English
Related papers

Related papers: Errors are Robustly Tamed in Cumulative Knowledge …

200 papers

Societal accumulation of knowledge is a complex process. The correctness of new units of knowledge depends not only on the correctness of new reasoning, but also on the correctness of old units that the new one builds on. The errors in such…

Social and Information Networks · Computer Science 2024-06-18 Omri Ben-Eliezer , Dan Mikulincer , Elchanan Mossel , Madhu Sudan

Incorporation of a new knowledge into neural networks with simultaneous preservation of the previous one is known to be a nontrivial problem. This problem becomes even more complex when new knowledge is contained not in new training…

Machine Learning · Computer Science 2019-09-10 Mikhail Iu. Leontev , Viktoriia Islenteva , Sergey V. Sukhov

Confident prediction is highly relevant in machine learning; for example, in applications such as medical diagnoses, wrong prediction can be fatal. For classification, there already exist procedures that allow to not classify data when the…

Statistics Theory · Mathematics 2015-07-28 Christophe Denis , Mohamed Hebiri

Sequential hypothesis testing asks for decision rules that update as data arrive. A natural goal is \emph{eventual correctness}: the rule may change its mind early on, but it should make only finitely many wrong decisions almost surely.…

Information Theory · Computer Science 2026-05-05 Amir Leshem

We present a representation of partial confidence in belief and preference that is consistent with the tenets of decision-theory. The fundamental insight underlying the representation is that if a person is not completely confident in a…

Artificial Intelligence · Computer Science 2013-04-11 David Heckerman , Holly B. Jimison

A common practice of ML systems development concerns the training of the same model under different data sets, and the use of the same (training and test) sets for different learning models. The first case is a desirable practice for…

Logic in Computer Science · Computer Science 2025-06-06 Leonardo Ceragioli , Giuseppe Primiero

Probabilistic knowledge graph embeddings represent entities as distributions, using learned variances to quantify epistemic uncertainty. We identify a fundamental limitation: these variances are relation-agnostic, meaning an entity receives…

Machine Learning · Computer Science 2026-01-05 Chorok Lee

Deep learning classifiers are assisting humans in making decisions and hence the user's trust in these models is of paramount importance. Trust is often a function of constant behavior. From an AI model perspective it means given the same…

What happens when a new piece of knowledge is introduced into the training data and how long does it last while a large language model (LM) continues to train? We investigate this question by injecting facts into LMs from a new probing…

Computation and Language · Computer Science 2024-10-30 Chen Sun , Nolan Andrew Miller , Andrey Zhmoginov , Max Vladymyrov , Mark Sandler

This paper contributes a novel embedding model which measures the probability of each belief $\langle h,r,t,m\rangle$ in a large-scale knowledge repository via simultaneously learning distributed representations for entities ($h$ and $t$),…

Artificial Intelligence · Computer Science 2015-05-25 Miao Fan , Qiang Zhou , Andrew Abel , Thomas Fang Zheng , Ralph Grishman

When collaborating with an AI system, we need to assess when to trust its recommendations. If we mistakenly trust it in regions where it is likely to err, catastrophic failures may occur, hence the need for Bayesian approaches for…

Artificial Intelligence · Computer Science 2021-02-23 Federico Cerutti , Lance M. Kaplan , Angelika Kimmig , Murat Sensoy

Federated learning brings potential benefits of faster learning, better solutions, and a greater propensity to transfer when heterogeneous data from different parties increases diversity. However, because federated learning tasks tend to be…

Machine Learning · Computer Science 2021-01-18 Duc Thien Nguyen , Shiau Hoong Lim , Laura Wynter , Desmond Cai

We develop an approach to incorporate additional knowledge, in the form of general purpose integrity constraints (ICs), to reduce uncertainty in probabilistic databases. While incorporating ICs improves data quality (and hence quality of…

Databases · Computer Science 2009-07-10 Naveen Ashish , Sharad Mehrotra , Pouria Pirzadeh

Conventional cluster-robust inference can be invalid when data contain clusters of unignorably large size. We formalize this issue by deriving a necessary and sufficient condition for its validity, and show that this condition is frequently…

Econometrics · Economics 2025-10-07 Harold D. Chiang , Yuya Sasaki , Yulong Wang

The community structure of complex networks reveals both their organization and hidden relationships among their constituents. Most community detection methods currently available are not deterministic, and their results typically depend on…

Physics and Society · Physics 2012-03-29 Andrea Lancichinetti , Santo Fortunato

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

A fundamental question in causal inference is whether it is possible to reliably infer manipulation effects from observational data. There are a variety of senses of asymptotic reliability in the statistical literature, among which the most…

Artificial Intelligence · Computer Science 2012-12-12 Jiji Zhang , Peter L. Spirtes

Knowledge distillation, i.e., one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers. It has even been observed that classifiers learn much…

Machine Learning · Computer Science 2021-05-28 Mary Phuong , Christoph H. Lampert

The vast majority of theoretical results in machine learning and statistics assume that the available training data is a reasonably reliable reflection of the phenomena to be learned or estimated. Similarly, the majority of machine learning…

Machine Learning · Computer Science 2017-06-13 Moses Charikar , Jacob Steinhardt , Gregory Valiant

Complex classifiers may exhibit "embarassing" failures in cases where humans can easily provide a justified classification. Avoiding such failures is obviously of key importance. In this work, we focus on one such setting, where a label is…

Machine Learning · Computer Science 2019-06-14 Deborah Cohen , Amit Daniely , Amir Globerson , Gal Elidan
‹ Prev 1 2 3 10 Next ›