$\delta$-CLUE: Diverse Sets of Explanations for Uncertainty Estimates

• URL: http://arxiv.org/abs/2104.06323v2
• Date: Wed, 14 Apr 2021 08:10:33 GMT
• Title: $\delta$-CLUE: Diverse Sets of Explanations for Uncertainty Estimates
• Authors: Dan Ley, Umang Bhatt, Adrian Weller
• Abstract summary: We augment the original CLUE approach, to provide what we call $delta$-CLUE. We instead return a $itset$ of plausible CLUEs: multiple, diverse inputs that are within a $delta$ ball of the original input in latent space.
• Score: 31.241489953967694
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating Counterfactual Latent Uncertainty Explanations (CLUEs). However, for a single input, such approaches could output a variety of explanations due to the lack of constraints placed on the explanation. Here we augment the original CLUE approach, to provide what we call $\delta$-CLUE. CLUE indicates $\it{one}$ way to change an input, while remaining on the data manifold, such that the model becomes more confident about its prediction. We instead return a $\it{set}$ of plausible CLUEs: multiple, diverse inputs that are within a $\delta$ ball of the original input in latent space, all yielding confident predictions.

Related papers

• Rejection via Learning Density Ratios [50.91522897152437]
  Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance. Our framework is tested empirically over clean and noisy datasets.
  arXiv  Detail & Related papers  (2024-05-29T01:32:17Z)
• Variational Prediction [95.00085314353436]
  We present a technique for learning a variational approximation to the posterior predictive distribution using a variational bound. This approach can provide good predictive distributions without test time marginalization costs.
  arXiv  Detail & Related papers  (2023-07-14T18:19:31Z)
• Conformalization of Sparse Generalized Linear Models [2.1485350418225244]
  Conformal prediction method estimates a confidence set for $y_n+1$ that is valid for any finite sample size. Although attractive, computing such a set is computationally infeasible in most regression problems. We show how our path-following algorithm accurately approximates conformal prediction sets.
  arXiv  Detail & Related papers  (2023-07-11T08:36:12Z)
• Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions [49.726408540784334]
  Key question in PLD-based accounting is how to approximate any (potentially continuous) PLD with a PLD over any specified discrete support. We show that our pessimistic estimate is the best possible among all pessimistic estimates.
  arXiv  Detail & Related papers  (2022-07-10T04:25:02Z)
• Fair Wrapping for Black-box Predictions [105.10203274098862]
  We learn a wrapper function which we define as an alpha-tree, which modifies the prediction. We show that our modification has appealing properties in terms of composition ofalpha-trees, generalization, interpretability, and KL divergence between modified and original predictions.
  arXiv  Detail & Related papers  (2022-01-31T01:02:39Z)
• Stable Conformal Prediction Sets [0.0]
  conformal prediction is a methodology that allows to estimate a confidence set for $y_n+1$ given $x_n+1$. While appealing, the computation of such set turns out to be infeasible in general. We combine conformal prediction techniques with algorithmic stability bounds to derive a prediction set computable with a single model fit.
  arXiv  Detail & Related papers  (2021-12-19T18:53:32Z)
• Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates [31.241489953967694]
  We study the diversity of such sets and find that many CLUEs are redundant. We then propose GLobal AMortised CLUE (GLAM-CLUE), a distinct and novel method which learns amortised mappings on specific groups of uncertain inputs. Our experiments show that $delta$-CLUE, $nabla$-CLUE, and GLAM-CLUE all address shortcomings of CLUE and provide beneficial explanations of uncertainty estimates to practitioners.
  arXiv  Detail & Related papers  (2021-12-05T18:27:21Z)
• Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification models [0.0]
  We extend the notion of probabilistic Sufficient Explanations (P-SE) The crux of P-SE is to compute the conditional probability of maintaining the same prediction. We deal with non-binary features, without learning the distribution of $X$ nor having the model for making predictions.
  arXiv  Detail & Related papers  (2021-11-08T17:27:52Z)
• $\Delta$-UQ: Accurate Uncertainty Quantification via Anchor Marginalization [40.581619201120716]
  We present $Delta$UQ -- a novel, general-purpose uncertainty estimator using the concept of anchoring in predictive models. We find this uncertainty is deeply connected to improper sampling of the input data, and inherent noise, enabling us to estimate the total uncertainty in any system.
  arXiv  Detail & Related papers  (2021-10-05T17:44:31Z)
• Multivariate Probabilistic Regression with Natural Gradient Boosting [63.58097881421937]
  We propose a Natural Gradient Boosting (NGBoost) approach based on nonparametrically modeling the conditional parameters of the multivariate predictive distribution. Our method is robust, works out-of-the-box without extensive tuning, is modular with respect to the assumed target distribution, and performs competitively in comparison to existing approaches.
  arXiv  Detail & Related papers  (2021-06-07T17:44:49Z)
• Ambiguity in Sequential Data: Predicting Uncertain Futures with Recurrent Models [110.82452096672182]
  We propose an extension of the Multiple Hypothesis Prediction (MHP) model to handle ambiguous predictions with sequential data. We also introduce a novel metric for ambiguous problems, which is better suited to account for uncertainties.
  arXiv  Detail & Related papers  (2020-03-10T09:15:42Z)

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.