English
Related papers

Related papers: Universal Regular Conditional Distributions

200 papers

We introduce compositional tensor trains (CTTs) for the approximation of multivariate functions, a class of models obtained by composing low-rank functions in the tensor-train format. This format can encode standard approximation tools,…

Numerical Analysis · Mathematics 2025-12-23 Martin Eigel , Charles Miranda , Anthony Nouy , David Sommer

Distributional reinforcement learning (DRL) has achieved empirical success in various domains. One core task in DRL is distributional policy evaluation, which involves estimating the return distribution $\eta^\pi$ for a given policy $\pi$.…

Machine Learning · Statistics 2025-01-17 Yang Peng , Liangyu Zhang , Zhihua Zhang

Persistence diagrams are common descriptors of the topological structure of data appearing in various classification and regression tasks. They can be generalized to Radon measures supported on the birth-death plane and endowed with an…

Computational Geometry · Computer Science 2022-12-19 Alex Elchesen , Iryna Hartsock , Jose A. Perea , Tatum Rask

In this paper we consider a new class of RBF (Radial Basis Function) neural networks, in which smoothing factors are replaced with shifts. We prove under certain conditions on the activation function that these networks are capable of…

Machine Learning · Computer Science 2023-04-11 Aysu Ismayilova , Muhammad Ismayilov

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

Deep Gaussian processes (DGPs) are multi-layer hierarchical generalisations of Gaussian processes (GPs) and are formally equivalent to neural networks with multiple, infinitely wide hidden layers. DGPs are nonparametric probabilistic models…

Motivated by applications to prediction and forecasting, we suggest methods for approximating the conditional distribution function of a random variable Y given a dependent random d-vector X. The idea is to estimate not the distribution of…

Statistics Theory · Mathematics 2007-06-13 Peter Hall , Qiwei Yao

Most stochastic gradient descent algorithms can optimize neural networks that are sub-differentiable in their parameters; however, this implies that the neural network's activation function must exhibit a degree of continuity which limits…

Neural and Evolutionary Computing · Computer Science 2021-12-16 Anastasis Kratsios , Behnoosh Zamanlooy

Large language models are capable of in-context learning, the ability to perform new tasks at test time using a handful of input-output examples, without parameter updates. We develop a universal approximation theory to elucidate how…

Machine Learning · Computer Science 2025-08-29 Gen Li , Yuchen Jiao , Yu Huang , Yuting Wei , Yuxin Chen

One of the theoretical pillars that sustain certain machine learning models are universal approximation theorems, which prove that they can approximate all functions from a function class to arbitrary precision. Independently, classical…

Disordered Systems and Neural Networks · Physics 2026-04-28 Tobias Reinhart , Gemma De les Coves

Universal approximation theorems provide a mathematical explanation for the expressive power of neural networks. They assert that, under mild conditions on the activation function, feedforward neural networks are dense in broad function…

Machine Learning · Computer Science 2026-05-21 Soumendu Sundar Mukherjee , Himasish Talukdar

Neural networks are one tool for approximating non-linear differential equations used in scientific computing tasks such as surrogate modeling, real-time predictions, and optimal control. PDE foundation models utilize neural networks to…

Machine Learning · Computer Science 2025-02-11 Elisa Negrini , Yuxuan Liu , Liu Yang , Stanley J. Osher , Hayden Schaeffer

Many practical problems need the output of a machine learning model to satisfy a set of constraints, $K$. Nevertheless, there is no known guarantee that classical neural network architectures can exactly encode constraints while…

Machine Learning · Computer Science 2022-02-10 Anastasis Kratsios , Behnoosh Zamanlooy , Tianlin Liu , Ivan Dokmanić

Since open social platforms allow for a large and continuous flow of unverified information, rumors can emerge unexpectedly and spread quickly. However, existing rumor detection (RD) models often assume the same training and testing…

Computation and Language · Computer Science 2022-09-12 Yuhui Zuo , Wei Zhu , Guoyong Cai

The machine learning community has recently put effort into quantized or low-precision arithmetics to scale large models. This paper proposes performing probabilistic inference in the quantized, discrete parameter space created by these…

Machine Learning · Computer Science 2025-08-20 Aleksanteri Sladek , Martin Trapp , Arno Solin

Potts models, which can be used to analyze dependent observations on a lattice, have seen widespread application in a variety of areas, including statistical mechanics, neuroscience, and quantum computing. To address the intractability of…

Computation · Statistics 2021-10-15 Anirban Chakraborty , Matthias Katzfuss , Joseph Guinness

We devise a distributional variant of gradient temporal-difference (TD) learning. Distributional reinforcement learning has been demonstrated to outperform the regular one in the recent study \citep{bellemare2017distributional}. In the…

Machine Learning · Computer Science 2019-04-04 Chao Qu , Shie Mannor , Huan Xu

We present a deep transformation model for probabilistic regression. Deep learning is known for outstandingly accurate predictions on complex data but in regression tasks, it is predominantly used to just predict a single number. This…

Machine Learning · Statistics 2020-04-02 Beate Sick , Torsten Hothorn , Oliver Dürr

We analyse quantile temporal-difference learning (QTD), a distributional reinforcement learning algorithm that has proven to be a key component in several successful large-scale applications of reinforcement learning. Despite these…

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock