# BackSlash: Rate Constrained Optimized Training of Large Language Models

arXiv: https://arxiv.org/abs/2504.16968 · HTML: https://mlsanity.com/paper/2504.16968/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 54 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Builds on (most cited first, 30 of 30)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://mlsanity.com/paper/1712.01887/) (2017)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [Speeding up Convolutional Neural Networks with Low Rank Expansions](https://mlsanity.com/paper/1405.3866/) (2014)
- [PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing](https://mlsanity.com/paper/1805.04409/) (2018)
- [Trained Ternary Quantization](https://mlsanity.com/paper/1612.01064/) (2016)
- [Ternary Weight Networks](https://mlsanity.com/paper/1605.04711/) (2016)
- [Bayesian Neural Network Priors Revisited](https://mlsanity.com/paper/2102.06571/) (2021)
- [Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation](https://mlsanity.com/paper/2111.14826/) (2021)
- [DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer](https://mlsanity.com/paper/1707.01220/) (2017)
- [Towards the Limit of Network Quantization](https://mlsanity.com/paper/1612.01543/) (2016)
- [T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor](https://mlsanity.com/paper/1904.02698/) (2019)
- [Rate Distortion For Model Compression: From Theory To Practice](https://mlsanity.com/paper/1810.06401/) (2018)
- [Efficient Dynamic-NeRF Based Volumetric Video Coding with Rate Distortion Optimization](https://mlsanity.com/paper/2402.01380/) (2024)
- [Domain-adaptive deep network compression](https://mlsanity.com/paper/1709.01041/) (2017)
- [Dynamic Structure Pruning for Compressing CNNs](https://mlsanity.com/paper/2303.09736/) (2023)
- [Structured Bayesian Compression for Deep Neural Networks Based on The Turbo-VBI Approach](https://mlsanity.com/paper/2302.10483/) (2023)
- [GAN-based Image Compression with Improved RDO Process](https://mlsanity.com/paper/2306.10461/) (2023)
- [LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratch](https://mlsanity.com/paper/2309.14157/) (2023)

## Built on by (most cited first, 1 of 1)

- [It Takes a Good Model to Train a Good Model: Generalized Gaussian Priors for Optimized LLMs](https://mlsanity.com/paper/2506.00486/) (2025)

## Abstract (arXiv)

The rapid advancement of large-language models (LLMs) has driven extensive research into parameter compression after training has been completed, yet compression during the training phase remains largely unexplored. In this work, we introduce Rate-Constrained Training (BackSlash), a novel training-time compression approach based on rate-distortion optimization (RDO). BackSlash enables a flexible trade-off between model accuracy and complexity, significantly reducing parameter redundancy while preserving performance. Experiments in various architectures and tasks demonstrate that BackSlash can reduce memory usage by 60% - 90% without accuracy loss and provides significant compression gain compared to compression after training. Moreover, BackSlash proves to be highly versatile: it enhances generalization with small Lagrange multipliers, improves model robustness to pruning (maintaining accuracy even at 80% pruning rates), and enables network simplification for accelerated inference on edge devices.