No article text was recorded for this version.
recomputation overhead (memory-computation trade-off)
Version 1 of 136 papers36 conceptsfrozen 2026-10-04
Papers in this version
- Blog: FACM: Flow-Anchored Consistency Models
- Blog: Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction
- Blog: Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
- Blog: OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot
- Blog: A Computational-Graph Partitioning Method for Training Memory-Constrained DNNs
- Blog: RevPHiSeg: A Memory-Efficient Neural Network for Uncertainty Quantification in Medical Image Segmentation
- Blog: Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropagation
- Blog: ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
- Blog: Beam-search SIEVE for low-memory speech recognition
- Blog: BP-Modified Local Loss for Efficient Training of Deep Neural Networks
- Blog: Nesterov Method for Asynchronous Pipeline Parallel Optimization
- Blog: DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training
- Blog: Learning with Auxiliary Activation for Memory-Efficient Training
- Blog: The Reversible Residual Network: Backpropagation Without Storing Activations
- Blog: Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks
- Blog: Spatially Parallel Convolutions
- Blog: An In-depth Study of Stochastic Backpropagation
- Blog: In-Place Activated BatchNorm for Memory-Optimized Training of DNNs
- Blog: Deeper Image Quality Transfer: Training Low-Memory Neural Networks for 3D Images
- Blog: GPU memory usage optimization for backward propagation in deep network training
- Blog: DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training
- Blog: DiTFastAttn: Attention Compression for Diffusion Transformer Models
- Blog: Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
- Blog: A Partially Reversible U-Net for Memory-Efficient Volumetric Image Segmentation
- Blog: Run-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative Models
- Blog: Run-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative Models
- Blog: Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning
- Blog: Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
- Blog: With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning
- Blog: A Fast Learning Algorithm for Image Segmentation with Max-Pooling Convolutional Networks
- Blog: Relational Feature Caching for Accelerating Diffusion Transformers
- Blog: KV Cache Transform Coding for Compact Storage in LLM Inference
- Blog: Backprop with Approximate Activations for Memory-efficient Network Training
- Blog: Gradient-based Editing of Memory Examples for Online Task-free Continual Learning
- Blog: Obscura: Concealing Recomputation Overhead in Training of Large Language Models with Bubble-filling Pipeline Transformation
- Blog: Towards Lossless Memory-efficient Training of Spiking Neural Networks via Gradient Checkpointing and Spike Compression
History & citation
Current · Permanent link
- This direction split from Activation Management for Memory Efficient Deep Learning (86% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_recomputation_overhead_memory_computatio_b432380e,
title = {recomputation overhead (memory-computation trade-off)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/recomputation-overhead-memory-computation-trade-off/rdr_b432380e335949f9af340602f976136c},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_recomputation_overhead_memory_computatio_b432380e_v1,
title = {recomputation overhead (memory-computation trade-off)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/recomputation-overhead-memory-computation-trade-off/rdr_b432380e335949f9af340602f976136c/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}