Conditional Distribution Quantization in Machine Learning

• URL: http://arxiv.org/abs/2502.07151v1
• Date: Tue, 11 Feb 2025 00:28:24 GMT
• Title: Conditional Distribution Quantization in Machine Learning
• Authors: Blaise Delattre, Sylvain Delattre, Alexandre Vérine, Alexandre Allauzen,
• Abstract summary: Conditional expectation mathbbE(Y mid X) often fails to capture the complexity of multimodal conditional distributions mathcalL(Y mid X) We propose using n-point conditional quantizations--functional mappings of X that are learnable via gradient descent--to approximate mathcalL(Y mid X)
• Score: 83.54039134248231
• License:
• Abstract: Conditional expectation \mathbb{E}(Y \mid X) often fails to capture the complexity of multimodal conditional distributions \mathcal{L}(Y \mid X). To address this, we propose using n-point conditional quantizations--functional mappings of X that are learnable via gradient descent--to approximate \mathcal{L}(Y \mid X). This approach adapts Competitive Learning Vector Quantization (CLVQ), tailored for conditional distributions. It goes beyond single-valued predictions by providing multiple representative points that better reflect multimodal structures. It enables the approximation of the true conditional law in the Wasserstein distance. The resulting framework is theoretically grounded and useful for uncertainty quantification and multimodal data generation tasks. For example, in computer vision inpainting tasks, multiple plausible reconstructions may exist for the same partially observed input image X. We demonstrate the effectiveness of our approach through experiments on synthetic and real-world datasets.

Related papers

• Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods [59.779795063072655]
  Chain-of-Thought (CoT) prompting and its variants have gained popularity as effective methods for solving multi-step reasoning problems. We analyze CoT prompting from a statistical estimation perspective, providing a comprehensive characterization of its sample complexity.
  arXiv  Detail & Related papers  (2024-08-25T04:07:18Z)
• Vector Quantile Regression on Manifolds [8.328891187733841]
  Quantile regression (QR) is a statistical tool for distribution-free estimation of conditional quantiles of a target variable given explanatory features. By leveraging optimal transport theory and c-concave functions, we meaningfully define conditional vector quantile functions of high-dimensional variables. We demonstrate the approach's efficacy and provide insights regarding the meaning of non-Euclidean quantiles through synthetic and real data experiments.
  arXiv  Detail & Related papers  (2023-07-03T14:17:12Z)
• Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification [4.728311759896569]
  We propose a novel, succinct, and effective approach for distribution prediction to quantify uncertainty in machine learning. It incorporates adaptively flexible distribution prediction of $mathbbP(mathbfy|mathbfX=x)$ in regression tasks. On extensive regression tasks from UCI datasets, we show that EMQ achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-11-26T11:45:32Z)
• Instability and Local Minima in GAN Training with Kernel Discriminators [20.362912591032636]
  Generative Adversarial Networks (GANs) are a widely-used tool for generative modeling of complex data. Despite their empirical success, the training of GANs is not fully understood due to the min-max optimization of the generator and discriminator. This paper analyzes these joint dynamics when the true samples, as well as the generated samples, are discrete, finite sets, and the discriminator is kernel-based.
  arXiv  Detail & Related papers  (2022-08-21T18:03:06Z)
• Distributional Gradient Boosting Machines [77.34726150561087]
  Our framework is based on XGBoost and LightGBM. We show that our framework achieves state-of-the-art forecast accuracy.
  arXiv  Detail & Related papers  (2022-04-02T06:32:19Z)
• Efficient CDF Approximations for Normalizing Flows [64.60846767084877]
  We build upon the diffeomorphic properties of normalizing flows to estimate the cumulative distribution function (CDF) over a closed region. Our experiments on popular flow architectures and UCI datasets show a marked improvement in sample efficiency as compared to traditional estimators.
  arXiv  Detail & Related papers  (2022-02-23T06:11:49Z)
• Arbitrary Conditional Distributions with Energy [11.081460215563633]
  A more general and useful problem is arbitrary conditional density estimation. We propose a novel method, Arbitrary Conditioning with Energy (ACE), that can simultaneously estimate the distribution $p(mathbfx_u mid mathbfx_o)$. We also simplify the learning problem by only learning one-dimensional conditionals, from which more complex distributions can be recovered during inference.
  arXiv  Detail & Related papers  (2021-02-08T18:36:26Z)
• Efficient Semi-Implicit Variational Inference [65.07058307271329]
  We propose an efficient and scalable semi-implicit extrapolational (SIVI) Our method maps SIVI's evidence to a rigorous inference of lower gradient values.
  arXiv  Detail & Related papers  (2021-01-15T11:39:09Z)
• Probabilistic Circuits for Variational Inference in Discrete Graphical Models [101.28528515775842]
  Inference in discrete graphical models with variational methods is difficult. Many sampling-based methods have been proposed for estimating Evidence Lower Bound (ELBO) We propose a new approach that leverages the tractability of probabilistic circuit models, such as Sum Product Networks (SPN) We show that selective-SPNs are suitable as an expressive variational distribution, and prove that when the log-density of the target model is aweighted the corresponding ELBO can be computed analytically.
  arXiv  Detail & Related papers  (2020-10-22T05:04:38Z)
• Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity [26.518803984578867]
  Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging. One typically resorts to sampling-based approximations of the true marginal. We propose a new training strategy which replaces these estimators by an exact yet efficient marginalization.
  arXiv  Detail & Related papers  (2020-07-03T19:36:35Z)

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.