English
Related papers

Related papers: Revisiting Optimism and Model Complexity in the Wa…

200 papers

There is a growing interest in societal concerns in machine learning systems, especially in fairness. Multicalibration gives a comprehensive methodology to address group fairness. In this work, we address the multicalibration error and…

Machine Learning · Computer Science 2021-06-08 Eliran Shabat , Lee Cohen , Yishay Mansour

A central question in modern machine learning and imaging sciences is to quantify the number of effective parameters of vastly over-parameterized models. The degrees of freedom is a mathematically convenient way to define this number of…

Machine Learning · Statistics 2019-11-12 Clarice Poon , Gabriel Peyré

In classical statistics, the bias-variance trade-off describes how varying a model's complexity (e.g., number of fit parameters) affects its ability to make accurate predictions. According to this trade-off, optimal performance is achieved…

Machine Learning · Statistics 2022-08-05 Jason W. Rocks , Pankaj Mehta

We revisit the classical problem of comparing regression functions, a fundamental question in statistical inference with broad relevance to modern applications such as data integration, transfer learning, and causal inference. Existing…

Methodology · Statistics 2025-10-29 Jian Yan , Zhuoxi Li , Yang Ning , Yong Chen

Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural networks. In this paper, we introduce a new, theoretically…

Machine Learning · Computer Science 2021-03-11 Lorenz Kuhn , Clare Lyle , Aidan N. Gomez , Jonas Rothfuss , Yarin Gal

We investigate the learning dynamics of classifiers in scenarios where classes are separable or classifiers are over-parameterized. In both cases, Empirical Risk Minimization (ERM) results in zero training error. However, there are many…

Machine Learning · Computer Science 2024-10-23 Julius Martinetz , Christoph Linse , Thomas Martinetz

Machine Learning (ML) is an expressive framework for turning data into computer programs. Across many problem domains -- both in industry and policy settings -- the types of computer programs needed for accurate prediction or optimal…

Machine Learning · Computer Science 2023-12-21 Elliot Creager

In statistical prediction, classical approaches for model selection and model evaluation based on covariance penalties are still widely used. Most of the literature on this topic is based on what we call the "Fixed-X" assumption, where…

Methodology · Statistics 2017-06-13 Saharon Rosset , Ryan J. Tibshirani

Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined…

Machine Learning · Computer Science 2018-03-02 Vladimir Feinberg , Alvin Wan , Ion Stoica , Michael I. Jordan , Joseph E. Gonzalez , Sergey Levine

In this paper, we argue that the prevailing approach to training and evaluating machine learning models often fails to consider their real-world application within organizational or societal contexts, where they are intended to create…

Machine Learning · Computer Science 2025-04-24 Burcu Sayin , Jie Yang , Xinyue Chen , Andrea Passerini , Fabio Casati

Perplexity -- a function measuring a model's overall level of "surprise" when encountering a particular output -- has gained significant traction in recent years, both as a loss function and as a simple-to-compute metric of model quality.…

Machine Learning · Computer Science 2026-02-02 Petar Veličković , Federico Barbero , Christos Perivolaropoulos , Simon Osindero , Razvan Pascanu

ML models have errors when used for predictions. The errors are unknown but can be quantified by model uncertainty. When multiple ML models are trained using the same training points, their model uncertainties may be statistically…

Machine Learning · Statistics 2025-09-23 Xiaoping Du

Predictions and forecasts of machine learning models should take the form of probability distributions, aiming to increase the quantity of information communicated to end users. Although applications of probabilistic prediction and…

Machine Learning · Statistics 2024-03-19 Hristos Tyralis , Georgia Papacharalampous

Probabilistic programming has emerged as a powerful paradigm in statistics, applied science, and machine learning: by decoupling modelling from inference, it promises to allow modellers to directly reason about the processes generating…

Machine Learning · Statistics 2019-06-10 Maria I. Gorinova , Dave Moore , Matthew D. Hoffman

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably…

Machine Learning · Statistics 2020-08-18 Ben Adlam , Jeffrey Pennington

Modern machine learning algorithms, especially deep learning based techniques, typically involve careful hyperparameter tuning to achieve the best performance. Despite the surge of intense interest in practical techniques like Bayesian…

Machine Learning · Computer Science 2025-05-01 Maria-Florina Balcan , Anh Tuan Nguyen , Dravyansh Sharma

It's regarded as an axiom that a good model is one that compromises between bias and variance. The bias is measured in training cost, while the variance of a (say, regression) model is measure by the cost associated with a validation set.…

Machine Learning · Computer Science 2021-10-07 Joseph R. Barr , Peter Shaw , Marcus Sobel

Parameter estimation connects mathematical models to real-world data and decision making across many scientific and industrial applications. Standard approaches such as maximum likelihood estimation and Markov chain Monte Carlo estimate…

Methodology · Statistics 2026-02-06 Matthew J Simpson , James S Bennett , Alexander Johnston , Ruth E Baker

Machine learning algorithms are increasingly used to inform critical decisions. There is a growing concern about bias, that algorithms may produce uneven outcomes for individuals in different demographic groups. In this work, we measure…

Machine Learning · Computer Science 2021-06-01 Runshan Fu , Yangfan Liang , Peter Zhang

We study the excess risk evaluation of classical penalized empirical risk minimization (ERM) with Bregman losses. We show that by leveraging the idea of wild refitting, one can efficiently upper bound the excess risk through the so-called…

Machine Learning · Statistics 2025-11-25 Haichen Hu , David Simchi-Levi