Window Training Regime Detector

Monitor short histories from distributed training replicas and detect whether their fluctuations are independent or synchronized using pairwise correlations. Use the detected regime to switch learning rate, gradient accumulation, or communication policy: synchronized high-variance episodes can receive a smaller step, while independent episodes can use more aggressive updates. The detector intentionally uses pairwise correlation features instead of a raw-waveform neural classifier, making it…

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Real-Time Edge-based Detection of Correlated AI Data-Center Load Episodes arXiv:2608.22719