English
Related papers

Related papers: Computational and Statistical Hardness of Calibrat…

200 papers

Despite their impressive predictive performance in various computer vision tasks, deep neural networks (DNNs) tend to make overly confident predictions, which hinders their widespread use in safety-critical applications. While there have…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Teodora Popordanoska , Aleksei Tiulpin , Matthew B. Blaschko

We make two contributions to the problem of estimating the $L_1$ calibration error of a binary classifier from a finite dataset. First, we provide an upper bound for any classifier where the calibration function has bounded variation.…

We study the problem of distinguishing between two symmetric probability distributions over $n$ bits by observing $k$ bits of a sample, subject to the constraint that all $k-1$-wise marginal distributions of the two distributions are…

Computational Complexity · Computer Science 2021-03-16 Christopher Williamson

Deep neural networks have demonstrated remarkable performance across numerous learning tasks but often suffer from miscalibration, resulting in unreliable probability outputs. This has inspired many recent works on mitigating…

Machine Learning · Computer Science 2025-09-23 Wenjian Huang , Guiping Cao , Jiahao Xia , Jingkun Chen , Hao Wang , Jianguo Zhang

Given two distributions $\mathcal{P}$ and $\mathcal{Q}$ over a high-dimensional domain $\{0,1\}^n$, and a parameter $\varepsilon$, the goal of distance estimation is to determine the statistical distance between $\mathcal{P}$ and…

Data Structures and Algorithms · Computer Science 2025-09-09 Gunjan Kumar , Kuldeep S. Meel , Yash Pote

As we move away from the data, the predictive uncertainty should increase, since a great variety of explanations are consistent with the little available information. We introduce Distance-Aware Prior (DAP) calibration, a method to correct…

Machine Learning · Statistics 2022-07-19 Gianluca Detommaso , Alberto Gasparin , Andrew Wilson , Cedric Archambeau

Being cautious is crucial for enhancing the trustworthiness of machine learning systems integrated into decision-making pipelines. Although calibrated probabilities help in optimal decision-making, perfect calibration remains unattainable,…

Machine Learning · Computer Science 2024-08-12 Mari-Liis Allikivi , Joonas Järve , Meelis Kull

A decision-theoretic characterization of perfect calibration is that an agent seeking to minimize a proper loss in expectation cannot improve their outcome by post-processing a perfectly calibrated predictor. Hu and Wu (FOCS'24) use this to…

Machine Learning · Computer Science 2025-11-18 Parikshit Gopalan , Konstantinos Stavropoulos , Kunal Talwar , Pranay Tankala

We consider the problem of hypothesis testing for discrete distributions. In the standard model, where we have sample access to an underlying distribution $p$, extensive research has established optimal bounds for uniformity testing,…

Machine Learning · Computer Science 2024-12-03 Maryam Aliakbarpour , Piotr Indyk , Ronitt Rubinfeld , Sandeep Silwal

Randomized algorithms depend on accurate sampling from probability distributions, as their correctness and performance hinge on the quality of the generated samples. However, even for common distributions like Binomial, exact sampling is…

Computation · Statistics 2025-06-17 Uddalok Sarkar , Sourav Chakraborty , Kuldeep S. Meel

When the distribution of the data used to train a classifier differs from that of the test data, i.e., under dataset shift, well-established routines for calibrating the decision scores of the classifier, estimating the proportion of…

Machine Learning · Computer Science 2025-05-19 Alejandro Moreo

We study the problem of approximately recovering a probability distribution given noisy measurements of its Chebyshev polynomial moments. This problem arises broadly across algorithms, statistics, and machine learning. By leveraging a…

Data Structures and Algorithms · Computer Science 2026-05-20 Cameron Musco , Christopher Musco , Lucas Rosenblatt , Apoorv Vikram Singh

We study the density estimation problem defined as follows: given $k$ distributions $p_1, \ldots, p_k$ over a discrete domain $[n]$, as well as a collection of samples chosen from a ``query'' distribution $q$ over $[n]$, output $p_i$ that…

Data Structures and Algorithms · Computer Science 2024-10-31 Anders Aamand , Alexandr Andoni , Justin Y. Chen , Piotr Indyk , Shyam Narayanan , Sandeep Silwal , Haike Xu

Hypothesis Selection is a fundamental distribution learning problem where given a comparator-class $Q=\{q_1,\ldots, q_n\}$ of distributions, and a sampling access to an unknown target distribution $p$, the goal is to output a distribution…

Machine Learning · Computer Science 2021-08-19 Olivier Bousquet , Mark Braverman , Klim Efremenko , Gillat Kol , Shay Moran

Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not…

Machine Learning · Statistics 2019-11-01 Jayaraman J. Thiagarajan , Bindya Venkatesh , Deepta Rajan

Given a sequence of samples $x_1, \dots , x_k$ promised to be drawn from one of two distributions $X_0, X_1$, a well-studied problem in statistics is to decide $\textit{which}$ distribution the samples are from. Information theoretically,…

Cryptography and Security · Computer Science 2025-10-29 Cassandra Marcussen , Aaron Putterman , Salil Vadhan

Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications. We discover that modern neural networks, unlike…

Machine Learning · Computer Science 2017-08-04 Chuan Guo , Geoff Pleiss , Yu Sun , Kilian Q. Weinberger

While the performance of machine learning systems has experienced significant improvement in recent years, relatively little attention has been paid to the fundamental question: to what extent can we improve our models? This paper provides…

Machine Learning · Computer Science 2026-05-13 Ryota Ushio , Takashi Ishida , Masashi Sugiyama

Calibration is a critical property for establishing the trustworthiness of predictors that provide uncertainty estimates. Multicalibration is a strengthening of calibration which requires that predictors be calibrated on a potentially…

Machine Learning · Computer Science 2025-09-23 Nathan Derhake , Siddartha Devic , Dutch Hansen , Kuan Liu , Vatsal Sharan

A machine learning model is calibrated if its predicted probability for an outcome matches the observed frequency for that outcome conditional on the model prediction. This property has become increasingly important as the impact of machine…

Machine Learning · Computer Science 2025-02-25 Muthu Chidambaram , Rong Ge