English
Related papers

Related papers: Lost and Found in Translation: Variational Diagnos…

200 papers

Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data. Once trained, one can hope to detect out-of-distribution (abnormal) latent vectors, but several issues arise when…

Machine Learning · Computer Science 2026-05-12 Alejandro Ascarate , Leo Lebrat , Rodrigo Santa Cruz , Clinton Fookes , Olivier Salvado

Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. The VAE objective consists of two terms, (i) reconstruction and (ii) KL regularization, balanced by a…

Machine Learning · Computer Science 2019-06-12 Hao Fu , Chunyuan Li , Xiaodong Liu , Jianfeng Gao , Asli Celikyilmaz , Lawrence Carin

Coding theorems in quantum Shannon theory express the ultimate rates at which a sender can transmit information over a noisy quantum channel. More often than not, the known formulas expressing these transmission rates are intractable,…

Quantum Physics · Physics 2010-06-15 Kamil Bradler , Patrick Hayden , Dave Touchette , Mark M. Wilde

We consider classical message transmission under entanglement assistance for compound memoryless and arbitrarily varying quantum channels. In both cases, we prove general coding theorems together with corresponding weak converse bounds. In…

Quantum Physics · Physics 2017-01-27 Holger Boche , Gisbert Janßen , Stephan Kaltenstadler

Variational Auto-Encoders (VAEs) have shown great potential in the unsupervised learning of data distributions. An VAE trained on normal images is expected to only be able to reconstruct normal images, allowing the localization of anomalous…

Computer Vision and Pattern Recognition · Computer Science 2020-05-22 Leixin Zhou , Wenxiang Deng , Xiaodong Wu

This work presents an analysis of the hidden representations of Variational Autoencoders (VAEs) using the Intrinsic Dimension (ID) and the Information Imbalance (II). We show that VAEs undergo a transition in behaviour once the bottleneck…

Machine Learning · Computer Science 2024-11-05 Charles Camboulin , Diego Doimo , Aldo Glielmo

Learning latent representations that are simultaneously expressive, geometrically well-structured, and reliably calibrated remains a central challenge for Variational Autoencoders (VAEs). Standard VAEs typically assume a diagonal Gaussian…

Machine Learning · Computer Science 2025-12-02 Mehmet Can Yavuz

We introduce a new quantum decoder based on a variant of the pretty good measurement, but defined via an alternative matrix quotient. We use this decoder to show new lower bounds on the error exponent both in the one-shot and asymptotic…

Quantum Physics · Physics 2025-07-29 Salman Beigi , Marco Tomamichel

The highest fidelity of quantum error-correcting codes of length n and rate R is proven to be lower bounded by 1 - exp [-n E(R)+ o(n)] for some function E(R) on noisy quantum channels that are subject to not necessarily independent errors.…

Quantum Physics · Physics 2015-06-26 Mitsuru Hamada

We study the estimation of an unknown quantum channel $\mathcal{E}$ with input dimension $d_1$, output dimension $d_2$ and Kraus rank at most $r$. We establish a connection between the query complexities in two models: (i) access to…

Quantum Physics · Physics 2026-02-04 Kean Chen , Nengkun Yu , Zhicheng Zhang

Trainable input embedding tables are a standard component of modern language models. We ask whether they are actually necessary at the input interface. For a vocabulary of size $V$, exact token identity requires only $K=\lceil \log_2…

Computation and Language · Computer Science 2026-05-12 A. Bochkov

We consider compound as well as arbitrarily varying classical-quantum channel models. For classical-quantum compound channels, we give an elementary proof of the direct part of the coding theorem. A weak converse under average error…

Quantum Physics · Physics 2016-08-14 Igor Bjelaković , Holger Boche , Gisbert Janßen , Janis Nötzel

We propose a novel Conditional Latent space Variational Autoencoder (CL-VAE) to perform improved pre-processing for anomaly detection on data with known inlier classes and unknown outlier classes. This proposed variational autoencoder (VAE)…

Machine Learning · Computer Science 2024-10-17 Oskar Åström , Alexandros Sopasakis

An additive noise channel is considered, in which the distribution of the noise is nonparametric and unknown. The problem of learning encoders and decoders based on noise samples is considered. For uncoded communication systems, the problem…

Information Theory · Computer Science 2021-11-17 Nir Weinberger

Unsupervised learning with functional data is an emerging paradigm of machine learning research with applications to computer vision, climate modeling and physical systems. A natural way of modeling functional data is by learning operators…

Machine Learning · Computer Science 2023-02-22 Jacob H. Seidman , Georgios Kissas , George J. Pappas , Paris Perdikaris

Advances in highly sensitive detection techniques for classical coherent communication systems have reduced the received signal power requirements to a few photons per bit. At this level one can take advantage of the quantum noise to create…

Quantum Physics · Physics 2019-07-23 Rupesh Kumar , Adrian Wonfor , Richard Penty , Tim Spiller , Ian White

Identifying customer segments in retail banking portfolios with different risk profiles can improve the accuracy of credit scoring. The Variational Autoencoder (VAE) has shown promising results in different research domains, and it has been…

Computational Engineering, Finance, and Science · Computer Science 2018-06-08 Rogelio Andrade Mancisidor , Michael Kampffmeyer , Kjersti Aas , Robert Jenssen

Electricity distribution cable networks suffer from incomplete and unbalanced data, hindering the effectiveness of machine learning models for predictive maintenance and reliability evaluation. Features such as the installation date of the…

Machine Learning · Computer Science 2025-01-22 Konrad Sundsgaard , Kutay Bölat , Guangya Yang

We consider rate R = k/n causal linear codes that map a sequence of k-dimensional binary vectors {b_t} to a sequence of n-dimensional binary vectors {c_t}, such that each c_t is a function of {b_1,b_2,...,b_t}. Such a code is called anytime…

Information Theory · Computer Science 2011-06-02 Ravi Teja Sukhavasi , Babak Hassibi

We revisit the idea of using deep neural networks for one-shot decoding of random and structured codes, such as polar codes. Although it is possible to achieve maximum a posteriori (MAP) bit error rate (BER) performance for both code…

Information Theory · Computer Science 2017-01-27 Tobias Gruber , Sebastian Cammerer , Jakob Hoydis , Stephan ten Brink