Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Replace a recurrent token-mixing operation with a finite-state carrier scan over binary or quantized token features. The local transition table is constrained to conserve a scalar token weight and to be bijective, making the mixer reversible, constant-memory, and less prone to activation drift than a generic recurrent layer.
Replace a dense recurrent transition matrix with a periodic CMV-style product of alternating local 2x2 unitary cores. The transition is exactly norm-preserving, has O(n) trainable parameters under periodic tying, and can be applied through local factor operations rather than stored as an n-by-n matrix. Use turnover refactorization when changing the ordering or boundary connection of cores, enabling a compact cyclic unitary state-space layer.
Replace a generic recurrent transition with two coupled unitary transitions that share one block column and differ by a sign on the other block column. Each transition preserves hidden-state norm exactly, while the structured difference gives a controlled two-path recurrent architecture for long-context modeling.
Add a fixed or weakly parameterized residual mixer whose interaction between sequence positions at distance \(r\) is proportional to \(1/(r\log^2 r)\). Instead of truncating the kernel at a short radius, represent its heavy tail with dyadic distance bands and compute each band using prefix sums or block pooling, giving every token access to arbitrarily distant context at roughly \(O(L\log L)\) cost.
Add a conservative correction after low-rank tensor compression so selected linear moments of an activation or learned state are exactly preserved. This can reduce tensor rank and memory without allowing compression error to accumulate in physically meaningful global quantities.
Replace a discrete or one-hot recurrent state table with a low-dimensional vector memory whose event embeddings are orthogonal whenever the corresponding events are mutually exclusive in an input exclusivity graph. The module uses continuous state vectors and can therefore target dimension \(d=\xi(G)\), whereas a discrete state encoding is lower-bounded by \(N\geq\chi(G)\). This should be tested on graph-defined formal-language recognition tasks, where the graph is known and the claimed…
Choose the retained context length by balancing the statistical complexity of adding lag j against the squared prediction bias from discarding it. Unlike a fixed context window, the rule uses both the remaining-horizon spectrum and the estimated tail energy, allowing a model to expand or shrink its memory online.
Compress the hidden state of a stable neural state-space layer using low-rank controllability and observability Gramians. States that are difficult to excite from the input or weakly visible at the output are removed, producing a smaller recurrent state with a principled input-output preservation criterion.
Build a fixed sparse token-mixing layer on n=qr cyclic positions whose directed edges are all offsets 1 through r, but execute the edges through r Hamiltonian path scans plus one prescribed chain. The paths preserve exact coverage of the circulant connectivity while exposing long sequential traversals that can be fused into custom kernels, recurrent scans, or state-space updates.
Build a sparse recurrent graph-neural layer on a path-by-path, path-by-cycle, or cycle-by-cycle latent lattice using a skew-zero-forcing seed set and its forcing order as a causal update schedule. Only the currently forced target node is activated at each step, so a small number of anchor states can propagate through the complete lattice while retaining local connectivity and periodic-boundary structure. The exact seed-count formulas predict the minimum number of anchors required by the graph…
Construct a reversible neural evolution from alternating learned drift and kick maps, then periodically apply the learned inverse sequence and penalize failure to reconstruct the original hidden state. The echo loss turns the paper's time-reversal protocol into a directly measurable stability certificate for long-depth neural dynamics and can identify whether errors are diffuse numerical noise or localized catastrophic faults.
Replace an unrestricted GRU or attention-based history encoder with a fixed companion-form shift register driven by the current action and observation, followed by a learned nonlinear policy. The register stores a structured finite history, while a learned matrix or MLP readout maps that history to a control-relevant latent state. This should provide a cheaper and more interpretable memory mechanism for partially observed environments, especially when the relevant dynamics are approximately…
Replace or augment the transition map of a recurrent state-space model with bounded analytic maps of a latent complex coordinate, using several finite Blaschke generators that share a fixed point. Enforcing a superattracting fixed point of local degree p creates a tunable hierarchy of memory erasure: the theory predicts double-exponential decorrelation with exponent log p, while a merely attracting fixed point gives ordinary exponential decay.
Replace an unrestricted additive recurrent or fast-weight memory with a sign-selectable update: for each incoming update vector, choose between adding and subtracting it so that a smooth compact potential of the memory state is minimized. This is appropriate when the memory representation has sign symmetry, such as signed random features or a learned linear sketch; it is not a drop-in replacement for ordinary gradient updates where the sign carries semantic information.
Replace unconstrained recurrent-state decay with a one-dimensional latent defect field whose states evolve by local diffusion and pair reactions. Defects can move over long distances and persist, while creation and removal occur only in pairs, giving the memory a structured cancellation mechanism that is potentially better suited to delayed-event and parity-like sequence dependencies than a standard GRU or diagonal SSM.
Apply a weak-trace spectral constraint to the covariance of antisymmetric second-order features, encouraging a 1/i eigenvalue envelope rather than forcing a finite trace norm. This targets the paper's sharp logarithmic Ky Fan behavior and may preserve useful long-tail interaction directions that nuclear-norm regularization would remove.
Replace a learned causal mixing profile by a monotone profile followed by a prefix-average Hardy mixer. The monotonicity constraint makes the mixer provably non-degenerate in the BMO sense: localized variation in the profile cannot be reduced below a calibrated factor by prefix averaging. This is a cheap alternative to dense causal attention for tasks where importance or state profiles are expected to decay along sequence position.
Replace a dense channel-mixing matrix in a sequence layer with alternating diagonal propagation and sparse unipotent Stokes jumps. The diagonal part carries independently controlled exponential phases, while the unipotent factors implement cheap residual-like mode conversion without changing determinant or requiring a dense matrix multiply. Constrain the phase magnitudes and jump coefficients during training to obtain a reversible, norm-monitorable mixer.
Replace an unconstrained recurrent or state-space transition with a complex-orthogonal flow generated by a skew-transpose matrix. The transition preserves a bilinear quadratic quantity exactly, preventing repeated application across long sequences from causing norm explosion or decay in the linear dynamics.
Add a bounded phase variable and a bank of local affine transport maps to an RNN or state-space model. The phase follows an irrational rotation, while the hidden state is transported through cells whose widths determine local gains, giving a controllable memory mechanism with analytically known distortion rather than an unconstrained recurrent Jacobian.
Replace a learned recurrent transition with a sparse binary reservoir compiled from prime-count gates. Three permanently active control vertices implement copy and XNOR transitions, allowing the signal state to realize an affine feedback register over \(\mathbb F_2\) with period \(2^m-1\) using only \(O(m)\) edges and bounded in-degree. Train only an input projection and readout, or use straight-through estimators if end-to-end adaptation is required.
Replace step-by-step hidden-state storage in a latent ODE, state-space model, or world model with a polynomial trajectory represented independently on short time blocks. At the end of each block, pass the next hidden state by summing temporal coefficients, allowing training and inference to discard the completed block while retaining a mathematically exact block interface.
Replace a dense token or channel mixing matrix by a fixed sparse directed graph whose states are ordered pairs of symbols and whose transitions advance through a cyclic phase. Each state has exactly two allowed successors, obtained by appending a symbol different from the previous two, producing a strongly connected, vertex-transitive sparse mixer with shared local dynamics. The prescribed phase structure prevents arbitrary short-cycle routing and can act as an anti-collapse inductive bias in…
Generate temporal attention or convolution weights with the Graham–Knuth–Patashnik recurrence instead of learning every lag weight independently. For nonnegative recurrence parameters, the resulting lag sequence is strongly log-concave, so its normalized kernel is naturally unimodal and suppresses high-frequency sign-free oscillations without requiring a separate smoothness penalty. The six parameters can be learned per head, channel group, or layer, giving O(1) learned parameters for an…