English
Related papers

Related papers: Convergence of Discrete MDL for Sequential Predict…

200 papers

Solomonoff completed the Bayesian framework by providing a rigorous, unique, formal, and universal choice for the model class and the prior. We discuss in breadth how and in which sense universal (non-i.i.d.) sequence prediction solves…

Machine Learning · Computer Science 2007-07-13 Marcus Hutter

This paper addresses the growing need to process non-Euclidean data, by introducing a geometric deep learning (GDL) framework for building universal feedforward-type models compatible with differentiable manifold geometries. We show that…

Machine Learning · Computer Science 2022-07-26 Anastasis Kratsios , Leonie Papon

Minimum message length is a general Bayesian principle for model selection and parameter estimation that is based on information theory. This paper applies the minimum message length principle to a small-sample model selection problem…

Methodology · Statistics 2018-02-13 Chi Kuen Wong , Enes Makalic , Daniel F. Schmidt

The predictive accuracy of Machine Learning (ML) models of molecular properties depends on the choice of the molecular representation. Based on the postulates of quantum mechanics, we introduce a hierarchy of representations which meet…

Chemical Physics · Physics 2016-11-23 Bing Huang , O. Anatole von Lilienfeld

The normalized maximum likelihood (NML) code length is widely used as a model selection criterion based on the minimum description length principle, where the model with the shortest NML code length is selected. A common method to calculate…

Statistics Theory · Mathematics 2024-09-16 Atsushi Suzuki , Kota Fukuzawa , Kenji Yamanishi

The inability of Machine Learning (ML) models to successfully extrapolate correct predictions from out-of-distribution (OoD) samples is a major hindrance to the application of ML in critical applications. Until the generalization ability of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Mark Philip Philipsen , Thomas Baltzer Moeslund

The Central Limit Theorem (CLT) establishes that sufficiently large sequences of independent and identically distributed random variables converge in probability to a normal distribution. This makes the CLT a fundamental building block of…

Logic in Computer Science · Computer Science 2026-03-10 Henning Basold , Oisín Flynn-Connolly , Chase Ford , Hao Wang

This paper discusses difference-in-differences (DID) estimation when there exist many control variables, potentially more than the sample size. In this case, traditional estimation methods, which require a limited number of variables, do…

General Economics · Economics 2019-01-09 Neng-Chieh Chang

This work provides test error bounds for iterative fixed point methods on linear predictors -- specifically, stochastic and batch mirror descent (MD), and stochastic temporal difference learning (TD) -- with two core contributions: (a) a…

Machine Learning · Computer Science 2022-06-29 Matus Telgarsky

Markov chain Monte Carlo (MCMC) simulations are commonly employed for estimating features of a target distribution, particularly for Bayesian inference. A fundamental challenge is determining when these simulations should stop. We consider…

Statistics Theory · Mathematics 2013-03-04 James M. Flegal , Lei Gong

The probability of observing $x_t$ at time $t$, given past observations $x_1...x_{t-1}$ can be computed with Bayes' rule if the true generating distribution $\mu$ of the sequences $x_1x_2x_3...$ is known. If $\mu$ is unknown, but known to…

Machine Learning · Computer Science 2016-11-18 Marcus Hutter

Networks are fundamental models for data used in practically every application domain. In most instances, several implicit or explicit choices about the network definition impact the translation of underlying data to a network…

Artificial Intelligence · Computer Science 2018-01-12 Ivan Brugere , Tanya Y. Berger-Wolf

We study the problem of learning a mixture of multiple linear dynamical systems (LDSs) from unlabeled short sample trajectories, each generated by one of the LDS models. Despite the wide applicability of mixture models for time-series data,…

Machine Learning · Statistics 2022-05-26 Yanxi Chen , H. Vincent Poor

We provide an efficient unified plug-in approach for estimating symmetric properties of distributions given $n$ independent samples. Our estimator is based on profile-maximum-likelihood (PML) and is sample optimal for estimating various…

Machine Learning · Statistics 2022-10-14 Moses Charikar , Zhihao Jiang , Kirankumar Shiragur , Aaron Sidford

The minimum message length principle is an information theoretic criterion that links data compression with statistical inference. This paper studies the strict minimum message length (SMML) estimator for $d$-dimensional exponential…

Information Theory · Computer Science 2014-03-24 James G. Dowty

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

We develop a geometric account of sequence modelling that links patterns in the data to measurable properties of the loss landscape in transformer networks. First, we cast conditional sequence distributions into a Hilbert-space framework…

Machine Learning · Computer Science 2025-04-28 Zhongtian Chen , Daniel Murfet

While much progress has been achieved over the last decades in neuro-inspired machine learning, there are still fundamental theoretical problems in gradient-based learning using combinations of neurons. These problems, such as saddle points…

Machine Learning · Computer Science 2023-06-16 Winfried Lohmiller , Philipp Gassert , Jean-Jacques Slotine

Pairwise difference learning (PDL) has recently been introduced as a new meta-learning technique for regression. Instead of learning a mapping from instances to outcomes in the standard way, the key idea is to learn a function that takes…

Machine Learning · Computer Science 2024-07-01 Mohamed Karim Belaid , Maximilian Rabus , Eyke Hüllermeier

Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data. Broad exposure to different tasks leads to versatile representations enabling general problem solving. But, what are the…