mlsanityData to 7 Oct 2026

Benign Autoencoders

arXiv 2210.00637 ↗First posted 2 Oct 2022cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent progress in Generative Artificial Intelligence (AI) relies on efficient data representations, often featuring encoder-decoder architectures. We formalize the mathematical problem of finding the optimal encoder-decoder pair and characterize its solution, which we name the "benign autoencoder" (BAE). We prove that BAE projects data onto a manifold whose dimension is the optimal compressibility dimension of the generative problem. We highlight surprising connections between BAE and several recent developments in AI, such as conditional GANs, context encoders, stable diffusion, stacked autoencoders, and the learning capabilities of generative models. As an illustration, we show how BAE can find optimal, low-dimensional latent representations that improve the performance of a discriminator under a distribution shift. By compressing "malignant" data dimensions, BAE leads to smoother and more stable gradients.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 63 references that are in the map. First posted on arXiv 2 Oct 2022.

Builds on

25 of 63 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  8. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  11. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  12. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
13 more
  1. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  2. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  3. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  4. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  5. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  6. 2016Adversarially Learned Inferencecited by 216
  7. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  8. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 213
  9. 2020When Do Neural Networks Outperform Kernel Methods?cited by 150
  10. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  11. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 121
  12. 2018Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flowcited by 103
  13. 2017Face Aging With Conditional Generative Adversarial Networkscited by 51

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Geometry-Preserving Encoder/Decoder in Latent Generative Models
  2. 2025A solvable model of learning generative diffusion: theory and insights
  3. 2025Manifold Decoders: A Framework for Generative Modeling from Nonlinear Embeddings
  4. 2023Complexity Matters: Rethinking the Latent Space for Generative Modeling
  5. 2026The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer
  6. 2025CoVAE: Consistency Training of Variational Autoencoders
  7. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
  8. 2024Sample what you cant compress