The relative importance of being Gaussian

• URL: http://arxiv.org/abs/2507.08059v1
• Date: Thu, 10 Jul 2025 14:51:39 GMT
• Title: The relative importance of being Gaussian
• Authors: F. Alberto Grünbaum, Tondgi Xu,
• Abstract summary: We study the performance of the algorithm when used with noise that is very far in nature from the Gaussian case.<n>Experiments are all carried out on a small laptop and for the smallest possible image size.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: The remarkable results for denoising in computer vision using diffusion models given in \cite{SDWMG,HJA,HHG} yield a robust mathematical justification for algorithms based on crucial properties of a sequence of Gaussian independent $N(0,1)$ random variables. In particular the derivations use the fact that a Gaussian distribution is determined by its mean and variance and that the sum of two Gaussians is another Gaussian. \bigskip The issue raised in this short note is the following: suppose we use the algorithm without any changes but replace the nature of the noise and use, for instance, uniformly distributed noise or noise with a Beta distribution, or noise which is a random superposition of two Gaussians with very different variances. One could, of course, try to modify the algorithm keeping in mind the nature of the noise, but this is not what we do. Instead we study the performance of the algorithm when used with noise that is very far in nature from the Gaussian case, where it is designed to work well. Usually these algorithms are implemented on very powerful computers. Our experiments are all carried out on a small laptop and for the smallest possible image size. Exploring how our observations are confirmed or changed when dealing in different situations remains an interesting challenge.

Related papers

• Better Gaussian Mechanism using Correlated Noise [1.450405446885067]
  We show that adding a random variable distributed as a Gaussian with variance scaled by $(sqrtd + 1)/4$ to all counts allows us to reduce the variance of the independent noise samples to scale only with $(d + sqrtd)/4$.<n>The central idea of our mechanism is simple and the technique is flexible.
  arXiv  Detail & Related papers  (2024-08-13T12:31:03Z)
• Learning Mixtures of Gaussians Using Diffusion Models [9.118706387430883]
  We give a new algorithm for learning mixtures of $k$ Gaussians to TV error $varepsilon$, with quasi-polynomial ($O(ntextpoly,logleft(fracn+kvarepsilonright))$) time and sample complexity.<n>Results extend to continuous mixtures of Gaussians where the mixing distribution is supported on a union of $k$ balls of constant radius.
  arXiv  Detail & Related papers  (2024-04-29T17:00:20Z)
• Already Moderate Population Sizes Provably Yield Strong Robustness to Noise [53.27802701790209]
  We show that two evolutionary algorithms can tolerate constant noise probabilities without increasing the runtime on the OneMax benchmark. Our results are based on a novel proof argument that the noiseless offspring can be seen as a biased uniform crossover between the parent and the noisy offspring.
  arXiv  Detail & Related papers  (2024-04-02T16:35:52Z)
• Some Constructions of Private, Efficient, and Optimal $K$-Norm and Elliptic Gaussian Noise [54.34628844260993]
  Differentially private computation often begins with a bound on some $d$-dimensional statistic's sensitivity. For pure differential privacy, the $K$-norm mechanism can improve on this approach using a norm tailored to the statistic's sensitivity space. This paper solves both problems for the simple statistics of sum, count, and vote.
  arXiv  Detail & Related papers  (2023-09-27T17:09:36Z)
• Gradient-free optimization of highly smooth functions: improved analysis and a new algorithm [87.22224691317766]
  This work studies problems with zero-order noisy oracle information under the assumption that the objective function is highly smooth. We consider two kinds of zero-order projected gradient descent algorithms.
  arXiv  Detail & Related papers  (2023-06-03T17:05:13Z)
• Optimizing the Noise in Self-Supervised Learning: from Importance Sampling to Noise-Contrastive Estimation [80.07065346699005]
  It is widely assumed that the optimal noise distribution should be made equal to the data distribution, as in Generative Adversarial Networks (GANs) We turn to Noise-Contrastive Estimation which grounds this self-supervised task as an estimation problem of an energy-based model of the data. We soberly conclude that the optimal noise may be hard to sample from, and the gain in efficiency can be modest compared to choosing the noise distribution equal to the data's.
  arXiv  Detail & Related papers  (2023-01-23T19:57:58Z)
• Higher degree sum-of-squares relaxations robust against oblivious outliers [14.58610686291355]
  We consider estimation models of the form $Y=X*+N$, where $X*$ is some $m$-dimensional signal we wish to recover. We introduce a family of algorithms that under mild assumptions recover the signal $X*$ in all estimation problems for which there exists a sum-of-squares algorithm.
  arXiv  Detail & Related papers  (2022-11-14T13:09:12Z)
• Target Aware Poisson-Gaussian Noise Parameters Estimation from Noisy Images [0.0]
  We use a Poisson-Gaussian noise model for the raw-images captured by the sensor. We propose two algorithms based on variance and cumulant statistics.
  arXiv  Detail & Related papers  (2022-10-21T17:53:56Z)
• The Optimal Noise in Noise-Contrastive Learning Is Not What You Think [80.07065346699005]
  We show that deviating from this assumption can actually lead to better statistical estimators. In particular, the optimal noise distribution is different from the data's and even from a different family.
  arXiv  Detail & Related papers  (2022-03-02T13:59:20Z)
• Shape Matters: Understanding the Implicit Bias of the Noise Covariance [76.54300276636982]
  Noise in gradient descent provides a crucial implicit regularization effect for training over parameterized models. We show that parameter-dependent noise -- induced by mini-batches or label perturbation -- is far more effective than Gaussian noise. Our analysis reveals that parameter-dependent noise introduces a bias towards local minima with smaller noise variance, whereas spherical Gaussian noise does not.
  arXiv  Detail & Related papers  (2020-06-15T18:31:02Z)
• The Discrete Gaussian for Differential Privacy [26.179150185540514]
  A key tool for building differentially private systems is adding Gaussian noise to the output of a function evaluated on a sensitive dataset. Previous work has demonstrated that seemingly innocuous numerical errors can entirely destroy privacy. We introduce and analyze the discrete Gaussian in the context of differential privacy.
  arXiv  Detail & Related papers  (2020-03-31T18:00:00Z)

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.