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 dense attention over structured object tokens with attention over role-filler tensor-product representations. A learned query specifies both a role and a filler, retrieves objects matching that binding, extracts a target role, and rebinds the extracted filler into an output object.
Use the local Jacobian of a looped transformer to estimate its remaining relaxation time and stop the recurrent computation when the predicted residual reduction is sufficient. Near a saddle-node fold, the paper's asymptotic relation converts an estimated dominant eigenvalue into a compute forecast, allowing dynamic iteration budgets instead of a conservative fixed maximum.
Replace the global EMA update for each linear-layer momentum matrix with a delta-rule update that learns the current output-side gradient value only along the current input-key direction. Frequently occurring directions are corrected repeatedly, while rarely visited directions are not unnecessarily overwritten or uniformly decayed. Use the resulting matrix as the ordinary momentum buffer in SGD, AdamW, or another optimizer.
Treat a neural-network training update as a control input and impose control-barrier inequalities on quantities that must remain safe, such as parameter norm, activation variance, attention-logit magnitude, or an estimated Lipschitz margin. At each step, solve a small quadratic program that stays as close as possible to the nominal gradient update while guaranteeing a first-order forward-invariance condition.
Replace an instantaneous diagonal optimizer with a causal convolution of recent gradients, where cross-layer or cross-module gradient correlations define a finite-memory Onsager response matrix. Estimate the response at several parameter-block pairs and lags, integrate it to obtain a finite-time transport matrix, and use its regularized inverse or symmetric part to precondition the update. This targets optimization regimes in which gradients propagate between blocks with measurable delay, such…
Use an online estimate of the positive feedback gain among logits, routing probabilities, and representations to adjust the softmax temperature. Increase temperature when the estimated cyclic gain approaches the instability regime, preventing exponential amplification and router collapse without globally weakening all layers.
Replace the usual random or elementwise-positive linear-attention feature map with a rank-one positive-semidefinite feature map derived from query and key vectors. For normalized inputs, the resulting kernel is the squared inner product, which is nonnegative and gives a geometrically structured interference pattern that is better suited to associative recall than an arbitrary low-rank feature map.
Treat neural modules as interconnected dynamical subsystems and estimate the gain from every module input to every neighboring module output. Replace an expensive global Jacobian spectral-radius calculation by decentralized directed-cycle tests inside clusters and path-gain tests between clusters. Penalizing violations during training should prevent exploding recurrent trajectories while retaining less conservative behavior than constraining every individual block independently.
Replace unconstrained residual updates with blocks whose Jacobian is monitored through a Davis–Wielandt shell. The shell simultaneously measures directional dissipation and non-normal amplification, yielding a per-block step-size or residual-scale bound that is stronger than checking only the largest eigenvalue or spectral norm.
Compress each hidden layer by retaining directions that are simultaneously reachable from the observed input distribution and observable at the network output. Unlike PCA or SVD, the retained subspace is weighted by downstream task sensitivity, so high-variance but output-irrelevant directions can be removed while low-variance predictive directions are preserved.
Replace an unconstrained token mixer or feed-forward residual map with a feature-conditioned rational operator whose transfer matrix is positive real on the positive orthant. Apply it through a resolvent, rather than an additive residual, so that the accretivity certificate yields a nonexpansive implicit update and suppresses activation explosions.
Replace ordinary row-softmax attention with a doubly stochastic Sinkhorn attention plan W, and periodically recover a gauge-fixed pairwise cost from W using the exact double-centering identity. Use this recovered cost to initialize or regularize a structured attention score, making the attention geometry identifiable despite arbitrary query and key row and column offsets.
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…
Replace a conventional whitening transform with a constrained whitening layer that minimizes cross-channel covariance while requiring every output channel to remain correlated with its designated input channel by at least a threshold \(\rho_{\min}\). The layer exploits the orthogonal freedom in whitening to find a rotation that preserves channel identity instead of arbitrarily mixing features. It can be inserted before an MLP, convolution, or attention projection and compared directly against…
Insert a linear Johnson–Lindenstrauss bottleneck around a set of jointly processed representations, choosing its width from the sharp finite-set dimension bound rather than from the model's nominal hidden size. The projection should preserve pairwise distances between tokens, patches, or retrieved items, allowing a downstream attention or MLP block to operate at lower width while retaining the geometry relevant to similarity computations.
Use predicted covariance reduction as a differentiable gate for selecting tokens, views, sensors, or retrieved demonstrations. The gate favors inputs with high expected information gain while accounting for acquisition cost, turning attention and data collection into active observability optimization.
Use the evolving singular spectrum of the represented matrix W_t=U_tV_t^{\top} to modulate one common, gauge-equivariant learning rate. Slow the shared update when spectral mass accumulates outside the intended low-rank subspace, preventing adaptive dynamics from amplifying nuisance tail directions while retaining the shared-rate structure needed for low-rank recovery.
Construct a robust covariance estimate of layer activations by replacing each feature with its empirical Gaussian normal score before eigendecomposition, then applying coordinate-wise nonlinear eigenvalue shrinkage rather than multiplying all eigenvalues by one scalar. Use the cleaned covariance to whiten activations or precondition updates to the associated linear layer. This targets unstable directions caused by small batches, heavy-tailed activations, and rare outliers while retaining…
Add a differentiable orientation-pooling layer after steerable filters or an orientation-bin expansion. It aggregates unoriented line evidence using doubled-angle vectors, so a feature at angle θ is identical to one at θ+π, while symmetric orientations cancel naturally instead of producing an arbitrary mean angle. Feed the network both the Cartesian order parameter and its magnitude-based confidence.
Construct overlapping attention windows from a block design instead of using one dense sequence-by-sequence attention matrix. Every token appears in exactly $r$ windows and every token pair co-occurs in exactly $\lambda$ windows, giving uniform coverage and avoiding the uneven connectivity of arbitrary sparse masks.
Compress a transformer KV cache by selecting actual past tokens whose key or hidden-state columns form a stable basis for all cached tokens. Instead of retaining tokens with the largest attention scores or leverage scores independently, compute rank-revealing pivoting of the leading right-singular-vector matrix and retain its pivot columns, then evaluate attention using the representatives plus an optional low-cost residual correction.
Use a low-rank Tucker reconstruction as a structured backbone and quantize only its residual after an orthogonal rotation. The rotation preserves residual energy but redistributes it across coordinates, reducing dynamic-range imbalance and making 2- or 4-bit uniform quantization less damaging than direct quantization of the original KV tensor.
Regularize the local recurrent Jacobian by its spectral radius rather than imposing the overly conservative operator-norm condition $\|J\|_2<1$. This permits useful non-normal updates with transient amplification while explicitly pushing the asymptotic dynamics toward a stable fixed point.
Construct a weight-tied transformer loop in which the recurrent state receives a bounded diagonal carry plus a learned block increment, rather than applying a residual identity inside the learned increment. Parameterize the carry so every channel is strictly below one, allowing many recurrent iterations without the state explosion observed with an unconstrained carry.