English
Related papers

Related papers: Efficient Mixture Learning in Black-Box Variationa…

200 papers

Here we propose the Reweighted Autoencoded Variational Bayes for Enhanced Sampling (RAVE) method, a new iterative scheme that uses the deep learning framework of variational autoencoders to enhance sampling in molecular simulations. RAVE…

Chemical Physics · Physics 2018-02-13 Joao Marcelo Lamim Ribeiro , Pablo Bravo Collado , Yihang Wang , Pratyush Tiwary

Semi-Supervised Variational Autoencoders (SSVAEs) are widely used models for data efficient learning. In this paper, we question the adequacy of the standard design of sequence SSVAEs for the task of text classification as we exhibit two…

Computation and Language · Computer Science 2021-09-28 Ghazi Felhi , Joseph Le Roux , Djamé Seddah

Variational autoencoders (VAEs) are a standard framework for inducing latent variable models that have been shown effective in learning text representations as well as in text generation. The key challenge with using VAEs is the {\it…

Machine Learning · Computer Science 2020-05-01 Serhii Havrylov , Ivan Titov

We propose a novel deep clustering method that integrates Variational Autoencoders (VAEs) into the Expectation-Maximization (EM) framework. Our approach models the probability distribution of each cluster with a VAE and alternates between…

Machine Learning · Computer Science 2025-01-14 Michael Adipoetra , Ségolène Martin

In the field of multi-objective optimization algorithms, multi-objective Bayesian Global Optimization (MOBGO) is an important branch, in addition to evolutionary multi-objective optimization algorithms (EMOAs). MOBGO utilizes Gaussian…

Machine Learning · Computer Science 2019-06-14 Kaifeng Yang , Michael Emmerich , André Deutz , Thomas Bäck

We introduce TrustVI, a fast second-order algorithm for black-box variational inference based on trust-region optimization and the reparameterization trick. At each iteration, TrustVI proposes and assesses a step based on minibatches of…

Machine Learning · Computer Science 2017-11-07 Jeffrey Regier , Michael I. Jordan , Jon McAuliffe

Variational inference has become a widely used method to approximate posteriors in complex latent variables models. However, deriving a variational inference algorithm generally requires significant model-specific analysis, and these…

Machine Learning · Statistics 2014-01-03 Rajesh Ranganath , Sean Gerrish , David M. Blei

Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned for a specific downstream task. The most common fine-tuning method is to update pretrained weights via low-rank adaptation (LoRA). Existing initialization…

Machine Learning · Computer Science 2025-10-21 Fabian Paischer , Lukas Hauzenberger , Thomas Schmied , Benedikt Alkin , Marc Peter Deisenroth , Sepp Hochreiter

This work introduces a new method for selecting the number of components in finite mixture models (FMMs) using variational Bayes, inspired by the large-sample properties of the Evidence Lower Bound (ELBO) derived from mean-field (MF)…

Methodology · Statistics 2026-04-23 Chenyang Wang , Yun Yang

This paper proposes an alternative algorithm for multichannel variational autoencoder (MVAE), a recently proposed multichannel source separation approach. While MVAE is notable in its impressive source separation performance, the…

Machine Learning · Computer Science 2019-02-14 Li Li , Hirokazu Kameoka , Shoji Makino

Bayesian (deep) neural networks (BNN) are often more attractive than the vanilla point-estimate deep learning in various aspects including uncertainty quantification, robustness to noise, resistance to overfitting, and more. The variational…

Machine Learning · Computer Science 2026-05-22 Minyoung Kim

This paper introduces a modified variational autoencoder (VAEs) that contains an additional neural network branch. The resulting branched VAE (BVAE) contributes a classification component based on the class labels to the total loss and…

Machine Learning · Computer Science 2024-01-08 Ahmed Salah , David Yevick

Real world datasets often contain entries with missing elements e.g. in a medical dataset, a patient is unlikely to have taken all possible diagnostic tests. Variational Autoencoders (VAEs) are popular generative models often used for…

Machine Learning · Computer Science 2021-03-23 Mark Collier , Alfredo Nazabal , Christopher K. I. Williams

The vector quantization is a widely used method to map continuous representation to discrete space and has important application in tokenization for generative mode, bottlenecking information and many other tasks in machine learning. Vector…

Machine Learning · Computer Science 2024-10-15 Mingyuan Yan , Jiawei Wu , Rushi Shah , Dianbo Liu

When trained effectively, the Variational Autoencoder (VAE) is both a powerful language model and an effective representation learning framework. In practice, however, VAEs are trained with the evidence lower bound (ELBO) as a surrogate…

Machine Learning · Computer Science 2019-09-04 Bohan Li , Junxian He , Graham Neubig , Taylor Berg-Kirkpatrick , Yiming Yang

Geoscientists use observed data to estimate properties of the Earth's interior. This often requires non-linear inverse problems to be solved and uncertainties to be estimated. Bayesian inference solves inverse problems under a probabilistic…

Geophysics · Physics 2024-01-01 Xuebin Zhao , Andrew Curtis

Deep state-space models (DSSMs) enable temporal predictions by learning the underlying dynamics of observed sequence data. They are often trained by maximising the evidence lower bound. However, as we show, this does not ensure the model…

Machine Learning · Computer Science 2026-02-27 Alexej Klushyn , Richard Kurle , Maximilian Soelch , Botond Cseke , Patrick van der Smagt

Black-box optimization is a powerful approach for discovering global optima in noisy and expensive black-box functions, a problem widely encountered in real-world scenarios. Recently, there has been a growing interest in leveraging domain…

Machine Learning · Computer Science 2024-02-06 Dat Phan-Trong , Hung The Tran , Alistair Shilton , Sunil Gupta

A critical approach for efficiently deploying Mixture-of-Experts (MoE) models with massive parameters is quantization. However, state-of-the-art MoE models suffer from non-negligible accuracy loss with extreme quantization, such as under 4…

Machine Learning · Computer Science 2025-04-08 Beichen Huang , Yueming Yuan , Zelei Shao , Minjia Zhang

Bayesian methods are particularly effective for addressing inverse problems due to their ability to manage uncertainties inherent in the inference process. However, employing these methods with costly forward models poses significant…

Computational Engineering, Finance, and Science · Computer Science 2025-10-30 G. Robalo Rei , C. P. Schmidt , J. Nitzler , M. Dinkel , W. A. Wall