#autoencoders

Dennis Alexis Valin Dittrichdavdittrich@fediscience.org
2025-03-17

When Dimensionality Hurts: The Role of #LLM Embedding Compression for Noisy Regression Tasks d.repec.org/n?u=RePEc:arx:pape
"… suggest that the optimal dimensionality is dependent on the signal-to-noise ratio, exposing the necessity of feature compression in high noise environments. The implication of the result is that researchers should consider the #noise of a task when making decisions about the dimensionality of text.

… findings indicate that sentiment and emotion-based representations do not provide inherent advantages over learned latent features, implying that their previous success in similar tasks may be attributed to #regularisation effects rather than intrinsic informativeness."
#ML #autoencoders #Overfitting

Fabrizio Musacchiopixeltracker@sigmoid.social
2024-10-28

I just added some extra chapters on #ANN. Since we are using #autoencoders, I thought it could be useful to provide some general introduction on #NeuralNetworks and how they can be tuned.

2024-08-04

'Manifold Learning by Mixture Models of VAEs for Inverse Problems', by Giovanni S. Alberti, Johannes Hertrich, Matteo Santacesaria, Silvia Sciutto.

jmlr.org/papers/v25/23-0396.ht

#autoencoders #manifold #manifolds

2023-12-25

'The Power of Contrast for Feature Learning: A Theoretical Analysis', by Wenlong Ji, Zhun Deng, Ryumei Nakada, James Zou, Linjun Zhang.

jmlr.org/papers/v24/21-1501.ht

#autoencoders #supervised #generative

2023-12-22

'Be More Active! Understanding the Differences Between Mean and Sampled Representations of Variational Autoencoders', by Lisa Bonheme, Marek Grzes.

jmlr.org/papers/v24/21-1145.ht

#autoencoders #disentangled #representations

2023-11-24

New preprint from our group ! 🧠 💻

*Whole-brain modelling of low-dimensional manifold modes reveals organising principle of brain dynamics*
biorxiv.org/content/10.1101/20

#brain #modeling #autoEncoders #variationalAutoEncoder #restingStateNetworks #manifold

2023-10-02

'Lifted Bregman Training of Neural Networks', by Xiaoyu Wang, Martin Benning.

jmlr.org/papers/v24/22-0934.ht

#autoencoders #classifiers #denoising

New Submissions to TMLRtmlrsub@sigmoid.social
2023-08-26

Conditional Sampling of Variational Autoencoders via Iterated Approximate Ancestral Sampling

openreview.net/forum?id=I5sJ6P

#autoencoders #sampling #sampler

New Submissions to TMLRtmlrsub@sigmoid.social
2023-08-20

A simple, efficient and scalable contrastive masked autoencoder for learning visual representations

openreview.net/forum?id=pjdxPt

#autoencoders #autoencoder #imagenet

2023-06-18

"What will happen to GPT-{n} once LLMs contribute much of the language found online? We find that use of model-generated content in training causes irreversible defects in the resulting models, where tails of the original content distribution disappear. ... We demonstrate that it has to be taken seriously if we are to sustain the benefits of training from large-scale data scraped from the web."

#LLM #GPT #ChatGPT #AutoEncoders #MachineLearning #ComputerScience #Research

arxiv.org/abs/2305.17493v2

Published papers at TMLRtmlrpub@sigmoid.social
2023-06-02

The Robustness Limits of SoTA Vision Models to Natural Variation

Mark Ibrahim, Quentin Garrido, Ari S. Morcos, Diane Bouchacourt

Action editor: Dumitru Erhan.

openreview.net/forum?id=QhHLwn

#autoencoders #robust #vision

New Submissions to TMLRtmlrsub@sigmoid.social
2023-05-31

Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation

openreview.net/forum?id=sbkZKB

#autoencoders #mixdvae #mixture

Tiago F. R. Ribeirotiago_ribeiro
2023-04-30

Conditional deep generative models as surrogates for spatial field solution reconstruction with quantified uncertainty in Structural Health Monitoring applications

arxiv.org/abs/2302.08329

Published papers at TMLRtmlrpub@sigmoid.social
2023-04-11

Integrating Bayesian Network Structure into Residual Flows and Variational Autoencoders

Jacobie Mouton, Rodney Stephen Kroon

openreview.net/forum?id=OsKXlW

#autoencoders #generative #flow

Tiago F. R. Ribeirotiago_ribeiro
2023-03-22

Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer Implementations

paperswithcode.com/paper/under

Client Info

Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst