English
Related papers

Related papers: Falsification and future performance

200 papers

This paper studies convergence of empirical risks in reproducing kernel Hilbert spaces (RKHS). A conventional assumption in the existing research is that empirical training data do not contain any noise but this may not be satisfied in some…

Optimization and Control · Mathematics 2020-05-19 Shaoyan Guo , Huifu Xu , Liwei Zhang

In many learning theory problems, a central role is played by a hypothesis class: we might assume that the data is labeled according to a hypothesis in the class (usually referred to as the realizable setting), or we might evaluate the…

Machine Learning · Computer Science 2022-11-17 Lunjia Hu , Charlotte Peale

Ensemble learning combines several individual models to obtain a better generalization performance. In this work we present a practical method for estimating the joint power of several classifiers. It differs from existing approaches which…

Artificial Intelligence · Computer Science 2023-12-22 Simi Haber , Yonatan Wexler

In this work, we consider a recently proposed entropy S (called varentropy) defined by a variational relationship dI=beta*(d<x>-<dx>) as a measure of uncertainty of random variable x. By definition, varentropy underlies a generalized…

Statistical Mechanics · Physics 2020-10-28 C. J. Ou , A. El Kaabouchi , L. Nivanen , F. Tsobnang , A. Le Méhauté , Qiuping A. Wang

Based on the framework of Conformal Prediction (CP), we study the online construction of confidence sets given a black-box machine learning model. By converting the target confidence levels into quantile levels, the problem can be reduced…

Machine Learning · Statistics 2025-05-23 Zhiyu Zhang , Zhou Lu , Heng Yang

In this paper from communication channel coding perspective we are able to present both a theoretical and practical discussion of AI's uncertainty, capacity and evolution for pattern classification based on the classical Rademacher…

Machine Learning · Computer Science 2021-02-16 Mingyong Zhou

We study several questions in the reliable agnostic learning framework of Kalai et al. (2009), which captures learning tasks in which one type of error is costlier than others. A positive reliable classifier is one that makes no false…

Machine Learning · Computer Science 2014-02-25 Varun Kanade , Justin Thaler

Modern deep learning based classifiers show very high accuracy on test data but this does not provide sufficient guarantees for safe deployment, especially in high-stake AI applications such as medical diagnosis. Usually, predictions are…

Machine Learning · Computer Science 2022-05-09 David Stutz , Krishnamurthy , Dvijotham , Ali Taylan Cemgil , Arnaud Doucet

Machine learning plays an increasingly significant role in many aspects of our lives (including medicine, transportation, security, justice and other domains), making the potential consequences of false predictions increasingly devastating.…

Computer Vision and Pattern Recognition · Computer Science 2020-07-01 Yuval Bahat , Gregory Shakhnarovich

Most existing literature on supervised machine learning assumes that the training dataset is drawn from an i.i.d. sample. However, many real-world problems exhibit temporal dependence and strong correlations between the marginal…

Machine Learning · Statistics 2025-06-18 Nikola Sandrić

A representative researcher has repeated opportunities for empirical research. To process findings, she must impose an "identifying assumption." She conducts research when the assumption is sufficiently plausible (taking into account both…

Theoretical Economics · Economics 2025-01-17 Andrew Ellis , Ran Spiegler

When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments…

Machine Learning · Computer Science 2023-05-05 Mattijs Baert , Pietro Mazzaglia , Sam Leroux , Pieter Simoens

Many recent works have shown that adversarial examples that fool classifiers can be found by minimally perturbing a normal input. Recent theoretical results, starting with Gilmer et al. (2018b), show that if the inputs are drawn from a…

Machine Learning · Computer Science 2019-10-29 Saeed Mahloujifar , Xiao Zhang , Mohammad Mahmoody , David Evans

Large pretrained self-attention neural networks, or transformers, have been very successful in various tasks recently. The performance of a model on a given task depends on its ability to memorize and generalize the training data. Large…

Machine Learning · Computer Science 2024-08-01 Aki Härmä , Marcin Pietrasik , Anna Wilbik

We present an information-theoretic framework to learn fixed-dimensional embeddings for tasks in reinforcement learning. We leverage the idea that two tasks are similar if observing an agent's performance on one task reduces our uncertainty…

Machine Learning · Computer Science 2024-05-10 Mridul Mahajan , Georgios Tzannetos , Goran Radanovic , Adish Singla

Statistical learning theory provides bounds of the generalization gap, using in particular the Vapnik-Chervonenkis dimension and the Rademacher complexity. An alternative approach, mainly studied in the statistical physics literature, is…

Disordered Systems and Neural Networks · Physics 2020-09-04 Alia Abbara , Benjamin Aubin , Florent Krzakala , Lenka Zdeborová

Matrix completion is a fundamental problem that comes up in a variety of applications like the Netflix problem, collaborative filtering, computer vision, and crowdsourcing. The goal of the problem is to recover a k-by-n unknown matrix from…

Information Theory · Computer Science 2014-02-19 Changho Suh

Prediction, where observed data is used to quantify uncertainty about a future observation, is a fundamental problem in statistics. Prediction sets with coverage probability guarantees are a common solution, but these do not provide…

Statistics Theory · Mathematics 2022-11-22 Leonardo Cella , Ryan Martin

We study the identifiability of parameters and falsifiability of predictions under the process of model expansion in a Bayesian setting. Identifiability is represented by the closeness of the posterior to the prior distribution and…

Statistics Theory · Mathematics 2025-10-15 Collin Cademartori

In this paper, a mathematical theory of learning is proposed that has many parallels with information theory. We consider Vapnik's General Setting of Learning in which the learning process is defined to be the act of selecting a hypothesis…

Machine Learning · Computer Science 2014-05-08 Ibrahim Alabdulmohsin