Unifilarisation of stochastic Mealy machines is an instance of coalgebraic determinisation over monads with support structure, producing causal stochastic behaviours rather than Moore-style output distributions.
Title resolution pending
13 Pith papers cite this work, alongside 788 external citations. Polarity classification is still indexing.
13
Pith papers citing it
788
external citations · Crossref
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 13representative citing papers
Reformulation invariance on inference problems forces minimization of the Kullback-Leibler divergence, narrowing from f-divergences to alpha-divergences to KL.
The normalized inverse-scale direction of LayerNorm's affine parameters is an exact algebraic kernel of the post-final-norm centred activation covariance for any input distribution in LayerNorm transformers.
Dead directions recover Watanabe's RLCT contribution and triple (λ, m, ν) from directional Fisher curvature decay rates in original parameter space for singular models, extended via K-FAC to networks and gauge-equivariant optimizers.
Projection heads act as geometric buffers; nonlinear heads induce negative Hessian curvature to escape dimensional collapse while linear heads rely on discrete dynamics and BatchNorm.
Zeno elimination via Schur complement in GKSL dynamics induces negative directions in quadratic response tensors even when the microscopic tensor is positive definite.
Residual network Jacobians under Frobenius normalization have singular spectra that form trace-normalized Cartan orbits satisfying slack-aware margin inequalities bounding exponent drift to order (log M)/L in zero-slack cases.
The proximal Galerkin method reformulates phase-field fracture constraints into saddle-point problems to enforce physical bounds and irreversibility for static and dynamic cases.
Latent diffusability is quantified by decomposing the MMSE rate along diffusion trajectories into Fisher Information and Fisher Information Rate, with three geometric penalties (dimensional compression, tangential distortion, curvature injection) identified as sources of failure.
The optimal weighted total loss decays as exp(-n times weighted Chernoff information) when the context weight factors across observations.
Proposes a body-grounded perspective model for AI agents using interoceptive viability signals, a Fisher-style metric on fused states, and conative alignment to produce stable body-directed behavior in a reward-free gridworld.
The Kerimov-Alekberli model uses KL divergence on a Riemannian manifold with a Fisher-derived threshold and the Landauer principle to treat adversarial perturbations as measurable physical work for real-time AI system stability.
citing papers explorer
-
Bayesian updates from coalgebraic determinisation
Unifilarisation of stochastic Mealy machines is an instance of coalgebraic determinisation over monads with support structure, producing causal stochastic behaviours rather than Moore-style output distributions.
-
Reformulation Invariance and the Axiomatic Foundations of Inference
Reformulation invariance on inference problems forces minimization of the Kullback-Leibler divergence, narrowing from f-divergences to alpha-divergences to KL.
-
Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale
The normalized inverse-scale direction of LayerNorm's affine parameters is an exact algebraic kernel of the post-final-norm centred activation covariance for any input distribution in LayerNorm transformers.
-
Dead Directions: Geometric Singular Learning
Dead directions recover Watanabe's RLCT contribution and triple (λ, m, ν) from directional Fisher curvature decay rates in original parameter space for singular models, extended via K-FAC to networks and gauge-equivariant optimizers.
-
The Geometry of Projection Heads: Conditioning, Invariance, and Collapse
Projection heads act as geometric buffers; nonlinear heads induce negative Hessian curvature to escape dimensional collapse while linear heads rely on discrete dynamics and BatchNorm.
-
Signature structure of quadratic response under Zeno-Schur coarse graining in open quantum systems
Zeno elimination via Schur complement in GKSL dynamics induces negative directions in quadratic response tensors even when the microscopic tensor is positive definite.
-
Geometric and Spectral Alignment for Deep Neural Network I
Residual network Jacobians under Frobenius normalization have singular spectra that form trace-normalized Cartan orbits satisfying slack-aware margin inequalities bounding exponent drift to order (log M)/L in zero-slack cases.
-
Proximal Galerkin for Phase Field Fracture
The proximal Galerkin method reformulates phase-field fracture constraints into saddle-point problems to enforce physical bounds and irreversibility for static and dynamic cases.
-
Understanding Latent Diffusability via Fisher Geometry
Latent diffusability is quantified by decomposing the MMSE rate along diffusion trajectories into Fisher Information and Fisher Information Rate, with three geometric penalties (dimensional compression, tangential distortion, curvature injection) identified as sources of failure.
-
Weighted Chernoff information and optimal loss exponent in context-sensitive hypothesis testing
The optimal weighted total loss decays as exp(-n times weighted Chernoff information) when the context weight factors across observations.
-
Body-Grounded Perspective Formation and Conative Attunement in Artificial Agents
Proposes a body-grounded perspective model for AI agents using interoceptive viability signals, a Fisher-style metric on fused states, and conative alignment to produce stable body-directed behavior in a reward-free gridworld.
-
The Kerimov-Alekberli Model: An Information-Geometric Framework for Real-Time System Stability
The Kerimov-Alekberli model uses KL divergence on a Riemannian manifold with a Fisher-derived threshold and the Landauer principle to treat adversarial perturbations as measurable physical work for real-time AI system stability.
- Measuring Primitive Accumulation: An Information-Theoretic Approach to Capitalist Enclosure in PIK2, Indonesia