Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Train attention logits so that the associated Sinkhorn-scaled operator has a favorable local spectral gap, making iterative normalization contract faster. Add a differentiable penalty on the second eigenvalue of the normalized operator while retaining the task loss and marginal-feasibility loss.
Construct a filtered cell complex from neural activations or a learned token/feature graph and track its persistence barcode incrementally as model activations change. Replace full persistent-homology recomputation at every checkpoint by maintaining homology bases and applying local transpositions when filtration blocks split or merge; use barcode drift as a training monitor or a weak regularization signal.
Replace a dense attention pattern by the exact intersection of a fixed or cheaply computed base graph H and a learned shared-label relation. Two tokens can exchange information only when they are adjacent in H and share at least one of d labels, producing a controllable structured sparsity pattern. The label count d becomes an explicit capacity and compute knob: increasing d enlarges the relation vocabulary without requiring a dense pairwise mask.
Insert a Walsh-Hadamard transform before a quantized categorical or activation bottleneck and assign coordinate-dependent quantization precision using the attenuation spectrum of a quaternary symmetric noise model. Coordinates corresponding to tensor-product frequencies with many nonzero indices are attenuated by higher powers of \(\delta\), so their quantization can be made coarser with little effect on the reconstructed post-noise representation. This creates a structured, fast transform…
Replace a dense third-order channel-interaction tensor by a fixed sparse support selected through the paper's uniform-marginal infeasibility certificate. Supports with a large dual margin have an effective entropy base below the channel alphabet size, suggesting fewer independent interaction slices and cheaper contractions. Use the certificate either during architecture search or as a pruning score for an already-trained tensorized layer.
Replace part of dense token mixing with a small bank of structured permutations acting on a hierarchical token tree. Diagonal inheritance shares the same local permutation across all descendant copies, while selector words activate one connector type at a chosen level and remain inactive on the next type, providing controllable multiscale receptive fields without constructing a dense attention matrix.
Use the paper's marginally irrelevant RG flow to schedule communication between two neural feature streams. A fast stream, such as transformer attention, can interact with a slower or more persistent stream, such as an SSM or low-frequency convolutional branch, through a gate that decreases like \(1/(1+a y_0 \ell)\) instead of remaining fixed across depth or training time. A learnable initial amplitude preserves adaptability while the inverse-logarithmic envelope suppresses harmful long-range…
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.
Represent sequence positions as vertices on a circle and use a maximal family of mutually non-crossing d-arcs to define the allowed attention interactions. Rotate the family by d positions, or use several phase-shifted families across successive layers, so each layer has only O(N) edges but repeated layers propagate information over long distances. The geometric compatibility rule replaces arbitrary local-window or hand-designed sparse masks with a structured family whose maximality gives broad…
Replace unconstrained pairwise token-routing interactions with a structured two-token router derived from an involutive set-theoretical Yang–Baxter solution. The pair operator is a convex interpolation between identity and a permutation of discrete routing states, so it cannot amplify probability mass or logits when applied to routing distributions. The Yang–Baxter relation provides a falsifiable test for whether three-token routing updates are insensitive to the two admissible…
Use the one-edit Hamiltonian walk as an explicit state machine for counters in autoregressive models or world models. Instead of regenerating and re-embedding an entire numeric string after every increment, update only the digit that changes, or append the single leading digit at a block transition.
Use effective coupling and field values from a local coarse-grained motif to decide whether a neural network should operate at fine or coarse resolution. Near the continuous critical boundary, retain fine-scale features because correlations become long-ranged; away from criticality, aggregate aggressively. Near discontinuous or reentrant boundaries, hysteresis prevents rapid switching between resolutions.
Use the tropical dynamical degree as an analytic expansion budget for repeated neural blocks. Layers with $pq>4$ deliberately expand along a known tropical eigendirection, while layers with $pq\leq4$ avoid exponential asymptotic growth; a schedule can therefore increase representational mixing without allowing hidden-state norms to explode.
Replace a neural layer's dense parameters by a real parameter tensor and a binary activity mask, then update the mask using importance scores measured across multiple perturbation intervals. Gates that repeatedly occur in non-dominated accuracy–cost configurations receive larger scores and are more likely to be retained or activated, avoiding uniformly random sparse rewiring.
Estimate how strongly each neural block contracts distinguishability and use the paper's weighted composition inequality to allocate depth, residual strength, or precision where information is actually preserved. Blocks that strongly contract information beyond the reference path receive a smaller residual gate, higher numerical precision, or are replaced by a cheaper identity-like operation.
Replace dense token-to-token attention with a learned composition of adjacent routing operators whose connectivity is stored as a non-crossing labelled arc diagram. Canonicalize the composed routing program using the Okada relations, then execute only the surviving sparse token paths.
Add a structured boundary-like operation to an MoE router that rapidly mixes expert probabilities toward a learned distribution while preserving predefined expert groups. The operation is a rank-one stochastic kernel, so it costs linear rather than quadratic work in the number of experts and can act as a controlled reset when routing becomes concentrated.