Solves: Accuracy

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

1956 ideas found

Failed on benchmark 2026

Calorimetric Training Transition Detector

Treat optimizer stochasticity as an effective temperature and periodically apply a small temperature pulse, such as a temporary change in minibatch size, learning rate, dropout, or Langevin-noise amplitude. Measure the transient excess optimization dissipation and use its integrated response as a heat-capacity-like signal; sharp peaks provide a principled trigger for learning-rate changes, regularization changes, or phase-transition logging.

Useful7/10
Difficulty5/10
Novelty7/10
Paper: Heat capacity as a marker for shape and jamming transitions in active systems arXiv:2608.17903
Failed on benchmark 2026

Gauge-Covariant Wilson-Loop Regularization

Attach an SU(2) transport matrix to every directed edge of a graph neural network and penalize nontrivial plaquette holonomies instead of penalizing individual edge transformations. The regularizer is invariant to arbitrary local changes of latent representation frame, encouraging path-consistent relational features without requiring all edges to share one global coordinate system.

Useful7/10
Difficulty6/10
Novelty7/10
Paper: Frustration without Glass: A Non-Abelian Gauge Model of Network Compatibility arXiv:2608.17817
Mechanism confirmed, baseline not beaten 2026

Koopman Hankel Dual Autoencoder

Replace pointwise sequence reconstruction with reconstruction of overlapping past and future Hankel windows in a shared latent manifold. A first encoder compresses the delay-coordinate trajectory, while a second decoder or predictor reconstructs the future block from the latent state; training therefore penalizes representations that fit observations but do not preserve dynamical evolution.

Useful7/10
Difficulty5/10
Novelty6/10
Paper: Fault detection on manifolds of nonlinear dynamical systems with dual autoencoders arXiv:2608.17698
Failed on benchmark 2026

Transverse Synchrony Training

Pair a neural latent dynamical system with a reference latent system driven by the same external input, and train a coupling or controller so that a synchrony residual converges to zero. The target is transverse stabilization of a behavior-equivalence manifold rather than pointwise tracking of one selected trajectory or equilibrium.

Useful7/10
Difficulty6/10
Novelty7/10
Paper: On the behavior assignment problem arXiv:2608.17652
Unverified 2026

Dynamic-programming Doob sampler for exact rare-event conditioning

Add an exact backward-conditioning module to a neural state-space model so trajectories satisfy a terminal label, target set, initial-state restriction, or prescribed event count without rejection. The module computes a backward feasibility message and reweights each neural transition toward states that can still satisfy the constraint, producing a conditioned process equivalent to a Doob transform. For large latent spaces, the exact message can be approximated by a value network and its…

Useful7/10
Difficulty6/10
Novelty5/10
Paper: Conditional-path Monte Carlo for rare stochastic dynamics on networks: Details and derivations arXiv:2608.17511
Failed on benchmark 2026

Kac-rotated fast projection

Replace a dense Haar or Gaussian random projection with a streamed product of random two-coordinate rotations followed by coordinate subsampling. The transform is exactly orthogonal before subsampling, requires only a list of rotation triples, and the paper's pseudo-mixing result predicts that degree-two statistics relevant to norm preservation and Johnson–Lindenstrauss embeddings become Haar-like after only O(n polylog(n)) rotations.

Useful7/10
Difficulty4/10
Novelty5/10
Paper: On the Pseudo-Mixing of Kac's Walk arXiv:2608.17374
Failed on benchmark 2026

HOCBF Safety Shield for Neural Policies

Use a neural policy only to generate a nominal action, then project that action onto the set satisfying a high-order control-barrier inequality derived from a smooth obstacle-distance function. This preserves the policy's behavior away from obstacles while enforcing a forward-invariant safety region near obstacles, and it can be used either as an inference-time shield or as a differentiable training layer.

Useful7/10
Difficulty5/10
Novelty6/10
Paper: Safe whole-body backstepping control for quadcopter path-following arXiv:2608.17259
Failed on benchmark 2026

Bregman-Projection Polyak Optimizer

Replace the Euclidean Polyak step in an optimizer with a mirror-descent step whose length is chosen by projecting onto the current affine lower-bound halfspace in Bregman geometry. This permits entropy geometry for simplex-valued router probabilities, log geometry for positive parameters, and other mirror maps without reducing the method to a norm-based learning-rate rule.

Useful7/10
Difficulty5/10
Novelty7/10
Paper: Mirror Polyak and a Primal-Dual Lifting arXiv:2608.17252
Mechanism confirmed, baseline not beaten 2026

Lipschitz Forward-Invariant Policy Certification

Certify during or after RL training that a neural policy keeps the closed-loop state inside a prescribed safe set under bounded disturbances and observation errors. Use spectral normalization or a Lipschitz penalty to reduce policy gain, then compute a conservative one-step safety margin that must remain positive over reachable states.

Useful7/10
Difficulty5/10
Novelty7/10
Paper: Safe Deep Reinforcement Learning for Energy-Efficient HVAC Control in Multi-Zone Residential Buildings arXiv:2608.17235
Failed on benchmark 2026

Dual Information-Demand Curiosity

Train a latent world model with a conditional-mutual-information lower-bound constraint instead of using a fixed curiosity or information-gain coefficient. The dual multiplier increases only when predicted observations contain less information about latent states and model parameters than the goal prior demands, and decreases when the target is exceeded; this produces an adaptive epistemic-pressure schedule with explicit inactive and saturated regimes.

Useful7/10
Difficulty5/10
Novelty6/10
Paper: Expected free energy as an information constraint on the Bethe Lagrangian arXiv:2608.17167
Mechanism confirmed, baseline not beaten 2026

Singular-Value-Robust Projector-Splitting LoRA

Train a fixed-rank neural weight update Y=USV^T with a projector-splitting Runge–Kutta step instead of independently applying Adam or gradient descent to U, S, and V. The update evolves the full low-rank matrix using the neural gradient but performs QR-based factor updates, avoiding S^{-1} and remaining stable when adapter singular values collapse or cross zero. Use a common-base midpoint construction so every internal stage starts from the same U,V basis and remains rank r.

Useful7/10
Difficulty5/10
Novelty6/10
Paper: Robust Projector-Splitting Runge-Kutta Integrators of Orders Two and Three arXiv:2608.17157
✓✓ Beats tuned baseline 2026

Randomized-QMC gradient batches

Replace IID latent or diffusion-noise samples used inside a neural expectation with a randomized low-discrepancy point set. Each randomized point has the correct marginal distribution, while the complete set covers the sampling domain more uniformly, reducing variance in minibatch loss and gradient estimates when the integrand is smooth in the base-noise coordinates.

Useful7/10
Difficulty4/10
Novelty6/10
Paper: Randomized quasi-Monte Carlo integration arXiv:2608.17143
Failed on benchmark 2026

TD-to-PDE Continuation Training

Train a neural value or latent-dynamics model with temporal-difference targets before enforcing a stiff differential-equation residual, and ramp the physics weight only after the critic has become predictive. For a stochastic dynamical model, the residual is computed using the infinitesimal generator, while terminal, safe, and failure boundary conditions are imposed through separate penalties.

Useful7/10
Difficulty5/10
Novelty7/10
Paper: Physics-informed Reinforcement Learning for Stochastic Reach-Avoid Analysis arXiv:2608.17117
Mechanism confirmed, baseline not beaten 2026

Causal E/I Micro-Event Cell

Replace signed-input aggregation in a spiking recurrent cell with a causal micro-event queue that processes excitatory and inhibitory arrivals in timestamp order, applying threshold and reset after each event. This preserves computations that disappear when all events in a timestep are replaced by one net current, particularly near threshold.

Useful7/10
Difficulty5/10
Novelty7/10
Paper: Order-Sensitive Fast-Synapse Limits in Sparse Excitatory-Inhibitory Threshold-Reset Networks arXiv:2608.16701
Mechanism confirmed, baseline not beaten 2026

Energy-Riesz checkpoint selector

Replace raw neural PDE training-loss checkpoint selection with a residual monitor measured in the variational energy geometry. For every archived network, solve an auxiliary conforming Riesz problem and select the checkpoint with the smallest reconstructed residual norm; nested auxiliary spaces make this score converge monotonically to the inaccessible energy error.

Useful7/10
Difficulty4/10
Novelty7/10
Paper: Reference-free logged energy-oracle recovery for neural approximations of symmetric coercive variational problems: conforming Riesz reconstruction and archive-level selection arXiv:2608.16473
Failed on benchmark 2026

MI-Guided Latent Protection

Use the estimated task relevance of each latent coordinate to allocate corruption, precision, or redundancy non-uniformly rather than applying uniform dropout or quantization noise. Coordinates with larger mutual-information sensitivity receive lower noise or more bits, while low-relevance coordinates are compressed or corrupted more aggressively.

Useful7/10
Difficulty4/10
Novelty6/10
Paper: Adaptive Unequal Error Protection for Semantic Split Learning over Wireless Channels arXiv:2608.16227
Failed on benchmark 2026

Conditional spacetime-cluster sampler for rare neural trajectories

Represent a stochastic recurrent or state-space model as an event trajectory and train it with trajectories conditioned on a rare terminal event, such as a catastrophic state, a constraint violation, or an unusually large prediction error. Instead of simulating forward until the event occurs, update connected spacetime clusters while holding the initial state and terminal event boundary fixed, so every retained trajectory is useful for rare-event learning. This provides a principled alternative…

Useful7/10
Difficulty7/10
Novelty8/10
Paper: Rare-event sampling for stochastic dynamics in network systems using cluster updates arXiv:2608.16171
Failed on benchmark 2026

Fisher-Observable Latent State Training

Add an observability regularizer to a recurrent state-space model or world model so that short sequences of predicted multimodal observations identify the latent state. The regularizer penalizes poorly conditioned Fisher information, preventing the model from storing important state variables in directions that its available observations cannot distinguish.

Useful7/10
Difficulty5/10
Novelty6/10
Paper: Improving Observability of Relative Orbit Estimation Using Bearing Measurements and Light Curves arXiv:2608.16135
Unverified 2026

Digital-Recurrence Lyapunov Monitor

Add a numerical-health monitor that distinguishes genuine contraction or chaos from finite-precision periodicization. It tracks hidden-state recurrence, effective cycle length, and the divergence between single-rollout and independent-restart Lyapunov estimates, then triggers precision escalation, rollout truncation, perturbation, or training early stopping when the diagnostic enters the recurrence-collapse regime.

Useful7/10
Difficulty5/10
Novelty8/10
Paper: When More Data Become Less Informative: Finite-Precision Periodicization and Collapse of Forecast-Error Lyapunov Estimates arXiv:2608.16120
Unverified 2026

Differentiable Simulation-Regularized Neural Dynamics

Train a neural controller or latent dynamics model together with a finite abstraction whose cells and successor relations are optimized using a smooth reverse-simulation surrogate. Penalizing concrete-to-abstract mismatch should suppress locally inconsistent or overly expansive latent transitions, while a separate reachability containment check preserves soundness. This creates a verification-aware training signal that targets spurious branching rather than only one-step prediction error.

Useful7/10
Difficulty6/10
Novelty8/10
Paper: $S^3$: A Smooth Simulation Surrogate for Optimizing Discrete Abstractions of Dynamical Systems arXiv:2608.15920
Unverified 2026

Dimension-Free Brenier Transport Layer

Build a neural transport layer by parameterizing a convex potential whose gradient maps a semi-log-concave latent distribution into a compact convex data domain. Use the paper's dimension-free Lipschitz certificate to set the layer's Jacobian scale, initialize the potential, and reject or regularize parameter updates that create excessive curvature. The goal is a bounded-output transport module that is less sensitive to latent dimension than diameter-based spectral heuristics.

Useful7/10
Difficulty6/10
Novelty7/10
Paper: Dimension-Free Lipschitz Bounds for Brenier Maps to Compactly Supported Log-Concave Targets arXiv:2608.15906
Unverified 2026

Bennett-whitened gradient trust region

Use the paper's self-normalized martingale bound to monitor cumulative stochastic gradient noise in covariance-whitened coordinates. Convert its time-uniform confidence boundary into a trust-region multiplier: retain the normal optimizer update while the observed noise is within the boundary, and shrink or clip the update after an exceedance.

Useful7/10
Difficulty5/10
Novelty6/10
Paper: Self-normalised Bennett inequalities for Hilbert-valued martingales arXiv:2608.15874
Unverified 2026

Exact-Curl Neural Field Output

Make a neural network predict a vector potential rather than a magnetic or velocity field, then obtain the physical vector field with a fixed differentiable discrete curl. The reconstructed field satisfies the discrete divergence-free constraint exactly, eliminating divergence-penalty tuning and preventing constraint drift during long rollouts.

Useful7/10
Difficulty4/10
Novelty5/10
Paper: A Structure- and Pressure-Positivity-Preserving Semi-implicit IMEX Finite Volume Scheme for Ideal MHD at All Acoustic Mach and Alfvén Mach Numbers with Generic Equation of State arXiv:2608.15837
Unverified 2026

Prolate Energy-Preserving Bottleneck

Insert a fixed DPSS/prolate projection before an expensive neural block, retaining exactly the modes whose time-frequency concentration eigenvalues exceed a target threshold. Use the paper's tail-quantile formula to choose the projection rank from sequence length, effective bandwidth, and tolerated energy loss, then optionally learn a small correction in the retained coordinates. Unlike a Fourier truncation, the basis is optimized for simultaneous localization in the finite input window and the…

Useful7/10
Difficulty5/10
Novelty7/10
Paper: Uniform sine-kernel determinant asymptotics, tail-side quantiles, and prolate eigenvalue bounds arXiv:2608.15808