Higher Nishimori Criticality and Exact Results at the Learning Transition of Deformed Toric Codes

• URL: http://arxiv.org/abs/2604.06324v1
• Date: Tue, 07 Apr 2026 18:00:43 GMT
• Title: Higher Nishimori Criticality and Exact Results at the Learning Transition of Deformed Toric Codes
• Abstract summary: We revisit a learning-induced tricritical point, at which three phases with strong, weak, and broken $Z$ symmetry meet.<n>This setting is exactly dual to a classical Bayesian inference phase diagram of the $2D$ classical Ising model.<n>We show that the power-law exponent of the Edwards-Anderson correlation function is exactly equal to that of the spin correlation function at the unmeasured Ising critical point.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We revisit a learning-induced tricritical point, at which three phases with strong, weak, and broken $Z_2$ symmetry meet, in the phase diagram of a deformed toric code wavefunction subjected to weak measurements. This setting is exactly dual to a classical Bayesian inference phase diagram of the $2D$ classical Ising model. Here we demonstrate that this tricritical point lies on a distinct $\textit{higher Nishimori line}$, which has an emergent gauge-invariant formulation, just like the ordinary Nishimori line but with a higher replica symmetry as a replica stat-mech model in the replica number $R\rightarrow2$ limit, where disorder is averaged according to the Born rule. As such, the learning tricritical point is in fact a $\textit{higher Nishimori critical point}$. Using this identification, we obtain a number of $\textit{exact results}$ at this $\textit{higher}$ Nishimori critical point; e.g., we show that the power-law exponent of the Edwards-Anderson correlation function is exactly equal to that of the spin correlation function at the unmeasured Ising critical point and verify this in numerical simulations. Using the tools of the proof of a $c$-effective theorem [arXiv:2507.07959], we show that the Casimir effective central charge $c_{\text{eff}}$ $\textit{decreases}$ under renormalization group (RG) flow from the $\textit{higher}$ Nishimori critical point to the unmeasured $2D$ Ising critical point, and is thus greater than $1/2$. This is corroborated by extensive numerical simulations finding $c_{\text{eff}} = 0.522(1)$. The analytical result also explains, with a physically motivated assumption, the numerically observed increase of the Casimir effective central charge under the RG flow from the ordinary Nishimori critical point to the clean Ising critical point in the random-bond Ising model. We also discuss $\textit{higher}$ Nishimori criticality in general dimensions $D>1$.

Related papers

• Learning Potts Models and $Z_3$ Toric Codes: Higher and Ordinary Nishimori Criticality [0.35185044688786976]
  We identify a $it higher$ Nishimori line in the learning phase diagram of the $2D$ $q$-state Potts model.<n>This line meets the critical temperature line of the Potts model, in a $it higher$ Nishimori critical point.
  arXiv  Detail & Related papers  (2026-08-20T17:06:53Z)
• Nishimori Threshold Estimation for Bayesian Inference and $\mathbb{Z}_q$ Surface Code Decoding [0.4910937238451485]
  We introduce an analytical estimate of error thresholds falling into the Nishimori universality class via a Fourier--Walsh projection scheme.<n>We find that the threshold values not only accurately agree with recent decohered-$mathbb Z_q$-toric-code numerics, but are found to satisfy the Gilbert-Varshamov self-dual entropy relation.<n>Our approach thereby points to a deeper connection between the clean and Born-disordered models, while allowing for instant analytical estimates of error thresholds for a variety of stabilizer codes.
  arXiv  Detail & Related papers  (2026-07-20T18:00:00Z)
• How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis [53.063298916923976]
  We study the feedback in a Gaussian single-index model with $r*(x) = *(langle *, xrangle)$ and $x sim N(0, I_d)$.<n>We analyze a two-stage neural reward model that first learns the hidden direction $*$ from reward-weighted samples and then fits the readout layer by weighted ridge regression.
  arXiv  Detail & Related papers  (2026-05-23T22:00:38Z)
• 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)
• Stateful Reasoning via Insight Replay [51.85629502016196]
  Chain-of-Thought (CoT) reasoning has become a foundation for eliciting multi-step reasoning in large language models.<n>We identify a major cause of this phenomenon: as the CoT grows, the model's attention to critical insights produced earlier in the trace gradually weakens.<n>We propose textbfInsightReplay, a stateful reasoning approach in which the model periodically extracts critical insights from its reasoning trace and replays them near the active generation frontier.
  arXiv  Detail & Related papers  (2026-05-14T06:52:59Z)
• Convergence Rate Analysis of LION [54.28350823319057]
  LION converges iterations of $cal(sqrtdK-)$ measured by gradient Karush-Kuhn-T (sqrtdK-)$. We show that LION can achieve lower loss and higher performance compared to standard SGD.
  arXiv  Detail & Related papers  (2024-11-12T11:30:53Z)
• Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis [55.561961365113554]
  3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in novel view synthesis (NVS)<n>In this paper, we introduce Self-Ensembling Gaussian Splatting (SE-GS)<n>We achieve self-ensembling by incorporating an uncertainty-aware perturbation strategy during training.<n> Experimental results on the LLFF, Mip-NeRF360, DTU, and MVImgNet datasets demonstrate that our approach enhances NVS quality under few-shot training conditions.
  arXiv  Detail & Related papers  (2024-10-31T18:43:48Z)
• KPZ scaling from the Krylov space [83.88591755871734]
  Recently, a superdiffusion exhibiting the Kardar-Parisi-Zhang scaling in late-time correlators and autocorrelators has been reported. Inspired by these results, we explore the KPZ scaling in correlation functions using their realization in the Krylov operator basis.
  arXiv  Detail & Related papers  (2024-06-04T20:57:59Z)
• Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback [58.66941279460248]
  Learning from human feedback plays an important role in aligning generative models, such as large language models (LLM)<n>We study a model within this domain--contextual dueling bandits with adversarial feedback, where the true preference label can be flipped by an adversary.<n>We propose an algorithm namely robust contextual dueling bandits (RCDB), which is based on uncertainty-weighted maximum likelihood estimation.
  arXiv  Detail & Related papers  (2024-04-16T17:59:55Z)
• Emergent criticality in a constrained boson model [0.0]
  We show, via explicit computation on a constrained bosonic model, that the presence of subsystem symmetries can lead to a quantum phase transition.<n>We verify this scenario via explicit exact-diagonalization computations, provide an effective Landau-Ginzburg theory for such a transition, and discuss the connection of our model to the PXP model describing Rydberg atom arrays.
  arXiv  Detail & Related papers  (2023-11-20T19:00:03Z)
• Measurement-induced phase transition for free fermions above one dimension [46.176861415532095]
  Theory of the measurement-induced entanglement phase transition for free-fermion models in $d>1$ dimensions is developed. Critical point separates a gapless phase with $elld-1 ln ell$ scaling of the second cumulant of the particle number and of the entanglement entropy.
  arXiv  Detail & Related papers  (2023-09-21T18:11:04Z)
• Nonequilibrium critical dynamics of the two-dimensional $\pm J$ Ising model [0.023787965910387825]
  The $pm J$ Ising model is a simple frustrated spin model, where the exchange couplings independently take the discrete value $-J$ with probability $p$ and $+J$ with probability $1-p$. Here, we investigate the nonequilibrium critical behavior of the two-dimensional $pm J$ Ising model, after a quench from different initial conditions to a critical point $T_c(p)$ on the paramagnetic-ferromagnetic (PF) transition line.
  arXiv  Detail & Related papers  (2023-04-24T11:02:33Z)
• Causal Bandits for Linear Structural Equation Models [58.2875460517691]
  This paper studies the problem of designing an optimal sequence of interventions in a causal graphical model. It is assumed that the graph's structure is known and has $N$ nodes. Two algorithms are proposed for the frequentist (UCB-based) and Bayesian settings.
  arXiv  Detail & Related papers  (2022-08-26T16:21:31Z)
• Kondo effect in a non-Hermitian, $\mathcal{PT}$-symmetric Anderson model with Rashba spin-orbit coupling [3.1013276969076666]
  We show that for a non-Hermitian hybridization, $lambda$ can renormalize the exceptional point even in the non-interacting case. We show that in the strong coupling regime, $lambda$ and interactions co-operate in strongly reducing the critical point associated with Kondo destruction.
  arXiv  Detail & Related papers  (2022-01-01T12:03:47Z)

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.