Protocol learns k-local Lindbladians to ε accuracy with Õ(n^{2k}/ε²) samples and projects to valid generators; improves to log n under sparsity assumptions.
super hub Canonical reference
Scale-Free Networks: Complex Webs in Nature and Technology
Canonical reference. 87% of citing Pith papers cite this work as background.
157
Pith papers citing it
Background
87% of classified citations
hub tools
citation-role summary
background 29
method 1
citation-polarity summary
authors
co-cited works
representative citing papers
Stochastic inflation emerges as GKLS open-system dynamics from tracing entangled modes entering a coarse-grained de Sitter patch, reproducing the classical phase-space Fokker-Planck equation.
Horizon-free pure-DP algorithm achieves optimal gap-dependent regret bound 1000*(log K/Δ_min + log K/ε) for stochastic online learning with K actions.
A framework for optimal posterior e-values with non-convex composite hypotheses, demonstrated via statistical tests for multiple voting systems including the first treatment of Schulze.
A coherence law based on the readout-visible aligned coherence rate (a Rayleigh quotient of the noise generator) predicts gradient survival in noisy U(1)-equivariant QNNs, with simulations confirming R²=0.979 and a special channel test showing no loss where predicted.
Transformer residual layers are approximated as an explicit Euler scheme for a controlled hidden-state flow whose mean-field limit is a first-order transport control problem with Pontryagin terminal condition given by the softmax residual.
First integrated spiking controller combining bipedal locomotion and arm control on a full-scale humanoid via NEF, SPA, and basal ganglia, validated in Nengo-Isaac Sim co-simulation.
DeepPolaron ML-MD simulations show rutile electrons form Ti-localized polarons hopping along [001] with 39 meV barrier and 4.4e-2 cm2/Vs mobility, while anatase holes form O-localized polarons hopping to second neighbors with 139 meV barrier and 1.4e-3 cm2/Vs mobility.
Proves future global stability and explicit decay rates for small perturbations of Maxwell-Jüttner equilibria (and vacuum for q > 1/3) of the massless Boltzmann equation on FLRW backgrounds with scale factor t^q, q in [0,1].
Presents a quantum soft PCA framework with Fermi-Dirac filter for principal subspace scoring without eigenvector recovery, claiming dimension-independent sample complexity O(η^{-2}).
Gradient Transformer learns to map TinyLM update vectors to LLM update vectors for data-free knowledge distillation using correlations from shadow datasets.
Training-language dominance, not English inherent properties, determines brain-LLM alignment across English, Chinese, and French, with additional independent effects from typological distance concentrated in syntactic brain regions.
Proposes a scale-calibrated median-of-means estimator for robust aggregation of distributed PCA estimates on the product of Euclidean space and Grassmann manifold.
Introduces De Simone laws over Kleisli categories that guarantee compositionality of coalgebraic trace equivalence and recovers the classical De Simone format while adding a probabilistic variant.
Aggregation mechanisms for surjective classifications are nearly dictatorial with high probability unless functions are nearly constant, with a full characterization of always-surjective mechanisms.
Derives covariant quadratic expansion in extrinsic curvature of the nonlocal effective action for a massless scalar field on manifolds with boundary, extending Monge-patch results to general surfaces.
The paper presents randomized tests with explicit query bounds for properties including number of leaves, maximum degree, typical distance, and diameter in tree-structured graphical models.
A solvable hierarchical model with power-law feature strengths yields explicit power-law scaling of prediction error through sequential recovery of latent directions by a layer-wise spectral algorithm.
Bayesian PLSs are special cases of non-stationary affine PIMs which are proven calibrated, and affine tracing automates construction of probabilistic iterative methods from classical code.
Moonflowers are introduced as set families with per-set unique elements, yielding near-optimal extremal bounds that enable logarithmic code sparsification with a matching lower bound.
Projective Kummer-type manifolds with finite-order symplectic birational self-maps acting nontrivially on H² are twisted modular except for Picard rank 3 cases characterized by their NS lattices; specific Mukai vectors are identified for finite-order wall-crossing maps on modular examples.
SGD, approximations of Newton's method, natural gradient descent, and Adam are proven compatible with evolutionary dynamics when augmented with DLS noise, turning them into valid in silico simulations of asexual Darwinian evolution.
Polynomial-time algorithm samples the Sherrington-Kirkpatrick Gibbs measure at beta < 1/2 with o(1) TVD error by combining potential Hessian ascent, stochastic localization, covariance estimates, and Jarzynski equality with rejection sampling.
The profile maximum likelihood estimator for the location in anisotropic hyperbolic wrapped normal models is strongly consistent, asymptotically normal, and attains the Hájek-Le Cam minimax lower bound under squared geodesic loss.
citing papers explorer
-
Brain-LLM Alignment Tracks Training Data, Not Typology
Training-language dominance, not English inherent properties, determines brain-LLM alignment across English, Chinese, and French, with additional independent effects from typological distance concentrated in syntactic brain regions.
-
On the Emergence of Syntax by Means of Local Interaction
A 2D neural cellular automaton spontaneously self-organizes into a Proto-CKY representation that exhibits syntactic processing capabilities for context-free grammars when trained on membership problems.
-
Saying More Than They Know: A Framework for Quantifying Epistemic-Rhetorical Miscalibration in Large Language Models
LLMs display a consistent pattern of elevated form-meaning divergence and uniform rhetorical device use in argumentative texts compared to humans, quantified by new metrics FMD, GPR, and RDDE.
-
When transformers learn "impossible" languages, what do they learn?
Transformers on impossible-language variants show gradual grammatical sensitivity loss but sharp long-sentence generation failures, supporting generative deficiency as a link to non-attestation.
-
Syntactic Belief Update as the Driver of Garden Path Processing Difficulty
Syntactic belief update via generalized Rényi divergence on syntactic trees predicts garden path reading times better than lexical surprisal.
-
Agent-based models for the evolution of morphological alternation patterns
Multi-agent simulations with naturalistic lexicons and phonological rules show scale-free networks and Bernoulli adoption produce more plausible morphologies, evaluated by an LLM historical linguist debate system and tested via historical case studies.
-
Child-directed speech facilitates production, not comprehension, in BabyLMs
CDS-trained BabyLMs show earlier and more appropriate production in a new frame-completion task while FineWeb-edu models lead on comprehension benchmarks, indicating current tests underestimate CDS benefits.
-
Model Collapse as Cultural Evolution
Iterated learning theory predicts and LLM experiments confirm non-monotonic compositionality during self-training, reframing model collapse as cultural transmission with matching human regularization patterns.
-
Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer
Fine-tuning LLMs on Arabic yields similar zero-shot gains on Semitic and non-Semitic languages, with chain-of-thought reasoning producing parallel benefits, indicating task alignment drives transfer more than language relatedness.
-
SimSiam Naming Game: A Unified Approach for Representation Learning and Emergent Communication
SSNG replaces sampling-based updates in MHNG with symmetric self-supervised representation alignment using Gumbel-Softmax for discrete messages, yielding higher linear-probe classification accuracy on CIFAR-10 and ImageNet-100 than referential, reconstruction, or MHNG baselines.
-
Rethinking the Idiomaticity Decomposability Hypothesis: Evidence from Distributional Learning
Language models show idiom decomposability correlates weakly with human judgments, negatively with syntactic flexibility, and contributes most strongly to representation stabilization during training alongside surprisal and frequency.
-
Readers make targeted regressions to plausible errors in reanalysis of "noisy-channel garden-path" sentences
Readers direct regressions to plausible error sites in noisy-channel garden-path sentences, consistent with Bayesian reanalysis under a noisy-channel model.