English
Related papers

Related papers: Soft Mean Expected Calibration Error (SMECE): A Ca…

200 papers

Several prior studies have suggested that word frequency biases can cause the Bert model to learn indistinguishable sentence embeddings. Contrastive learning schemes such as SimCSE and ConSERT have already been adopted successfully in…

Computation and Language · Computer Science 2023-09-15 Pu Miao , Zeyao Du , Junlin Zhang

Modern neural networks can achieve high accuracy while remaining poorly calibrated, producing confidence estimates that do not match empirical correctness. Yet calibration is often treated as a post-hoc attribute. We take a different…

Machine Learning · Computer Science 2026-04-23 Alessandro Morosini , Matea Gjika , Tomaso Poggio , Pierfrancesco Beneventano

Empirical Bayes estimators are based on minimizing the average risk with the hyper-parameters in the weighting function being estimated from observed data. The performance of an empirical Bayes estimator is typically evaluated by its mean…

Statistics Theory · Mathematics 2025-03-18 Yue Ju , Bo Wahlberg , Håkan Hjalmarsson

Machine learning-based decision support systems are increasingly deployed in clinical settings, where probabilistic scoring functions are used to inform and prioritize patient management decisions. However, widely used scoring rules, such…

Machine Learning · Computer Science 2025-07-01 Gerardo A. Flores , Alyssa H. Smith , Julia A. Fukuyama , Ashia C. Wilson

Collective decision-making requires aggregating multiple noisy information channels about an unknown state of the world. Classical epistemic justifications of majority rule rely on homogeneity assumptions often violated when individual…

General Economics · Economics 2026-04-09 Enrico Manfredi

Over the last years, word and sentence embeddings have established as text preprocessing for all kinds of NLP tasks and improved the performances significantly. Unfortunately, it has also been shown that these embeddings inherit various…

Computation and Language · Computer Science 2024-09-13 Sarah Schröder , Alexander Schulz , Philip Kenneweg , Robert Feldhans , Fabian Hinder , Barbara Hammer

Most supervised machine learning tasks are subject to irreducible prediction errors. Probabilistic predictive models address this limitation by providing probability distributions that represent a belief over plausible targets, rather than…

Machine Learning · Statistics 2022-10-25 David Widmann , Fredrik Lindsten , Dave Zachariah

Calibration is a classical notion from the forecasting literature which aims to address the question: how should predicted probabilities be interpreted? In a world where we only get to observe (discrete) outcomes, how should we evaluate a…

Machine Learning · Computer Science 2025-09-03 Parikshit Gopalan , Lunjia Hu

The classical mixture of linear experts (MoE) model is one of the widespread statistical frameworks for modeling, classification, and clustering of data. Built on the normality assumption of the error terms for mathematical and…

Methodology · Statistics 2020-07-15 Elham Mirfarah , Mehrdad Naderi , Ding-Geng Chen

Training modern neural networks is an inherently noisy process that can lead to high \emph{prediction churn} -- disagreements between re-trainings of the same model due to factors such as randomization in the parameter initialization and…

Machine Learning · Computer Science 2021-06-15 Dara Bahri , Heinrich Jiang

For many interesting tasks, such as medical diagnosis and web page classification, a learner only has access to some positively labeled examples and many unlabeled examples. Learning from this type of data requires making assumptions about…

Machine Learning · Computer Science 2018-08-28 Jessa Bekker , Jesse Davis

In many practical applications of machine learning, a discrepancy often arises between a source distribution from which labeled training examples are drawn and a target distribution for which only unlabeled data is observed. Traditionally,…

Machine Learning · Statistics 2025-03-05 Paweł Teisseyre , Jan Mielniczuk

Learning with softmax cross-entropy on one-hot labels often leads to overconfident predictions and poor robustness under noise or perturbations. Label smoothing mitigates this by redistributing some confidence uniformly, but treats all…

Quantum Physics · Physics 2025-10-02 Fang Qi , Lu Peng , Zhengming Ding

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single corrective…

Machine Learning · Computer Science 2019-10-29 Meelis Kull , Miquel Perello-Nieto , Markus Kängsepp , Telmo Silva Filho , Hao Song , Peter Flach

Classification is a fundamental task in many applications on which data-driven methods have shown outstanding performances. However, it is challenging to determine whether such methods have achieved the optimal performance. This is mainly…

Machine Learning · Computer Science 2024-01-30 Minoh Jeong , Martina Cardone , Alex Dytso

Modern recommendation systems fuse user behavior graphs and review texts but often encounter a "Fusion Gap" caused by False Negatives, Popularity Bias, and Signal Ambiguity. We propose SymCERE (Symmetric NCE), a contrastive learning…

Information Retrieval · Computer Science 2025-12-17 Toyotaro Suzumura , Hisashi Ikari , Hiroki Kanezashi , Md Mostafizur Rahman , Yu Hirate

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

Post-click conversion rate (CVR) is a reliable indicator of online customers' preferences, making it crucial for developing recommender systems. A major challenge in predicting CVR is severe selection bias, arising from users' inherent…

Artificial Intelligence · Computer Science 2025-12-02 Wenbo Hu , Xin Sun , Qiang liu , Le Wu , Liang Wang

Much of Software Engineering (SE) research assumes that progress depends on massive datasets and CPU-intensive optimizers. Yet has this assumption been rigorously tested? The counter-evidence presented in this paper suggests otherwise. For…

Software Engineering · Computer Science 2026-03-31 Kishan Kumar Ganguly , Tim Menzies

In this work, we revisit the problem of active sequential prediction-powered mean estimation, where at each round one must decide the query probability of the ground-truth label upon observing the covariates of a sample. Furthermore, if the…

Machine Learning · Statistics 2026-04-21 Maria-Eleni Sfyraki , Jun-Kun Wang
‹ Prev 1 8 9 10 Next ›