# Questions tagged [conformal-prediction]

The tag has no usage guidance.

11 questions
Filter by
Sorted by
Tagged with
64 views

### Confidence Interval on Probability Estimate (related to conformal prediction)

The question: I'm wondering if anyone knows of a way to obtain a confidence interval on a probability estimates obtained from a model (e.g., from a logistic regression model or a neural network) in a ...
• 123
1 vote
52 views

### Is my interpretation of "the probability over data $X_1, ... X_N$ correct?

This may seem like a pretty simple question, but I want to make sure I am getting this right because it seems pretty foundational. I'm reading this note on conformal prediction. In the very first ...
• 415
83 views

### Conformal prediction for time series classification?

I have read that conformal prediction requires IID. However, I have seen methods that enable uncertainty quantification for time series forecasting. Do you know if there is some similar for time ...
51 views

### How do i apply conformal prediction to achieve voxel-wise uncertainty quantification in a 3D binary segmentation problem?

Context: Typically in an image segmentation problem we go from the model's output logits to sigmoids to discrete labels (0 or 1 in this case). Akin to a binary classification problem, we can set up a ...
1 vote
56 views

### Conformal prediction nonconformity measure

I want to implement offline inductive conformal prediction for a bianry classificstion task but I have an issue with finding an appropriate nonconformity measure. Shafer proposes the Nearest neighbor ...
• 11
4k views

### Intuitive explanation of conformal prediction

I have recently started learning about conformal prediction. I am a programmer without a strong mathematical background, but with a strong intuitive, applied background in statistics. I am trying to ...
• 2,296
1 vote
30 views

### Conformal prediction for model-assisted survey estimation

In model assisted survey estimation, one typically uses the generalized difference estimator:  \hat{t}_{ma} = \sum_{k \in U} \hat{m}(\mathbf{x}_k) + \sum_{k \in S} \frac{y_k - \hat{m}(\mathbf{x}_k)}{...
1 vote
139 views

### What does it mean for a pair of data points to be i.i.d?

I am studying conformal prediction where they mention that the data points in the calibration data should be i.i.d. Here's what it reads - we reserve a moderate number (e.g., 500) of fresh i.i.d. ...
431 views

### How to formally define a conditional distribution conditioning on an event of probability zero?

Given $[X,Y]\sim N(0,I_2)$, a intuitive guess of the value of $P(X=x|\{X,Y\}=\{x,y\})$, where $\{\}$ means unordered set, is $1/2$ by symmetry. This type of notations is typically applied in ...
• 39
616 views

### A question about the exchangeability assumption in conformal predictions

Conformal predictions allow one to add prediction intervals to arbitrary machine learning regression models. For more information see Algorithmic Learning in a Random World. An assumption of conformal ...
• 2,152