English
Related papers

Related papers: On Sequences with Non-Learnable Subsequences

200 papers

We introduce a notion of computable randomness for infinite sequences that generalises the classical version in two important ways. First, our definition of computable randomness is associated with imprecise probability models, in the sense…

Probability · Mathematics 2020-09-23 Floris Persiau , Jasper De Bock , Gert de Cooman

Solomonoff's inductive learning model is a powerful, universal and highly elegant theory of sequence prediction. Its critical flaw is that it is incomputable and thus cannot be used in practice. It is sometimes suggested that it may still…

Artificial Intelligence · Computer Science 2007-05-23 Shane Legg

Probabilistic forecasting of multivariate time series is essential for various downstream tasks. Most existing approaches rely on the sequences being uniformly spaced and aligned across all variables. However, real-world multivariate time…

Machine Learning · Computer Science 2025-02-18 Yijun Li , Cheuk Hang Leung , Qi Wu

Using the game-theoretic framework for probability, Vovk and Shafer. have shown that it is always possible, using randomization, to make sequential probability forecasts that pass any countable set of well-behaved statistical tests. This…

Machine Learning · Computer Science 2008-10-21 Vladimir V. V'yugin

Process Outcome Prediction entails predicting a discrete property of an unfinished process instance from its partial trace. High-capacity outcome predictors discovered with ensemble and deep learning methods have been shown to achieve top…

Machine Learning · Computer Science 2024-07-19 Francesco Folino , Luigi Pontieri , Pietro Sabatino

Solomonoff's central result on induction is that the posterior of a universal semimeasure M converges rapidly and with probability 1 to the true sequence generating posterior mu, if the latter is computable. Hence, M is eligible as a…

Machine Learning · Computer Science 2007-07-16 Marcus Hutter , Andrej Muchnik

Many state-of-the-art algorithms for solving hard combinatorial problems in artificial intelligence (AI) include elements of stochasticity that lead to high variations in runtime, even for a fixed problem instance. Knowledge about the…

Artificial Intelligence · Computer Science 2018-07-10 Katharina Eggensperger , Marius Lindauer , Frank Hutter

We develop a correspondence between the theory of sequential algorithms and classical reasoning, via Kreisel's no-counterexample interpretation. Our framework views realizers of the no-counterexample interpretation as dynamic processes…

Logic in Computer Science · Computer Science 2018-12-31 Thomas Powell

Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts,…

Machine Learning · Computer Science 2022-04-04 Martin Mundt , Iuliia Pliushch , Sagnik Majumder , Yongwon Hong , Visvanathan Ramesh

Many learning tasks can be viewed as sequence prediction problems. For example, online classification can be converted to sequence prediction with the sequence being pairs of input/target data and where the goal is to correctly predict the…

Machine Learning · Computer Science 2012-02-10 Tor Lattimore , Marcus Hutter , Vaibhav Gavane

Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learned from a (single) training set, assumed to issue from an unknown probability distribution. In actual deployment,…

Machine Learning · Computer Science 2024-10-25 Michele Caprio , Maryam Sultana , Eleni Elia , Fabio Cuzzolin

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

Recursive Neural Networks are non-linear adaptive models that are able to learn deep structured information. However, these models have not yet been broadly accepted. This fact is mainly due to its inherent complexity. In particular, not…

Neural and Evolutionary Computing · Computer Science 2009-11-18 Alejandro Chinea

When dealing with process calculi and automata which express both nondeterministic and probabilistic behavior, it is customary to introduce the notion of scheduler to solve the nondeterminism. It has been observed that for certain…

Cryptography and Security · Computer Science 2007-06-13 Konstantinos Chatzikokolakis , Catuscia Palamidessi

Certifiable, adaptive uncertainty estimates for unknown quantities are an essential ingredient of sequential decision-making algorithms. Standard approaches rely on problem-dependent concentration results and are limited to a specific…

Machine Learning · Computer Science 2023-11-09 Nicolas Emmenegger , Mojmír Mutný , Andreas Krause

Bases have become an integral part of modern deep learning-based models for time series forecasting due to their ability to act as feature extractors or future references. To be effective, a basis must be tailored to the specific set of…

Machine Learning · Computer Science 2024-01-19 Zelin Ni , Hang Yu , Shizhan Liu , Jianguo Li , Weiyao Lin

We consider a model of selective prediction, where the prediction algorithm is given a data sequence in an online fashion and asked to predict a pre-specified statistic of the upcoming data points. The algorithm is allowed to choose when to…

Machine Learning · Computer Science 2019-05-30 Mingda Qiao , Gregory Valiant

Time series forecasting is an important and forefront task in many real-world applications. However, most of time series forecasting techniques assume that the training data is clean without anomalies. This assumption is unrealistic since…

Machine Learning · Computer Science 2024-02-06 Hao Cheng , Qingsong Wen , Yang Liu , Liang Sun

A new general procedure for a priori selection of more predictable events from a time series of observed variable is proposed. The procedure is applicable to time series which contains different types of events that feature significantly…

Neural and Evolutionary Computing · Computer Science 2007-05-23 Igor B. Konovalov

It is argued that deep learning is efficient for data that is generated from hierarchal generative models. Examples of such generative models include wavelet scattering networks, functions of compositional structure, and deep rendering…

Machine Learning · Computer Science 2018-09-06 Elchanan Mossel