PRISM: Principled Reference Identification for Schrodinger Bridge Model

• URL: http://arxiv.org/abs/2608.06893v1
• Date: Fri, 07 Aug 2026 07:25:19 GMT
• Title: PRISM: Principled Reference Identification for Schrodinger Bridge Model
• Abstract summary: We develop PRISM, a theory of bridge reference design.<n>We prove an invisibility principle: with the exact drift and unlimited solver steps, every admissible reference recovers the true posterior.<n>Experiments show that noise color and temporal scheduling are interchangeable, and regularization shifts the optimal reference toward white noise.
• Score: 30.25013471217802
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Schrödinger bridge models restore a clean signal from a degraded observation by following the conditional bridges of a reference process, yet this reference is chosen heuristically, typically white noise with a hand-tuned schedule. We develop PRISM, a theory of bridge reference design. We characterize the time-varying Gaussian references that remain exactly tractable with per-mode schedules: precisely those whose instantaneous covariances commute. We then prove an invisibility principle: with the exact drift and unlimited solver steps, every admissible reference recovers the true posterior. The choice of reference therefore matters only under finite computational resources. For a fixed step budget, we derive the finite-step objective in closed form and prove that every optimal noise spectrum is proportional to Pk, the spectrum of information destroyed by the sensor, with a mode-independent constant x*(T) = (2 ln T)^-1/2 (1 + o(1)). The analysis shows that noise color and temporal scheduling are interchangeable, and regularization provably shifts the optimal reference toward white noise. Experiments in Gaussian settings confirm the predicted orderings and the closed-form loss floors. On FFHQ, the distortion-- perception trade-off and spectral localization transfer, but white noise outperforms the matched reference; a pre-registered study that changes the training regime refutes ridge whitening as the explanation. A 2x2 mechanism study then traces the inversion to the non-Gaussian per-mode statistics of real images. PRISM turns reference design from a hyperparameter sweep into a calculation in the Gaussian regime, and locates exactly where real images break it.

Related papers

• Relational Wigner-Smith Duration in Wheeler-DeWitt Scattering [0.0]
  A closed Friedmann-Lemaitre-Robertson-Walker Wheeler-DeWitt model is formulated as an exact reflection problem.<n>An analytic expression is obtained for this duration, its classical recollapse limit, and the leading quantum correction.<n>Results define duration and transition observables entirely through correlations and scattering records of a stationary constrained state.
  arXiv  Detail & Related papers  (2026-08-18T06:32:09Z)
• Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability [51.56484100374058]
  We prove the first identifiability theorem for a mechanistic-interpretability primitive.<n>The spectrum is an identifiable, model-intrinsic fingerprint with a stated error bar, not a legible decomposition.
  arXiv  Detail & Related papers  (2026-08-10T19:42:01Z)
• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• A Spectral Theory of Normalized Corrected GNN Propagation [2.9801823421431854]
  We develop a spectral theory for emphnormalized corrected GNN propagation.<n>The central theoretical question is whether this corrected normalized operator preserves class-discnative signal after many propagation layers.<n>We also establish a multi-class partial recovery theorem showing contraction toward class centers for most nodes.
  arXiv  Detail & Related papers  (2026-06-22T16:38:50Z)
• Metropolis-Adjusted Diffusion Models [39.6979566317926]
  Sampling from score-based diffusion models incurs bias due to time discretisation and the approximation of the score function.<n>We introduce the first exact method for adjusting Langevin corrections in diffusion models, based on a two-coin Bernoulli factory algorithm.
  arXiv  Detail & Related papers  (2026-05-10T16:57:51Z)
• Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction [45.25461515976432]
  Plug-and-Play diffusion prior (DP) frameworks have emerged as a powerful paradigm for imaging reconstruction.<n>We present a novel approach to resolving bias-hallucination trade-off, achieving state-of-the-art gradients with significantly accelerated convergence.
  arXiv  Detail & Related papers  (2026-02-26T16:58:43Z)
• On the Wasserstein Convergence and Straightness of Rectified Flow [54.580605276017096]
  Rectified Flow (RF) is a generative model that aims to learn straight flow trajectories from noise to data.<n>We provide a theoretical analysis of the Wasserstein distance between the sampling distribution of RF and the target distribution.<n>We present general conditions guaranteeing uniqueness and straightness of 1-RF, which is in line with previous empirical findings.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• Modelling 1/f Noise in TRNGs via Fractional Brownian Motion [1.3053649021965603]
  Security of random number generators is not fully understood due to complex $1/falpha$ phase noise.<n>We introduce fractional Brownian motion as a comprehensive theoretical framework, capturing power-law spectral densities from white to flicker frequency noise.
  arXiv  Detail & Related papers  (2024-10-18T06:38:34Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• Detecting Label Noise via Leave-One-Out Cross Validation [0.0]
  We present a simple algorithm for identifying and correcting real-valued noisy labels from a mixture of clean and corrupted samples. A heteroscedastic noise model is employed, in which additive Gaussian noise terms with independent variances are associated with each and all of the observed labels. We show that the presented method can pinpoint corrupted samples and lead to better regression models when trained on synthetic and real-world scientific data sets.
  arXiv  Detail & Related papers  (2021-03-21T10:02:50Z)
• Gaussian MRF Covariance Modeling for Efficient Black-Box Adversarial Attacks [86.88061841975482]
  We study the problem of generating adversarial examples in a black-box setting, where we only have access to a zeroth order oracle. We use this setting to find fast one-step adversarial attacks, akin to a black-box version of the Fast Gradient Sign Method(FGSM) We show that the method uses fewer queries and achieves higher attack success rates than the current state of the art.
  arXiv  Detail & Related papers  (2020-10-08T18:36:51Z)
• Uncertainty Inspired RGB-D Saliency Detection [70.50583438784571]
  We propose the first framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Inspired by the saliency data labeling process, we propose a generative architecture to achieve probabilistic RGB-D saliency detection. Results on six challenging RGB-D benchmark datasets show our approach's superior performance in learning the distribution of saliency maps.
  arXiv  Detail & Related papers  (2020-09-07T13:01:45Z)

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.