ML: Loss

Machine-learning ideas tagged Loss in the ML taxonomy of the Math2NN corpus.

343 ideas found

Unverified 2026

Mapping-Cone Boundary Consistency Loss

Augment a neural model with a learned target differential form and a source-side correction whose compatibility is enforced by the mapping-cone differential. For a map F from M to N, train the model so that the target quantity is closed and its pullback to M is exactly the differential of the correction, providing a structured bulk-boundary consistency constraint instead of independent feature matching.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Periods, prequantization, and rigidity in relative multisymplectic geometry arXiv:2607.07149
Unverified 2026

Euler-Balance Regularizer for Binary Neural Fields

Add a global Euler-characteristic residual to a network predicting complementary phases A and B on a voxel grid or simplicial mesh. The regularizer forces predicted phase topology and separating-interface topology to satisfy the tubular-tiling balance law, helping reject geometrically plausible but topologically inconsistent segmentations. It is especially suitable when labels cover only one phase, interfaces are noisy, or the hidden complementary phase must be inferred.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Soft cells, Tubular Tilings and the Hidden Phases in Binary Mixtures arXiv:2607.06810
Unverified 2026

Annealed Infinity-Harmonic Dual Head

Add a two-channel geometric head producing scalar fields u(x) and v(x) on a two-dimensional input or latent coordinate domain. Train it initially with a moderate p-harmonic duality constraint, then anneal p upward so u approaches an infinity-harmonic field while v remains its rotated-gradient dual; this penalizes isolated steep gradient spikes and promotes smooth, coherent level sets.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Infinity-harmonic functions and inverse mean curvature flow clusters arXiv:2607.06698
Unverified 2026

Stable Magnitude Bottleneck

Insert a magnitude-only bottleneck whose output is the absolute value of a random independent-feature expansion of the latent vector. Train a decoder to reconstruct the latent representation or input modulo one global sign, while explicitly rejecting feature distributions whose normalized L1 mass is too small. The module provides a controlled way to obtain sign-invariant representations without allowing arbitrary coordinate-wise sign loss.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Stable Phase Retrieval for Spans of Independent Random Variables arXiv:2607.06693
Unverified 2026

Patterned-Walk Graph Signature

Augment a graph neural network or graph transformer with counts of cyclic walks whose successive steps are required to be graph edges or graph non-edges according to a binary pattern. These features encode induced-subgraph structure that ordinary adjacency powers miss, and can be concatenated to the graph-level token or used as an auxiliary prediction target.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Generalized spectral closedness of $\mathcal{F}$-free graph classes arXiv:2607.06455
Unverified 2026

Affine directional Sobolev regularizer

Replace the usual squared input-Jacobian penalty with a stochastic approximation of the affine Sobolev energy, which computes an inverse-power spherical average of directional derivative norms. The negative exponent emphasizes directions with unusually small sensitivity and prevents the regularizer from being represented only by the largest-gradient direction.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Stability for the Affine Sobolev Inequality and its Critical Points for $p\ge 2$ arXiv:2607.06415
Unverified 2026

Gap-Aware Hopf Stability Loss

Train a neural field to output a symmetric conformation tensor C(x) while penalizing large spatial variation whenever its leading eigenvalue approaches the second eigenvalue. The resulting loss directly targets the mechanism identified by the paper: a topological change cannot occur cheaply unless the field develops a small spectral gap or a sufficiently concentrated gradient.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Hopf Obstruction and Transported Forced Brakke Motion in Ordered Viscoelastic Cores arXiv:2607.05879
Unverified 2026

Riesz Fractional Variation Regularizer

Add a fractional oscillation penalty to scalar functions produced by a neural network on an ordered grid. Unlike a derivative penalty, this remains meaningful for nonsmooth or nowhere-differentiable outputs and interpolates between total-variation-like behavior and Sobolev-like smoothness.

Useful5/10
Difficulty3/10
Novelty6/10
Paper: A variation on the Pólya-Segő principle in one dimension arXiv:2607.03450
Unverified 2026

Smooth-Plus-Boundary-Lifting Network

Represent the prediction as a sum of a smooth interior branch and a fractional boundary branch: u_theta(x)=u_int_theta(x)+d(x)^a u_bd_theta(x). This mirrors the paper's direct-sum solution structure and allocates separate network capacity to the globally regular component and the boundary layer.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: The structure of solution spaces for fractional-order operators, with gradient estimates arXiv:2607.02312
Unverified 2026

Tree-Cone Distribution Head

Represent a neural network's categorical output over a rooted tree using cumulative probability mass on each rooted subtree. Train pairs of examples with a stochastic-dominance loss that compares these subtree masses, avoiding enumeration of all upper sets and making hierarchical monotonicity explicit. This is suitable for taxonomies, severity levels, hierarchical intents, and structured world-model states.

Useful5/10
Difficulty3/10
Novelty4/10
Paper: Characterizing finite posets whose probabilistic powerdomain are RB-domains arXiv:2607.02231
Unverified 2026

Separability-Ambiguity Regularizer

Estimate how often a representation lies on a separating hyperplane for alternative separable dichotomies, and use this quantity as a boundary-concentration penalty. Unlike a single classifier margin, the score measures whether many admissible separators consider the point ambiguous.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Function-Counting Theory for Low-Dimensional Data Structures arXiv:2607.01010
Unverified 2026

Degree-Weighted Fourier Collision Regularizer

For two monotone prediction heads receiving binary features, penalize cases where their covariance is smaller than the sharp degree-weighted collision of their Fourier spectra. This discourages uncontrolled agreement on high-order interaction patterns while preserving low-order shared structure, and can be used either as a constraint or as a diagnostic for monotone multi-task models.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: The sharp diagonal spectral correlation inequality on the discrete cube arXiv:2606.32024
Unverified 2026

Clique-density feasibility regularizer

Add a differentiable penalty to a graph generator or graph predictor when its soft higher-order clique density violates the sharp lower bound implied by its lower-order clique density. The regularizer encourages generated graphs to have mathematically consistent motif statistics without hard-discretizing the predicted adjacency matrix.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: On clique-to-clique densities arXiv:2606.31967
Unverified 2026

Layerwise linking-number topology probe

Use linking number as a diagnostic and optional regularizer for representations of paired closed data manifolds. The probe identifies layers that collapse or separate class geometry through collisions and folds, giving an architecture-selection signal beyond loss and Jacobian singular values.

Useful5/10
Difficulty7/10
Novelty8/10
Paper: Low-dimensional topology of deep neural networks arXiv:2606.31856
Unverified 2026

Certified Neural Ritz Solver

Parameterize candidate eigenfunctions with a neural network, project them into a finite spectral trial space, and compute Ritz eigenvalues from the resulting Galerkin matrices. Train against the paper's rigorous lower-bound transform rather than trusting the raw Ritz values, producing a certificate that the predicted eigenvalues do not underestimate the exact eigenvalues under the projection-error assumptions.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Guaranteed Lower Eigenvalue Bounds for Spectral Galerkin Methods with Application to Schrödinger Operators arXiv:2607.04247
Unverified 2026

Top-L subsequence-consistency training

Train a sequence encoder-decoder with an explicit list-consistency objective: after insertion or deletion corruption, require the correct prediction to remain among the top $L$ hypotheses compatible with the clean latent sequence. Instead of optimizing only one alignment, retain multiple low-cost monotone alignments or candidate latent decodings and penalize the model when the clean target falls outside this list.

Useful5/10
Difficulty6/10
Novelty5/10
Paper: The Insertion List-Decoding Capacity and an Improved Bound on the Deletion List-Decoding Capacity arXiv:2607.03989
Unverified 2026

PED finite-state graph layer

Add a finite-state message-passing layer that tracks local configurations corresponding to perfect edge domination or dominating induced matchings instead of transmitting unconstrained node embeddings alone. On graphs with a tree, series-parallel, or small-separator decomposition, the layer produces an exact or differentiable partition function over globally valid edge configurations, which can be used as node features, an auxiliary loss, or a structural prior.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Counting perfect edge dominating sets: extremal results and linear-time algorithms arXiv:2607.03894
Unverified 2026

Chi-Square-Calibrated Covariance Matching

Use the paper's asymptotic null law to decide when two minibatch covariance structures are statistically distinguishable, rather than applying a fixed covariance-matching weight throughout training. This creates a confidence-gated regularizer that is strong when discrepancies exceed sampling noise and weak when the observed difference is compatible with finite-batch variability.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Connecting Riemannian Geometry and Statistical Inference for Correlation Matrices arXiv:2608.27209
Unverified 2026

Capacitary Boundary Regularizer

Add an inverse-capacitary-distance penalty to coordinate-network outputs near complex forbidden sets, rather than using only Euclidean distance-to-boundary weighting. The penalty is theoretically compatible with the network's spatial Dirichlet energy: it suppresses large values near obstacles while the gradient penalty controls the weighted singularity, even when the obstacle is thin, perforated, or fractal-like.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Capacitary-Distance Hardy Inequality arXiv:2608.26663
Unverified 2026

Fock-Coercive Magnitude Loss for Complex Features

Parameterize a complex neural feature F(z) as a low-degree holomorphic polynomial and train it from magnitude-squared observations using a Gaussian-weighted residual to the best constant intensity baseline. The paper's coercivity inequality makes this more than an observation-space loss: small intensity variation certifiably bounds the error of the phase-invariant squared feature F^2-F(0)^2. Use the bound as a regularizer or as a replacement for an unavailable complex-target loss in…

Useful5/10
Difficulty5/10
Novelty7/10
Paper: A complex-analytic proof of square-restricted stable phase retrieval in Fock space arXiv:2608.26365
Unverified 2026

Certified partition-function reranking

Replace MAP scoring of discrete latent configurations by comparison of the total energy-model mass assigned to each candidate class. Estimate each class partition function with annealed importance sampling driven by identical random seeds, then return a prediction only when a paired bootstrap confidence interval certifies that its log-partition score exceeds every competitor.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Certified decoding of quantum LDPC codes arXiv:2608.25545
Unverified 2026

Post-Fixing Orthogonality Regularizer

Add a graph-derived conditional moment penalty to a neural representation or predictor. For each nested Markov constraint represented after fixing variables in R, residualize functions of (X,Z) with respect to Z under the post-fixing distribution and penalize their weighted correlation with functions of (Y,Z). This directly targets the equality constraint and can be more informative than an unconditional decorrelation penalty.

Useful5/10
Difficulty6/10
Novelty5/10
Paper: Toward a Semiparametric Efficiency Theory under Equality Constraints in Nested Markov Models arXiv:2608.24602
Unverified 2026

Ground-state fractional regularizer

For a coordinate network representing a field near a boundary or interface, factor the prediction as u(x)=h(x)v(x), where h is a known fractional-Hardy ground-state profile, and regularize v with a weighted nonlocal difference energy. Add the corresponding critical Hardy penalty to the loss so that the network spends capacity on the nonsingular residual v instead of relearning the boundary singularity.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Critical fractional Hardy inequalities arXiv:2608.24389
Unverified 2026

Weak-type pairwise smoothness penalty

Regularize a network using the weak-L^p tail of scale-normalized feature differences between an input and sampled perturbations, instead of averaging all pairwise differences with an ordinary L^p penalty. The weak norm emphasizes persistent high local sensitivities while being less dominated by a single extreme pair than a hard maximum.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Weak-type characterizations of Sobolev and bounded variation spaces on metric measure spaces arXiv:2608.24106