activity
20012026
most citedRadon-Nikodym derivatives of quantum operations

38 citations · 81 across the 27 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2025

Expressivity of Quadratic Neural ODEs

Joshua Hanson, Maxim Raginsky

This work focuses on deriving quantitative approximation error bounds for neural ordinary differential equations having at most quadratic nonlinearities in the dynamics. The simple…

cs.LG20222 cited

Input-to-State Stable Neural Ordinary Differential Equations with Applications to Transient Modeling of Circuits

Alan Yang, Jie Xiong, Maxim Raginsky +1

This paper proposes a class of neural ordinary differential equations parametrized by provably input-to-state stable continuous-time recurrent neural networks. The model dynamics a…

cs.LG202114 cited

Information-theoretic generalization bounds for black-box learning algorithms

Hrayr Harutyunyan, Maxim Raginsky, Greg Ver Steeg +1

We derive information-theoretic generalization bounds for supervised learning algorithms based on the information contained in predictions rather than in the output of the training…

cs.LG2019

Model-Augmented Estimation of Conditional Mutual Information for Feature Selection

Alan Yang, AmirEmad Ghassami, Maxim Raginsky +2

Markov blanket feature selection, while theoretically optimal, is generally challenging to implement. This is due to the shortcomings of existing approaches to conditional independ…

cs.LG2019

Universal Approximation of Input-Output Maps by Temporal Convolutional Nets

Joshua Hanson, Maxim Raginsky

There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in traini…

cs.LG2019

Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit

Belinda Tzen, Maxim Raginsky

In deep latent Gaussian models, the latent variable is generated by a time-inhomogeneous Markov chain, where at each time step we pass the current state through a parametric nonlin…