Solves: Accuracy

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

2078 ideas found

Unverified 2026

High-girth Bethe assignment layer

Replace independent softmax routing or attention normalization with a differentiable approximate distribution over one-to-one assignments, using the Bethe permanent as the partition-function surrogate. Constrain the allowed token-to-expert or query-to-key support graph to have high girth, which gives an explicit bound on the approximation error and reduces short-cycle-induced correlations.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: Optimal girth-dependent bounds for the Bethe approximation of the permanent arXiv:2609.02017
Unverified 2026

Noise-Induced Compact-Support Neural Field

Replace ordinary dropout or soft sparsity penalties on a nonnegative spatial or token activation field with sublinear multiplicative stochastic dynamics. The field receives local diffusion or graph smoothing, while noise amplitude u^gamma vanishes at zero but is relatively strong near zero; this creates an absorbing zero state and may produce exact contiguous inactive regions. The module is suitable for feature maps, graph-node fields, token routing scores, or continuous neural operators.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Instantaneous shrinking of supports for stochastic PDEs arXiv:2609.01984
Unverified 2026

Bernstein Bounded Implicit Representation

Parameterize a scalar or vector implicit neural field on each spatial cell with Bernstein polynomials and constrain its coefficients instead of sampling many points to enforce output bounds. The Bernstein convex-hull property gives a deterministic pointwise bound everywhere in the cell, making the method useful for neural fields representing densities, concentrations, masks, or material parameters.

Useful6/10
Difficulty4/10
Novelty7/10
Paper: Bounds-Constrained Finite Element Approximation of Time-Dependent Partial Differential Equations arXiv:2609.01915
Unverified 2026

Asymmetric Conservative Interaction Layer

Build a neural interaction layer for multiple populations whose cross-population kernels are ordered, so the response of population s to population t need not equal the response of t to s. Evaluate the interaction in divergence form and apply an explicit moment-nullspace projection so each layer preserves total mass, momentum, and energy instead of learning these constraints from penalties.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Learning a general class of admissible multi-species collision operators from molecular dynamics arXiv:2609.01845
Unverified 2026

Early-EM KL Router

Replace direct optimization of noisy simplex-valued mixture or MoE gate weights with a fixed number of EM responsibility updates. The finite iteration count acts as an implicit reverse-KL regularizer toward the uniform gate distribution, preserving low-frequency experts without selecting an arbitrary entropy coefficient.

Useful6/10
Difficulty4/10
Novelty4/10
Paper: On the discretization of the object space in inverse problems with application to cryo-electron microscopy arXiv:2609.01688
Unverified 2026

Graphic-Minor Diversity Regularizer

Use signed spanning-forest minor numerators to encourage a graph-structured neural layer to preserve independent multi-coordinate responses instead of collapsing several outputs onto the same direction. The determinant coefficients are only 0 or ±1, making the regularizer combinatorial and sign-exact rather than a noisy learned determinant surrogate.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: All-Minors Matrix-Tree Theory for Superport Networks: Completed Quotient-Incidence Determinants and Conductance-Weighted Subdivision Extensions arXiv:2609.01672
Unverified 2026

Learning-Coefficient Architecture Selection

Replace parameter-count or validation-loss-only model selection with a singular-complexity score based on the evidence scaling of each candidate neural network. Select or prune architectures using \(n\widehat L_n+\widehat\lambda\log n-(\widehat m-1)\log\log n\), which can prefer overparameterized but highly redundant networks when their effective singular complexity is lower.

Useful6/10
Difficulty7/10
Novelty6/10
Paper: Solomonoff Induction and Singular Integrals arXiv:2609.01666
Unverified 2026

Quantum-Expander Covariance Mixer

Insert a fixed expander channel before a covariance-dependent feature transformation. The channel repeatedly conjugates the feature covariance by a constant number of sparse Pauli/CNOT unitaries, preserving total feature energy while contracting anisotropic covariance components. Use the mixed covariance for whitening or as a regularized normalization statistic, and test whether it gives more stable training than dense whitening or an explicit isotropy penalty.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Depth-1 expanders on the unitary group and applications arXiv:2609.01605
Unverified 2026

Local-complexity adaptive gradient clipping

Replace one global gradient-clipping threshold with an example- or parameter-block-specific threshold derived from the local metric complexity of its stochastic gradient process. High-complexity examples receive stronger clipping or downweighting, while locally simple examples retain more of their useful gradient signal.

Useful6/10
Difficulty6/10
Novelty5/10
Paper: Pointwise Majorization for sub-Weibull and Mixed Tail Processes with Applications in Quadratic Chaos and Ergodic Diffusions arXiv:2609.01576
Unverified 2026

Lax–Oleinik Aubry contact probe

Use the discrepancy between a learned potential and its long-time backward Lax–Oleinik evolution to identify dynamically critical states. Persistent near-contact points are candidates for the Aubry set and can guide adaptive collocation, while states with large gaps can receive fewer training samples.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: $L^\infty$ Variational Approximation of the Aubry Set arXiv:2609.01557
Unverified 2026

Soft-supremum weak-KAM loss

Train a neural periodic potential to minimize an exponential variational functional rather than a mean-squared Hamilton–Jacobi residual. Increasing the inverse-temperature parameter concentrates optimization on the worst violating locations, encouraging a learned critical subsolution whose equality set represents dynamically important regions.

Useful6/10
Difficulty3/10
Novelty5/10
Paper: $L^\infty$ Variational Approximation of the Aubry Set arXiv:2609.01557
Unverified 2026

Decision-Dependent Robustness Cutting Planes

Replace ordinary adversarial training over a fixed perturbation set with adaptive robust training in which the admissible perturbations depend on the current network state. Train on a small active set of hard scenarios, then search for a newly admissible scenario with larger loss or constraint violation and add it only when needed. This should reduce redundant adversarial examples while targeting worst-case regions induced by the current model.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Generalized Semi-Infinite Programming for Robust Optimal Control with Decision-Dependent Uncertainty arXiv:2609.01538
Unverified 2026

Zeta spectral monitor for recurrent training

Use the determinant and trace-power identities of the rules matrix as a spectral diagnostic for recurrent or state-space training. Penalize unstable or excessively resonant modes through a truncated log-zeta objective, while retaining selected eigenvalues near the unit circle when long memory is desired. This gives a falsifiable transition criterion based on closed-walk growth rather than only gradient norms.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: The Quadratic Easy Coefficients Conjecture via Finite-Type Shifts and Zeta Functions arXiv:2609.01399
Unverified 2026

Signed de Bruijn parity memory

Augment an RNN or state-space model with a finite-state binary-context module whose transitions are those of a de Bruijn graph, while a signed transition channel records a quadratic parity function of the recent context. The exact finite-memory branch preserves cancellation-sensitive parity features that a continuous hidden state may forget, and a learned readout can combine it with the ordinary neural state.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: The Quadratic Easy Coefficients Conjecture via Finite-Type Shifts and Zeta Functions arXiv:2609.01399
Unverified 2026

Sparse-Cost Temperature Calibration

Use a small set of known or trusted pairwise costs to estimate the effective entropic temperature of a Sinkhorn attention or mixture-of-experts routing layer directly from its observed transport plan. This provides a calibration controller that can detect over-concentrated routing and adjust epsilon without backpropagating through a costly temperature search.

Useful6/10
Difficulty4/10
Novelty8/10
Paper: An exact and fast solution of the inverse Regularized Optimal Transport problem arXiv:2609.01278
Unverified 2026

Random-Travel-Time Temporal Layer

Replace the fixed delay in a temporal layer with a distribution of physically structured delays induced by uncertain transport velocity. The layer aggregates features arriving at several travel times and can use the deterministic mean-velocity path during most training steps, periodically correcting it with stochastic samples.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Optimal Inflow Control for Transport Equations with Uncertain Velocities and Demand arXiv:2609.01291
Unverified 2026

Branched Rough Residual Block

Replace a standard recurrent or neural-CDE Euler transition with a second-order rough transition that receives both first-order increments of the input path and learned second-order branched increments. Unlike a geometric signature block, the second-order coefficients are independent learned maps rather than being forced to equal derivatives or shuffle-symmetric combinations of first-order vector fields, allowing the model to represent order-sensitive and non-geometric interactions in irregular…

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Rough differential equations on manifolds via natural bundles arXiv:2609.01190
Unverified 2026

Marginal Fractional Coupling Layer

Replace a local smoothness penalty or local state transition along a sequence or depth coordinate by a marginal fractional quadratic energy with Fourier multiplier |k|. The sigma=1 kernel is nonlocal and scale-free, so it can preserve long-range correlations while suppressing high-frequency instability more selectively than an ordinary Laplacian penalty.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: BKT-like Correlation Scaling and Twist Responses in a One-Dimensional Fractional $U(1)$ Ginzburg--Landau Model arXiv:2609.00721
Unverified 2026

Fractional Ellipsoidal Sparse Attention

Replace dense attention weights with a compactly supported anisotropic bump derived from the obstacle solution, using one learnable ellipsoid per attention head or feature group. Tokens outside the learned ellipsoid receive exactly zero weight, while tokens inside receive smoothly decaying weights according to a fractional exponent. The learned positive-definite matrix represents orientation, scale, and correlations between feature dimensions.

Useful6/10
Difficulty6/10
Novelty5/10
Paper: Ellipsoidal Positivity Sets for Fractional Obstacle Problems with Quadratic Forcing arXiv:2609.00703
Unverified 2026

Besov spectral regularization for shallow ReLU

Add a multiscale Besov penalty to the output of a shallow ReLU^k network, targeting the smoothness threshold that the paper proves is sufficient for finite ridge-variation representation. This suppresses pathological high-frequency output while preserving low-frequency approximation, providing a principled alternative to ordinary parameter weight decay.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: Sharp embeddings between quasi-Banach Besov spaces and shallow ReLU variation spaces arXiv:2609.00680
Unverified 2026

Empirical Preimage-Entropy Regularization

Apply the paper's empirical preimage-entropy construction to a learned recurrent transition map, penalizing excessive distinguishable hidden-state histories that produce the same current state while preserving multiple histories when the task requires genuine multimodality. Unlike a raw inverse-Jacobian penalty, the regularizer is computed only among inverse trajectories having similar empirical state distributions, so it distinguishes useful multimodal memory from uncontrolled branch explosion.

Useful6/10
Difficulty7/10
Novelty9/10
Paper: Empirical variational principles for preimage entropies arXiv:2609.00655
Unverified 2026

Gap-Continuation KKT Meta-Layer

Replace an unrolled constrained inner optimization in a meta-learning or hyperparameter-learning system with a KKT-based single-level layer. Instead of imposing primal-dual complementarity exactly from the first iteration, solve a sequence of relaxed problems with decreasing complementarity tolerances, making early optimization smoother and reducing failures caused by degenerate active-set geometry.

Useful6/10
Difficulty6/10
Novelty4/10
Paper: Disciplined Bilevel Programming arXiv:2609.00644
Unverified 2026

Reciprocal Beta-Angle Mixer

Insert a projection-space mixer that combines several fixed or learned directions using reciprocal correlations with the current feature, then normalize the result. The exact construction has a universal beta law for its squared input-output cosine, so it can create controlled angular diversity while remaining deterministic and independent of the chosen direction dictionary.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Universal Beta Incidence Angles: Cauchy Rigidity and Infinite Arrangements arXiv:2609.00603
Unverified 2026

Sparse Legendre Shape Hypernetwork

Use a sparse multivariate Legendre expansion as the geometry-to-network-weights map, rather than an unconstrained MLP that consumes all shape parameters. The hypernetwork predicts only coefficients for a selected set of polynomial multi-indices, allowing high-dimensional or countably parameterized shape uncertainty to be handled with a number of learned terms determined by coefficient decay rather than ambient dimension.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Shape Holomorphy and Sparse Approximation of the Maxwell Electric Field Integral Operator arXiv:2609.00466