Related papers: Predictive Inference with Feature Conformal Prediction

Predictive Inference with Feature Conformal Prediction

URL: http://arxiv.org/abs/2210.00173v4
Date: Sat, 8 Apr 2023 13:54:55 GMT
Title: Predictive Inference with Feature Conformal Prediction
Authors: Jiaye Teng, Chuan Wen, Dinghuai Zhang, Yoshua Bengio, Yang Gao, Yang Yuan
Abstract summary: We propose feature conformal prediction, which extends the scope of conformal prediction to semantic feature spaces. From a theoretical perspective, we demonstrate that feature conformal prediction provably outperforms regular conformal prediction under mild assumptions. Our approach could be combined with not only vanilla conformal prediction, but also other adaptive conformal prediction methods.
Score: 80.77443423828315
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Conformal prediction is a distribution-free technique for establishing valid prediction intervals. Although conventionally people conduct conformal prediction in the output space, this is not the only possibility. In this paper, we propose feature conformal prediction, which extends the scope of conformal prediction to semantic feature spaces by leveraging the inductive bias of deep representation learning. From a theoretical perspective, we demonstrate that feature conformal prediction provably outperforms regular conformal prediction under mild assumptions. Our approach could be combined with not only vanilla conformal prediction, but also other adaptive conformal prediction methods. Apart from experiments on existing predictive inference benchmarks, we also demonstrate the state-of-the-art performance of the proposed methods on large-scale tasks such as ImageNet classification and Cityscapes image segmentation.The code is available at \url{https://github.com/AlvinWen428/FeatureCP}.

Related papers

Conformal Prediction for Hierarchical Data [5.580128181112309]
We propose a first step towards combining Conformal Prediction and Forecast Reconciliation. We show that the validity granted by SCP remains while improving the efficiency of the prediction sets.
arXiv Detail & Related papers (2024-11-20T17:26:26Z)
Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering [55.15192437680943]
Generative models lack rigorous statistical guarantees for their outputs. We propose a sequential conformal prediction method producing prediction sets that satisfy a rigorous statistical guarantee. This guarantee states that with high probability, the prediction sets contain at least one admissible (or valid) example.
arXiv Detail & Related papers (2024-10-02T15:26:52Z)
Probabilistic Conformal Prediction with Approximate Conditional Validity [81.30551968980143]
We develop a new method for generating prediction sets that combines the flexibility of conformal methods with an estimate of the conditional distribution. Our method consistently outperforms existing approaches in terms of conditional coverage.
arXiv Detail & Related papers (2024-07-01T20:44:48Z)
Conformal online model aggregation [29.43493007296859]
This paper proposes a new approach towards conformal model aggregation in online settings. It is based on combining the prediction sets from several algorithms by voting, where weights on the models are adapted over time based on past performance.
arXiv Detail & Related papers (2024-03-22T15:40:06Z)
Probabilistic Conformal Prediction Using Conditional Random Samples [73.26753677005331]
PCP is a predictive inference algorithm that estimates a target variable by a discontinuous predictive set. It is efficient and compatible with either explicit or implicit conditional generative models.
arXiv Detail & Related papers (2022-06-14T03:58:03Z)
CovarianceNet: Conditional Generative Model for Correct Covariance Prediction in Human Motion Prediction [71.31516599226606]
We present a new method to correctly predict the uncertainty associated with the predicted distribution of future trajectories. Our approach, CovariaceNet, is based on a Conditional Generative Model with Gaussian latent variables.
arXiv Detail & Related papers (2021-09-07T09:38:24Z)
Optimized conformal classification using gradient descent approximation [0.2538209532048866]
Conformal predictors allow predictions to be made with a user-defined confidence level. We consider an approach to train the conformal predictor directly with maximum predictive efficiency. We test the method on several real world data sets and find that the method is promising.
arXiv Detail & Related papers (2021-05-24T13:14:41Z)
Private Prediction Sets [72.75711776601973]
Machine learning systems need reliable uncertainty quantification and protection of individuals' privacy. We present a framework that treats these two desiderata jointly. We evaluate the method on large-scale computer vision datasets.
arXiv Detail & Related papers (2021-02-11T18:59:11Z)
Short-term prediction of Time Series based on bounding techniques [0.0]
This paper is reconsidered the prediction problem in time series framework by using a new non-parametric approach. The innovation is to consider both deterministic and deterministic-stochastic assumptions in order to obtain the upper bound of the prediction error. A benchmark is included to illustrate that the proposed predictor can obtain suitable results in a prediction scheme, and can be an interesting alternative method to the classical non-parametric methods.
arXiv Detail & Related papers (2021-01-26T11:27:36Z)
Validity, consonant plausibility measures, and conformal prediction [7.563864405505623]
We present a new notion, called Type-2 validity, relevant to other prediction-related tasks. We show that both types of prediction validity can be achieved by interpreting the conformal prediction output as the contour function of a consonant plausibility measure.
arXiv Detail & Related papers (2020-01-24T23:24:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.