ML: Loss

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

343 ideas found

Unverified 2026

Shifted-Hermite Gaussian-tail primitive

Replace repeated evaluations of a Gaussian tail or Mills ratio in a neural loss or sampler with a short shifted-Hermite expansion. Choose a positive reference threshold x and represent the actual threshold as x+t; the same expansion then handles a whole batch of different shifts t using recursively generated Hermite coefficients.

Useful5/10
Difficulty3/10
Novelty6/10
Paper: Appell Polynomials in Shifted Asymptotic Expansions: the Mills ratio, Hermite polynomials, and Stieltjes bounds arXiv:2607.26636
Unverified 2026

Grazing-aware kinetic boundary loss

For a neural approximation $f_\theta(x,v)$ of a kinetic transport solution, weight boundary-condition errors by the trace measure induced by the transport field rather than sampling or penalizing all phase-boundary points uniformly. Use $\omega_p(a)=\min\{|a|,|a|^p\}$ with $a=v\cdot n(x)$; $p=1$ is the natural flux weight, while larger $p$ suppresses poorly resolved grazing interactions more aggressively and can be selected from the boundary regularity.

Useful5/10
Difficulty3/10
Novelty7/10
Paper: Sharp kinetic trace theory arXiv:2607.24708
Unverified 2026

Polynomial Tube Regularizer

Regularize a two-dimensional latent class support or decision-boundary projection by requiring its measured small-radius tube area to follow the quadratic law predicted for conic geometry. Penalize the fitted linear and quadratic coefficients only weakly, but strongly penalize nonquadratic residuals and rapidly changing coefficients across training checkpoints. The intended effect is to remove cusps, tangential near-contacts, and narrow gaps without directly imposing smoothness on the network…

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Conic reach and polynomial parallel volume in the plane arXiv:2607.24487
Unverified 2026

Conditional MTP2 lattice regularizer

Add a structural loss that penalizes violations of conditional MTP2 for a modelled conditional CDF. For conditioning vectors and outcome thresholds ordered componentwise, the model is encouraged to satisfy a multiplicative lattice inequality, which should produce more coherent conditional distributions and imply useful stochastic and tail monotonicity properties.

Useful5/10
Difficulty4/10
Novelty8/10
Paper: An MTP$_2$ property for conditional distributions arXiv:2607.24394
Unverified 2026

Visible-Time Drift Training

Train a neural drift model for a partially observed diffusion using only increments accumulated at times when the latent process is visible, while feeding the projected observation as the state input. The projection may create boundary finite-variation artifacts, but the paper's visible-time identity implies that these artifacts do not bias stochastic estimating equations restricted by the visibility indicator.

Useful5/10
Difficulty3/10
Novelty7/10
Paper: Nonparametric Drift Estimation for Multidimensional Stochastic Differential Equations under Censoring arXiv:2607.24088
Unverified 2026

Sharp Curl-Helicity Regularizer

Add a scale-invariant inequality penalty to a neural vector-potential model on a discretized round 3-sphere. The penalty enforces the theorem's sharp lower bound between the L^{3/2} norm of the predicted magnetic field B=curl A and its helicity H=<B,A>, discouraging pathological high-frequency or spatially concentrated fields that fit observations but have implausible geometry. A divergence-free gauge and Killing-form initialization make the constraint numerically well-conditioned.

Useful5/10
Difficulty5/10
Novelty9/10
Paper: The sharp curl-Sobolev inequality arXiv:2607.23827
Unverified 2026

Residual-Contraction log1p Kernel

Implement \(\log(1+u)\) through the bounded residual \(\rho(u)\), refining the argument by repeated square roots and propagating the residual backward with a rational recurrence. Use this table-free approximation in softplus and log-sum-exp kernels, where millions of logarithms are evaluated and predictable arithmetic can outperform general-purpose library calls on vectorized hardware.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: A Fixed-Point Construction of the Elementary Transcendental Functions arXiv:2607.23196
Unverified 2026

Factor-Two Neural Model-Criticism Test

Use a frozen neural discrepancy score and conditional Monte Carlo replicas to test whether a generative model or learned sampler is compatible with a null data distribution, without requiring mixed chains or joint exchangeability. The resulting empirical p-value has a finite-sample false-alarm bound of at most two times the nominal level, making it safer than an ordinary Monte Carlo rank test for validation and deployment monitoring.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Monte Carlo testing: non-asymptotic guarantees without joint exchangeability arXiv:2607.23010
Unverified 2026

Convex-Ordered Count Head

Equip a neural-network count head with a mean parameter and a dispersion parameter from the Conway-Maxwell-Poisson family, then enforce a mean-preserving convex-order relationship between predictions. This provides a principled way to make the predictive count distribution more or less tail-dispersed while retaining the same predicted mean, potentially improving calibration on overdispersed or underdispersed count data.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Lorenz and convex ordering of parasite burden distributions with density-dependent deaths arXiv:2607.21931
Unverified 2026

Three-Class Fuzzy Multi-Loss Scalarizer

Replace a fixed weighted sum of normalized neural-network objectives with a differentiable fuzzy scalarizer that assigns every criterion to desirable, tolerable, and undesirable regions. Explicit output consequents turn these semantic classes into a scalar training loss, while localized memberships reduce flat plateaus and make the optimizer distinguish genuine preference minima from arbitrary ties.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Rule-Induced Behavior of Fuzzy Scalar Objective Functions for Reliable Multi-Criteria Decision Making arXiv:2607.20731
Unverified 2026

Positive Grassmannian subset head

Replace independent logits for all d-subsets with a neural head that outputs a d-by-n matrix A and assigns subset weight x_I=det(A_{:,I}). After normalization, these minors define a probability distribution over subsets. The head imposes a strong algebraic coupling between subset probabilities, reducing parameters and potentially improving extrapolation to rarely observed subsets.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Maximum Likelihood Estimation on the Grassmannian of Lines arXiv:2607.19593
Unverified 2026

Singular Gradient-Barrier Continuation

Train a neural scalar field with a singular energy that becomes infinite as the input gradient approaches a prescribed threshold, then increase the barrier strength through a monotonic continuation schedule. Unlike ordinary squared gradient penalties, the barrier strongly prevents late-training boundary violations and targets a strict margin rather than merely minimizing average gradient magnitude.

Useful5/10
Difficulty4/10
Novelty4/10
Paper: Minimizers and Weak Solutions for Singular Born--Infeld Type Functionals arXiv:2607.17794
Unverified 2026

Differentiable Hankel PSD regularizer

Attach finite Hankel positive-semidefiniteness penalties to a neural model that predicts scalar moments, cumulants, or beta-distribution parameters. The exact beta inequality supplies a very cheap first-stage barrier, while eigenvalue penalties on larger Hankel matrices constrain higher-order structure.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Higher-Order Hankel Obstructions to Free Infinite Divisibility for Beta Distributions arXiv:2607.17630
Unverified 2026

Intrinsic-Volume Router Regularizer

Represent each bias-free hard MoE routing region as a polyhedral cone in router feature space and regularize its estimated conic intrinsic-volume sequence. The penalty enforces the paper's strengthened log-concavity inequality, preventing routing regions from having implausible concentration at isolated face dimensions and potentially reducing unstable expert starvation.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Log-Concavity of Conic Intrinsic Volumes arXiv:2607.17278
Unverified 2026

Hadamard Flux Loss for Neural Free Boundaries

Use the paper's boundary Hadamard formula as a sensitivity-weighted interface objective for a neural potential and a neural implicit domain. Boundary points with large outward normal flux receive larger shape-update weight, while the positive mixed Monge–Ampère boundary measure supplies a geometry-aware quadrature weight. This gives a mathematically motivated alternative to uniformly weighted boundary residuals in neural free-boundary and obstacle-problem solvers.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: A Hadamard Formula for Equilibrium Envelopes under Parallel Deformation arXiv:2607.17187
Unverified 2026

Cofilling-Shattering Robustness Regularizer

Insert a learned binary or soft linear syndrome map between a feature vector and a compact latent code, and penalize q-dimensional syndrome subspaces that contain any nonzero combination reachable by a low-weight feature perturbation. Unlike independently maximizing the margin of each latent direction, this regularizer protects all linear combinations in the subspace, preventing an adversary from exploiting cancellations or a better-conditioned basis. A soft check-support term can additionally…

Useful5/10
Difficulty7/10
Novelty7/10
Paper: Cofilling Shattering: A Syndrome-Support Hierarchy for Check Erasures arXiv:2607.17028
Unverified 2026

Spatial-depth robust loss gating

Estimate the spatial distribution of minibatch embeddings using normalized residuals, then use the resulting spatial depth as a bounded confidence weight on each example's loss. Examples whose embeddings are spatially central receive near-unit weight, while isolated or adversarial examples are automatically downweighted without estimating covariance matrices or choosing a dimension-dependent bandwidth.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Dimension-invariant uniform consistency of the empirical spatial distribution function and its associated spatial depth estimator arXiv:2607.16092
Unverified 2026

2p+1 Random Fourier Dynamics Loss

Train a parametric neural dynamical model by matching randomized Fourier features of observed and simulated trajectory windows, using k=2p+1 features when the model has p trainable dynamic parameters. The random projections compress long noisy trajectories into a small identification signal while retaining nonlinear dependence on all lags, potentially making model calibration less sensitive to correlated, non-Gaussian, or state-dependent observation noise.

Useful5/10
Difficulty3/10
Novelty4/10
Paper: Dynamic models with $p$ parameters are identified by $2p+1$ random features arXiv:2607.16035
Unverified 2026

Geometric observability gating

Build a graph diffusion or neural-operator encoder whose sparse-observation loss is weighted according to graph distance from the observed nodes. For early diffusion times, suppress supervision or cross-attention demands that are geometrically impossible because signals at distance \(d\) are attenuated like \(e^{-d^2/(2t)}\); gradually release those constraints as diffusion time grows.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Optimal geometric barriers for weighted observability of heat semigroups on metric measure spaces arXiv:2607.13279
Unverified 2026

Killed-Resolvent Residual for Neural Obstacle Solvers

Train a value network for stopping or intervention decisions using a killed-resolvent identity rather than an unrestricted diffusion residual. Simulating only until the process exits the continuation region makes the learning target local to the relevant decision domain and correctly handles nonsmooth max rewards.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Reflected Optimal Stopping with a Max-Type Payoff: Measure-Valued Stopping Gains and Killed Resolvent Representation arXiv:2607.09987
Unverified 2026

Dirichlet-calibrated mean-loss alarm

Replace heuristic moving-average thresholds for a nonnegative neural-network quantity with an exact finite-sample p-value computed from a batch of independent observations. Use the p-value to stop training, trigger a learning-rate reduction, or reject a model whose expected loss or safety cost exceeds a prescribed threshold, without assuming bounded, Gaussian, or identically distributed observations.

Useful5/10
Difficulty3/10
Novelty8/10
Paper: An Exact Distribution-Free Test for Means of Nonnegative Random Variables arXiv:2607.08415
Unverified 2026

Covering-Based Interaction Regularization

Regularize a neural network using exact finite-difference interaction terms at a chosen perturbation scale, while retaining the covering decomposition of a composition f∘g. Instead of penalizing only the total mixed difference, separately penalize selected covering terms containing large subsets or overlapping subsets, which targets higher-order and nonlocal interactions without computing Hessians.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Discrete Faà di Bruno via Möbius Inversion arXiv:2607.07742
Unverified 2026

Invariant cone positive feature head

Constrain selected degree-four feature blocks to represent globally nonnegative binary quartics using a positive-semidefinite Gram matrix. This gives a structured alternative to unconstrained activations for energy, uncertainty, density, or direction-dependent gating features that must remain nonnegative under every planar direction.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: On 4-dimensional convex projective domains invariant by a lattice of $\mathrm{SL}_2 (\mathbb{R})$ arXiv:2607.07150