English
Related papers

Related papers: Information-theoretic Generalization Analysis for …

200 papers

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

Data-sparse settings such as robotic manipulation, molecular physics, and galaxy morphology classification are some of the hardest domains for deep learning. For these problems, equivariant networks can help improve modeling across…

Machine Learning · Computer Science 2026-01-30 Edward Berman , Jacob Ginesin , Marco Pacini , Robin Walters

Deep neural networks have been shown to be highly miscalibrated. often they tend to be overconfident in their predictions. It poses a significant challenge for safety-critical systems to utilise deep neural networks (DNNs), reliably. Many…

Machine Learning · Computer Science 2022-05-05 Aditya Singh , Alessandro Bay , Biswa Sengupta , Andrea Mirabile

Research has shown that deep networks tend to be overly optimistic about their predictions, leading to an underestimation of prediction errors. Due to the limited nature of data, existing studies have proposed various methods based on model…

Machine Learning · Computer Science 2023-10-24 Jia-Qi Yang , De-Chuan Zhan , Le Gan

Prompt tuning of large-scale vision-language models such as CLIP enables efficient task adaptation without updating model weights. However, it often leads to poor confidence calibration and unreliable predictive uncertainty. We address this…

We present a unifying picture of PAC-Bayesian and mutual information-based upper bounds on the generalization error of randomized learning algorithms. As we show, Tong Zhang's information exponential inequality (IEI) gives a general recipe…

Machine Learning · Computer Science 2021-10-26 Pradeep Kr. Banerjee , Guido Montúfar

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

There is intense interest in applying machine learning to problems of causal inference in fields such as healthcare, economics and education. In particular, individual-level causal inference has important applications such as precision…

Machine Learning · Statistics 2017-05-17 Uri Shalit , Fredrik D. Johansson , David Sontag

Predictions are often probabilities; e.g., a prediction could be for precipitation tomorrow, but with only a 30% chance. Given such probabilistic predictions together with the actual outcomes, "reliability diagrams" help detect and diagnose…

Statistics Theory · Mathematics 2022-11-15 Imanol Arrieta-Ibarra , Paman Gujral , Jonathan Tannen , Mark Tygert , Cherie Xu

This paper studies the problem of post-hoc calibration of machine learning classifiers. We introduce the following desiderata for uncertainty calibration: (a) accuracy-preserving, (b) data-efficient, and (c) high expressive power. We show…

Machine Learning · Computer Science 2020-07-01 Jize Zhang , Bhavya Kailkhura , T. Yong-Jin Han

Dealing with biased data samples is a common task across many statistical fields. In survey sampling, bias often occurs due to unrepresentative samples. In causal studies with observational data, the treated versus untreated group…

Computation · Statistics 2019-07-29 Xiaojing Wang , Jingang Miao , Yunting Sun

Informally, a model is calibrated if its predictions are correct with a probability that matches the confidence of the prediction. By far the most common method in the literature for measuring calibration is the expected calibration error…

Machine Learning · Computer Science 2024-06-04 Muthu Chidambaram , Holden Lee , Colin McSwiggen , Semon Rezchikov

Rigorous statistical methods, including parameter estimation with accompanying uncertainties, underpin the validity of scientific discovery, especially in the natural sciences. With increasingly complex data models such as deep learning…

Machine Learning · Computer Science 2026-02-18 Aurora Grefsrud , Nello Blaser , Trygve Buanes

Deep learning models, including modern systems like large language models, are well known to offer unreliable estimates of the uncertainty of their decisions. In order to improve the quality of the confidence levels, also known as…

Machine Learning · Computer Science 2024-04-15 Jiayi Huang , Sangwoo Park , Osvaldo Simeone

Computing expected information gain (EIG) from prior to posterior (equivalently, mutual information between candidate observations and model parameters or other quantities of interest) is a fundamental challenge in Bayesian optimal…

Methodology · Statistics 2026-01-30 Fengyi Li , Ricardo Baptista , Youssef Marzouk

Despite their incredible performance, it is well reported that deep neural networks tend to be overoptimistic about their prediction confidence. Finding effective and efficient calibration methods for neural networks is therefore an…

Machine Learning · Computer Science 2023-09-07 Lucas Clarté , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová

Applications such as weather forecasting and personalized medicine demand models that output calibrated probability estimates---those representative of the true likelihood of a prediction. Most models are not calibrated out of the box but…

Machine Learning · Computer Science 2020-02-03 Ananya Kumar , Percy Liang , Tengyu Ma

A variety of different performance metrics are commonly used in the machine learning literature for the evaluation of classification systems. Some of the most common ones for measuring quality of hard decisions are standard and balanced…

Machine Learning · Computer Science 2023-09-22 Luciana Ferrer

For many applications, an ensemble of base classifiers is an effective solution. The tuning of its parameters(number of classes, amount of data on which each classifier is to be trained on, etc.) requires G, the generalization error of a…

In most practical applications such as recommendation systems, display advertising, and so forth, the collected data often contains missing values and those missing values are generally missing-not-at-random, which deteriorates the…

Machine Learning · Computer Science 2024-05-27 Mingming Ha , Xuewen Tao , Wenfang Lin , Qionxu Ma , Wujiang Xu , Linxun Chen