Predicting integers from continuous parameters

• URL: http://arxiv.org/abs/2602.10751v1
• Date: Wed, 11 Feb 2026 11:30:48 GMT
• Title: Predicting integers from continuous parameters
• Authors: Bas Maat, Peter Bloem,
• Abstract summary: We study the problem of predicting numeric labels that are constrained to the integers or to a subrange of the integers.<n>For example, the number of up-votes on social media posts, or the number of bicycles available at a public rental station.<n>While it is possible to model these as continuous values, and to apply traditional regression, this approach changes the underlying distribution on the labels from discrete to continuous.
• Score: 0.08594140167290099
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the problem of predicting numeric labels that are constrained to the integers or to a subrange of the integers. For example, the number of up-votes on social media posts, or the number of bicycles available at a public rental station. While it is possible to model these as continuous values, and to apply traditional regression, this approach changes the underlying distribution on the labels from discrete to continuous. Discrete distributions have certain benefits, which leads us to the question whether such integer labels can be modeled directly by a discrete distribution, whose parameters are predicted from the features of a given instance. Moreover, we focus on the use case of output distributions of neural networks, which adds the requirement that the parameters of the distribution be continuous so that backpropagation and gradient descent may be used to learn the weights of the network. We investigate several options for such distributions, some existing and some novel, and test them on a range of tasks, including tabular learning, sequential prediction and image generation. We find that overall the best performance comes from two distributions: Bitwise, which represents the target integer in bits and places a Bernoulli distribution on each, and a discrete analogue of the Laplace distribution, which uses a distribution with exponentially decaying tails around a continuous mean.

Related papers

• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Survey of Data-driven Newsvendor: Unified Analysis and Spectrum of Achievable Regrets [6.356813626290215]
  In the Newsvendor problem, the goal is to guess the number that will be drawn from some distribution.<n>In the data-driven version, the distribution is unknown, and one must work with samples from the distribution.<n>This paper studies all combinations of these variants, filling in many gaps in the literature and simplifying many proofs.
  arXiv  Detail & Related papers  (2024-09-05T13:19:08Z)
• Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion [61.03681839276652]
  Diffusion Forcing is a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels.<n>We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens.
  arXiv  Detail & Related papers  (2024-07-01T15:43:25Z)
• Generative Assignment Flows for Representing and Learning Joint Distributions of Discrete Data [2.6499018693213316]
  We introduce a novel generative model for the representation of joint probability distributions of discrete random variables.<n>The approach uses measure transport by randomized assignment flows on the statistical submanifold of factorizing distributions.
  arXiv  Detail & Related papers  (2024-06-06T21:58:33Z)
• An Improved Algorithm for Learning Drifting Discrete Distributions [2.2191203337341525]
  We present a new adaptive algorithm for learning discrete distributions under distribution drift. We observe a sequence of independent samples from a discrete distribution that is changing over time, and the goal is to estimate the current distribution. To use more samples, we must resort to samples further in the past, and we incur a drift error due to the bias introduced by the change in distribution. We present a novel adaptive algorithm that can solve this trade-off without any prior knowledge of the drift.
  arXiv  Detail & Related papers  (2024-03-08T16:54:27Z)
• A Heavy-Tailed Algebra for Probabilistic Programming [53.32246823168763]
  We propose a systematic approach for analyzing the tails of random variables. We show how this approach can be used during the static analysis (before drawing samples) pass of a probabilistic programming language compiler. Our empirical results confirm that inference algorithms that leverage our heavy-tailed algebra attain superior performance across a number of density modeling and variational inference tasks.
  arXiv  Detail & Related papers  (2023-06-15T16:37:36Z)
• Wrapped Distributions on homogeneous Riemannian manifolds [58.720142291102135]
  Control over distributions' properties, such as parameters, symmetry and modality yield a family of flexible distributions. We empirically validate our approach by utilizing our proposed distributions within a variational autoencoder and a latent space network model.
  arXiv  Detail & Related papers  (2022-04-20T21:25:21Z)
• Learning Group Importance using the Differentiable Hypergeometric Distribution [16.30064635746202]
  partitioning elements into subsets of unknown sizes is essential in many applications. In this work, we propose the differentiable hypergeometric distribution. We show that we can learn the size of subsets in two typical applications: weakly-supervised learning and clustering.
  arXiv  Detail & Related papers  (2022-03-03T10:44:50Z)
• Personalized Trajectory Prediction via Distribution Discrimination [78.69458579657189]
  Trarimiy prediction is confronted with the dilemma to capture the multi-modal nature of future dynamics. We present a distribution discrimination (DisDis) method to predict personalized motion patterns. Our method can be integrated with existing multi-modal predictive models as a plug-and-play module.
  arXiv  Detail & Related papers  (2021-07-29T17:42:12Z)
• Probabilistic Kolmogorov-Arnold Network [1.4732811715354455]
  The present paper proposes a method for estimating probability distributions of the outputs in the case of aleatoric uncertainty. The suggested approach covers input-dependent probability distributions of the outputs, as well as the variation of the distribution type with the inputs. Although the method is applicable to any regression model, the present paper combines it with KANs, since the specific structure of KANs leads to computationally-efficient models' construction.
  arXiv  Detail & Related papers  (2021-04-04T23:49:15Z)
• Distributional Random Forests: Heterogeneity Adjustment and Multivariate Distributional Regression [0.8574682463936005]
  We propose a novel forest construction for multivariate responses based on their joint conditional distribution. The code is available as Python and R packages drf.
  arXiv  Detail & Related papers  (2020-05-29T09:05:00Z)
• GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergences [70.30467057209405]
  Generative Adversarial Networks (GANs) are modern methods to learn the underlying distribution of a data set. GANs are designed in a model-free fashion where no additional information about the underlying distribution is available. We propose a principled design of a model-based GAN that uses a set of simple discriminators on the neighborhoods of the Bayes-net/MRF.
  arXiv  Detail & Related papers  (2020-03-02T04:31:22Z)

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.