Adversarially Contrastive Estimation of Conditional Neural Processes

• URL: http://arxiv.org/abs/2303.13004v1
• Date: Thu, 23 Mar 2023 02:58:14 GMT
• Title: Adversarially Contrastive Estimation of Conditional Neural Processes
• Authors: Zesheng Ye, Jing Du, Lina Yao
• Abstract summary: Conditional Neural Processes(CNPs) formulate distributions over functions and generate function observations with exact conditional likelihoods. We propose calibrating CNPs with an adversarial training scheme besides regular maximum likelihood estimates. From generative function reconstruction to downstream regression and classification tasks, we demonstrate that our method fits mainstream CNP members.
• Score: 39.77675002999259
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Conditional Neural Processes~(CNPs) formulate distributions over functions and generate function observations with exact conditional likelihoods. CNPs, however, have limited expressivity for high-dimensional observations, since their predictive distribution is factorized into a product of unconstrained (typically) Gaussian outputs. Previously, this could be handled using latent variables or autoregressive likelihood, but at the expense of intractable training and quadratically increased complexity. Instead, we propose calibrating CNPs with an adversarial training scheme besides regular maximum likelihood estimates. Specifically, we train an energy-based model (EBM) with noise contrastive estimation, which enforces EBM to identify true observations from the generations of CNP. In this way, CNP must generate predictions closer to the ground-truth to fool EBM, instead of merely optimizing with respect to the fixed-form likelihood. From generative function reconstruction to downstream regression and classification tasks, we demonstrate that our method fits mainstream CNP members, showing effectiveness when unconstrained Gaussian likelihood is defined, requiring minimal computation overhead while preserving foundation properties of CNPs.

Related papers

• Dynamic Negative Guidance of Diffusion Models [13.873685216429868]
  We show that Negative Prompting (NP) is limited by the assumption of a constant guidance scale. We derive a principled technique called Dynamic Negative Guidance, which relies on a near-optimal time and state dependent modulation of the guidance. We show that it is possible to use DNG with Stable Diffusion to obtain more accurate and less invasive guidance than NP.
  arXiv  Detail & Related papers  (2024-10-18T12:02:21Z)
• Rényi Neural Processes [14.11793373584558]
  We propose R'enyi Neural Processes (RNP) to ameliorate the impacts of prior misspecification. We scale the density ratio $fracpq$ by the power of (1-$alpha$) in the divergence gradients with respect to the posterior. Our experiments show consistent log-likelihood improvements over state-of-the-art NP family models.
  arXiv  Detail & Related papers  (2024-05-25T00:14:55Z)
• Spectral Convolutional Conditional Neural Processes [4.52069311861025]
  Conditional Neural Processes (CNPs) constitute a family of probabilistic models that harness the flexibility of neural networks to parameterize processes. We propose Spectral Convolutional Conditional Neural Processes (SConvCNPs), a new addition to the NPs family that allows for more efficient representation of functions in the frequency domain.
  arXiv  Detail & Related papers  (2024-04-19T21:13:18Z)
• Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability [50.44439018155837]
  We propose to include a calibration term directly into the training objective of the neural model. By introducing a relaxation of the classical formulation of calibration error we enable end-to-end backpropagation. It is directly applicable to existing computational pipelines allowing reliable black-box posterior inference.
  arXiv  Detail & Related papers  (2023-10-20T10:20:45Z)
• Autoregressive Conditional Neural Processes [20.587835119831595]
  Conditional neural processes (CNPs) are attractive meta-learning models. They produce well-calibrated predictions and are trainable via a simple maximum likelihood procedure. CNPs are unable to model dependencies in their predictions. We propose to change how CNPs are deployed at test time, without any modifications to the model or training procedure.
  arXiv  Detail & Related papers  (2023-03-25T13:34:12Z)
• Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation [59.45669299295436]
  We propose a Monte Carlo PDE solver for training unsupervised neural solvers. We use the PDEs' probabilistic representation, which regards macroscopic phenomena as ensembles of random particles. Our experiments on convection-diffusion, Allen-Cahn, and Navier-Stokes equations demonstrate significant improvements in accuracy and efficiency.
  arXiv  Detail & Related papers  (2023-02-10T08:05:19Z)
• Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes [70.80716221080118]
  The paper takes a generative perspective on policy evaluation via temporal-difference (TD) learning. The OS-GPTD approach is developed to estimate the value function for a given policy by observing a sequence of state-reward pairs. To alleviate the limited expressiveness associated with a single fixed kernel, a weighted ensemble (E) of GP priors is employed to yield an alternative scheme.
  arXiv  Detail & Related papers  (2021-12-01T23:15:09Z)
• When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting [70.54920804222031]
  Most existing forecasting models disregard uncertainty quantification, resulting in mis-calibrated predictions. Recent works in deep neural models for uncertainty-aware time-series forecasting also have several limitations. We model the forecasting task as a probabilistic generative process and propose a functional neural process model called EPIFNP.
  arXiv  Detail & Related papers  (2021-06-07T18:31:47Z)
• Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation [99.92568326314667]
  We propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation. Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle. We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of calibration on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2020-11-05T08:04:34Z)
• Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes [32.02612871707347]
  We propose ConvNP, which endows Neural Processes (NPs) with translation equivariance and extends convolutional conditional NPs to allow for dependencies in the predictive distribution. We demonstrate the strong performance and generalization capabilities of ConvNPs on 1D, regression image completion, and various tasks with real-world-temporal data.
  arXiv  Detail & Related papers  (2020-07-02T18:25:27Z)

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.