The E$Δ$-MHC-Geo Transformer: Adaptive Geodesic Operations with Guaranteed Orthogonality

• URL: http://arxiv.org/abs/2605.06729v1
• Date: Thu, 07 May 2026 11:37:23 GMT
• Title: The E$Δ$-MHC-Geo Transformer: Adaptive Geodesic Operations with Guaranteed Orthogonality
• Abstract summary: E$$-MHC-Geo Transformer is a novel architecture that unifies Manifold-Constrained Hyper-Connections (mHC), Deep Delta Learning (DDL), and the Cayley transform.
• Score: 2.28438857884398
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present the E$Δ$-MHC-Geo Transformer, a novel architecture that unifies Manifold-Constrained Hyper-Connections (mHC), Deep Delta Learning (DDL), and the Cayley transform to obtain input-adaptive, unconditionally orthogonal residual connections. Unlike DDL, whose Householder operator is orthogonal only at $β\in \{0,2\}$, our Data-Dependent Cayley rotation $Q(x)=(I+(β/2)A(x))^{-1}(I-(β/2)A(x))$ preserves orthogonality for all $β$ and all inputs. To handle negation, an eigenvalue $-1$ case that Cayley provably excludes, we introduce the E$Δ$-MHC-Geo Hybrid, which combines Cayley rotation with Householder reflection via a learned operator-selection gate $X'=γ(X)Q(X)X+(1-γ(X))H_2(X)X$. A midpoint-collapse regularizer, $4γ(1-γ)$, encourages boundary gate decisions, where each selected component is orthogonal. In matched-parameter comparisons, with approximately 1.79M parameters per model and mean +/- standard deviation over 3 seeds, against four baselines including the concurrent JPmHC, E$Δ$-MHC-Geo achieves the best long-horizon stability, 1.9x over JPmHC and 3.8x over GPT; the best near-$π$ rotation loss, 4.5x over JPmHC on single-plane; strong norm preservation, with 0.001 mean deviation; and 0.96 negation cosine alignment in a diagnostic reflection probe, all with 33% fewer layers. While JPmHC's wider representation excels on pure rotation, its finite Cayley residual mixer excludes an exact $λ=-1$ operator and has no reflection branch, motivating our hybrid approach for accessing both connected components of $O(n)$.

Related papers

• Exact Limits of Random Projections for Preserving Geometry: Distance Recovery, Nearest-Neighbor Rankings, and Covariance Shape in Gaussian Models [0.0]
  Johnson-Lindenstrauss lemma guarantees that a random projection of $n$ points to $m=O(varepsilon-2log n)$ dimensions preserves linear squared distances.<n>In high dimensions, however, distances concentrate around a baseline while key geometric information lies in much smaller fluctuations.<n>We show that the JL bound can therefore be uninformative about retained geometry.
  arXiv  Detail & Related papers  (2026-09-02T06:12:34Z)
• Geodesic Quantum $f$-Divergences [1.9336815376402718]
  We show strengthened geodesic quantum quantum-divergences $D_ft$, $0leq tleq1.<n>They reduce to the $(,z)$ Petz and Rényi divergences joining the Petz and Umegaki families.<n>We also determine parameter-monity regimes and the intersections with the $(,z)$ family.
  arXiv  Detail & Related papers  (2026-08-16T16:07:56Z)
• ForgettingOT: Certified Speculative Batching from Sinkhorn's Projective Forgetting [0.0]
  We show that the eigenmode of the fixed-point Jacobian $J_tstar=QP=Pstar P$ controls the strict correction tail.<n>ForgettingOT turns this nonlinear Perron--Frobenius fact into a certified executor for streams of related Sinkhorn problems.
  arXiv  Detail & Related papers  (2026-07-27T17:59:36Z)
• Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence [54.59847568544922]
  We study horizon-free regret for finite-horizon time-homogeneous Markov decision processes with $A$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.<n>We prove a regret upper bound [tilde O(sqrtSAK+S8A3)] with failure probability $$, where $K$ is the number of episodes and $tilde O(sqrtSAK+S3K)$ hides $mathsfpoly
  arXiv  Detail & Related papers  (2026-07-22T07:42:19Z)
• Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m [0.0]
  Independently trained transformers compute the same function in residual-stream bases that differ by a uniform random rotation.<n>We call this phenomenon polymorphism: same function, mutually unintelligible interior coordinates.<n>The phenomenon is invisible to the standard SAE metric.
  arXiv  Detail & Related papers  (2026-05-23T13:37:59Z)
• Hidden-State Privacy Has an Empty Middle [51.56484100374058]
  We prove a complementary Fisher-ball lower bound: every full-rank Gaussian release at $O(1)$ Fisher utility admits a direction whose Mahalanobis signal grows linearly in hidden width.<n>A split-memory transformer trained from scratch reaches $G_mathrmMah in [20, 33]$ at 90M and maintains a $6$--$24times$ advantage over same-budget GPT baselines from 30M to 1B at a fixed-token language loss penalty.
  arXiv  Detail & Related papers  (2026-05-21T20:12:09Z)
• OAM-Induced Lattice Rotation Reveals a Fractional Optimum in Fault-Tolerant GKP Quantum Sensing [0.0]
  We establish that orbital-angular-momentum encoding and Gottesman-Kitaev-Preskill (GKP) lattice geometry are structurally coupled.<n>Using an end-to-end differentiable Strawberry Fields--TensorFlow circuit, we jointly optimise $ell$, the lattice aspect ratio $r$, and the finite-energy envelope $$ to maximise quantum Fisher information.
  arXiv  Detail & Related papers  (2026-05-13T09:49:16Z)
• Hardware Validation of DAGI via a Modular "Ridge" Signature and High-Order Synergistic Information [0.0]
  DAGI (Directed Acyclic Graph Information) framework on IBM Quantum hardware.<n>Small, controlled experiment whose ideal output distribution is constrained to a low-dimensional modular manifold (a "ridge)<n>Key recovery exceeds chance: per-shot accuracy 0.1689 (chance 0.125, 95% Wilson CI [0.1610, 0.1772])<n>These results support the claim that DAGI detects and quantifies non-trivial, hardware-resilient information structure.
  arXiv  Detail & Related papers  (2026-04-16T14:16:59Z)
• Online Covariance Estimation in Averaged SGD: Improved Batch-Mean Rates and Minimax Optimality via Trajectory Regression [12.805268849262243]
  We study online covariance matrix estimation for Polyak-Ruppert averaged gradient descent (SGD)<n>The construction reveals that the bottleneck is the sublinear accumulation of information about the Hessian from the SGD drift.
  arXiv  Detail & Related papers  (2026-04-12T20:49:33Z)
• Optimal Scalar Quantization for Matrix Multiplication: Closed-Form Density and Phase Transition [50.36362492608702]
  We study entrywise scalar quantization of two matrices prior to multiplication.<n>We obtain a closed-form optimal point density [ star(u) propto exp!left(-fracu26right)bigl( (1-2)+2u22bigr), qquad u=fracx_X,, and prove a correlation-driven phase transition.
  arXiv  Detail & Related papers  (2026-03-20T01:53:44Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• Robust Sublinear Convergence Rates for Iterative Bregman Projections [21.689846521201588]
  We use entropic regularization to approximate linear programs whose constraints split into two (or more) tractable blocks.<n>We derive the flow-Sinkhorn algorithm for the Wasserstein-1 distance on graphs.
  arXiv  Detail & Related papers  (2026-02-01T18:20:19Z)
• Robust inverse material design with physical guarantees using the Voigt-Reuss Net [0.0]
  We propose a spectrally normalized surrogate for forward and inverse mechanical homogenization with hard physical guarantees.<n>In 3D linear elasticity on an open dataset of biphasic microstructures, a fully connected Voigt-Reuss net trained on $>!7.5times 105$ FFT-based labels with 236 isotropy-in descriptors.<n>Overall, the Voigt-Reuss net unifies accurate, physically admissible forward prediction with large-batch, constraint-consistent inverse design.
  arXiv  Detail & Related papers  (2025-11-14T15:17:37Z)
• Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs [56.237917407785545]
  We consider the problem of learning an $varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Key to our solution is a novel projection technique based on ideas from harmonic analysis. Our result bridges the gap between two popular but conflicting perspectives on continuous-space MDPs.
  arXiv  Detail & Related papers  (2024-05-10T09:58:47Z)
• Topology-aware Generalization of Decentralized SGD [91.59494285490784]
  We show that the generalizability of D-SGD is positively correlated with the spectral gap.<n>To our best knowledge, this is the first work on the generalization of D-SGD.
  arXiv  Detail & Related papers  (2022-06-25T16:03:48Z)
• Variance-Aware Confidence Set: Variance-Dependent Bound for Linear Bandits and Horizon-Free Bound for Linear Mixture MDP [76.94328400919836]
  We show how to construct variance-aware confidence sets for linear bandits and linear mixture Decision Process (MDP) For linear bandits, we obtain an $widetildeO(mathrmpoly(d)sqrt1 + sum_i=1Ksigma_i2) regret bound, where $d is the feature dimension. For linear mixture MDP, we obtain an $widetildeO(mathrmpoly(d)sqrtK)$ regret bound, where
  arXiv  Detail & Related papers  (2021-01-29T18:57:52Z)
• SDP Achieves Exact Minimax Optimality in Phase Synchronization [19.909352968029584]
  We study the phase synchronization problem with noisy measurements $Y=z*z*+sigma WinmathbbCntimes ntimes n. We prove that SDP achieves error bound $ (1+o)fracnp22np$ under a squared $ell$ loss.
  arXiv  Detail & Related papers  (2021-01-07T03:14:05Z)
• Optimal Robust Linear Regression in Nearly Linear Time [97.11565882347772]
  We study the problem of high-dimensional robust linear regression where a learner is given access to $n$ samples from the generative model $Y = langle X,w* rangle + epsilon$ We propose estimators for this problem under two settings: (i) $X$ is L4-L2 hypercontractive, $mathbbE [XXtop]$ has bounded condition number and $epsilon$ has bounded variance and (ii) $X$ is sub-Gaussian with identity second moment and $epsilon$ is
  arXiv  Detail & Related papers  (2020-07-16T06:44:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.