MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
- URL: http://arxiv.org/abs/2405.18979v2
- Date: Mon, 24 Jun 2024 09:12:08 GMT
- Title: MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
- Authors: Renchunzi Xie, Ambroise Odonnat, Vasilii Feofanov, Weijian Deng, Jianfeng Zhang, Bo An,
- Abstract summary: Current logit-based methods are vulnerable to overconfidence issues, leading to prediction bias, especially under the natural shift.
We propose MaNo, which applies a data-dependent normalization on the logits to reduce prediction bias, and takes the $L_p$ norm of the matrix of normalized logits as the estimation score.
MaNo achieves state-of-the-art performance across various architectures in the presence of synthetic, natural, or subpopulation shifts.
- Score: 25.643876327918544
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Leveraging the models' outputs, specifically the logits, is a common approach to estimating the test accuracy of a pre-trained neural network on out-of-distribution (OOD) samples without requiring access to the corresponding ground truth labels. Despite their ease of implementation and computational efficiency, current logit-based methods are vulnerable to overconfidence issues, leading to prediction bias, especially under the natural shift. In this work, we first study the relationship between logits and generalization performance from the view of low-density separation assumption. Our findings motivate our proposed method MaNo which (1) applies a data-dependent normalization on the logits to reduce prediction bias, and (2) takes the $L_p$ norm of the matrix of normalized logits as the estimation score. Our theoretical analysis highlights the connection between the provided score and the model's uncertainty. We conduct an extensive empirical study on common unsupervised accuracy estimation benchmarks and demonstrate that MaNo achieves state-of-the-art performance across various architectures in the presence of synthetic, natural, or subpopulation shifts.
Related papers
- ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection [41.41164637577005]
Post-hoc out-of-distribution (OOD) detection has garnered intensive attention in reliable machine learning.
We propose a novel theoretical framework grounded in Bregman divergence to provide a unified perspective on density-based score design.
We show that our proposed textscConjNorm has established a new state-of-the-art in a variety of OOD detection setups.
arXiv Detail & Related papers (2024-02-27T21:02:47Z) - Exploiting Observation Bias to Improve Matrix Completion [16.57405742112833]
We consider a variant of matrix completion where entries are revealed in a biased manner.
The goal is to exploit the shared information between the bias and the outcome of interest to improve predictions.
We find that with this two-stage algorithm, the estimates have 30x smaller mean squared error compared to traditional matrix completion methods.
arXiv Detail & Related papers (2023-06-07T20:48:35Z) - On the Importance of Feature Separability in Predicting
Out-Of-Distribution Error [25.995311155942016]
We propose a dataset-level score based upon feature dispersion to estimate the test accuracy under distribution shift.
Our method is inspired by desirable properties of features in representation learning: high inter-class dispersion and high intra-class compactness.
arXiv Detail & Related papers (2023-03-27T09:52:59Z) - Improving Adaptive Conformal Prediction Using Self-Supervised Learning [72.2614468437919]
We train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores.
We empirically demonstrate the benefit of the additional information using both synthetic and real data on the efficiency (width), deficit, and excess of conformal prediction intervals.
arXiv Detail & Related papers (2023-02-23T18:57:14Z) - Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions.
In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data.
We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
arXiv Detail & Related papers (2022-01-11T23:01:12Z) - General Greedy De-bias Learning [163.65789778416172]
We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space.
GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
arXiv Detail & Related papers (2021-12-20T14:47:32Z) - Learning to Estimate Without Bias [57.82628598276623]
Gauss theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models.
In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints.
A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance.
arXiv Detail & Related papers (2021-10-24T10:23:51Z) - Counterfactual Maximum Likelihood Estimation for Training Deep Networks [83.44219640437657]
Deep learning models are prone to learning spurious correlations that should not be learned as predictive clues.
We propose a causality-based training framework to reduce the spurious correlations caused by observable confounders.
We conduct experiments on two real-world tasks: Natural Language Inference (NLI) and Image Captioning.
arXiv Detail & Related papers (2021-06-07T17:47:16Z) - BENN: Bias Estimation Using Deep Neural Network [37.70583323420925]
We present BENN -- a novel bias estimation method that uses a pretrained unsupervised deep neural network.
Given a ML model and data samples, BENN provides a bias estimation for every feature based on the model's predictions.
We evaluated BENN using three benchmark datasets and one proprietary churn prediction model used by a European Telco.
arXiv Detail & Related papers (2020-12-23T08:25:35Z) - CASTLE: Regularization via Auxiliary Causal Graph Discovery [89.74800176981842]
We introduce Causal Structure Learning (CASTLE) regularization and propose to regularize a neural network by jointly learning the causal relationships between variables.
CASTLE efficiently reconstructs only the features in the causal DAG that have a causal neighbor, whereas reconstruction-based regularizers suboptimally reconstruct all input features.
arXiv Detail & Related papers (2020-09-28T09:49:38Z)
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.