Lossless compression with state space models using bits back coding

• URL: http://arxiv.org/abs/2103.10150v2
• Date: Fri, 19 Mar 2021 10:53:45 GMT
• Title: Lossless compression with state space models using bits back coding
• Authors: James Townsend, Iain Murray
• Abstract summary: We generalize the 'bits back with ANS' method to time-series models with a latent Markov structure. We provide experimental evidence that our method is effective for small scale models, and discuss its applicability to larger scale settings such as video compression.
• Score: 17.625326990547332
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: We generalize the 'bits back with ANS' method to time-series models with a latent Markov structure. This family of models includes hidden Markov models (HMMs), linear Gaussian state space models (LGSSMs) and many more. We provide experimental evidence that our method is effective for small scale models, and discuss its applicability to larger scale settings such as video compression.

Related papers

• Diffusion Product Quantization [18.32568431229839]
  We explore the quantization of diffusion models in extreme compression regimes to reduce model size while maintaining performance. We apply our compression method to the DiT model on ImageNet and consistently outperform other quantization approaches.
  arXiv  Detail & Related papers  (2024-11-19T07:47:37Z)
• Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective [52.778766190479374]
  Latent-based image generative models have achieved notable success in image generation tasks. Despite sharing the same latent space, autoregressive models significantly lag behind LDMs and MIMs in image generation. We propose a simple but effective discrete image tokenizer to stabilize the latent space for image generative modeling.
  arXiv  Detail & Related papers  (2024-10-16T12:13:17Z)
• Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models [9.91972450276408]
  This paper introduces an innovative approach for the parametric and practical compression of Large Language Models (LLMs) based on reduced order modelling. Our method represents a significant advancement in model compression by leveraging matrix decomposition, demonstrating superior efficacy compared to the prevailing state-of-the-art structured pruning method.
  arXiv  Detail & Related papers  (2023-12-12T07:56:57Z)
• CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing [83.63107444454938]
  We propose a consistency-regularized ensemble learning approach based on perturbed models, named CAMERO. Specifically, we share the weights of bottom layers across all models and apply different perturbations to the hidden representations for different models, which can effectively promote the model diversity. Our experiments using large language models demonstrate that CAMERO significantly improves the generalization performance of the ensemble model.
  arXiv  Detail & Related papers  (2022-04-13T19:54:51Z)
• Riemannian Score-Based Generative Modeling [56.20669989459281]
  We introduce score-based generative models (SGMs) demonstrating remarkable empirical performance. Current SGMs make the underlying assumption that the data is supported on a Euclidean manifold with flat geometry. This prevents the use of these models for applications in robotics, geoscience or protein modeling.
  arXiv  Detail & Related papers  (2022-02-06T11:57:39Z)
• Low-Rank Constraints for Fast Inference in Structured Models [110.38427965904266]
  This work demonstrates a simple approach to reduce the computational and memory complexity of a large class of structured models. Experiments with neural parameterized structured models for language modeling, polyphonic music modeling, unsupervised grammar induction, and video modeling show that our approach matches the accuracy of standard models at large state spaces.
  arXiv  Detail & Related papers  (2022-01-08T00:47:50Z)
• What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression [68.82486784654817]
  We study two popular model compression techniques including knowledge distillation and pruning. We show that compressed models are significantly less robust than their PLM counterparts on adversarial test sets. We develop a regularization strategy for model compression based on sample uncertainty.
  arXiv  Detail & Related papers  (2021-10-16T00:20:04Z)
• Lossless Compression with Latent Variable Models [4.289574109162585]
  We use latent variable models, which we call 'bits back with asymmetric numeral systems' (BB-ANS) The method involves interleaving encode and decode steps, and achieves an optimal rate when compressing batches of data. We describe 'Craystack', a modular software framework which we have developed for rapid prototyping of compression using deep generative models.
  arXiv  Detail & Related papers  (2021-04-21T14:03:05Z)
• Scaling Hidden Markov Language Models [118.55908381553056]
  This work revisits the challenge of scaling HMMs to language modeling datasets. We propose methods for scaling HMMs to massive state spaces while maintaining efficient exact inference, a compact parameterization, and effective regularization.
  arXiv  Detail & Related papers  (2020-11-09T18:51:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.