No article text was recorded for this version.
backpropagation memory overhead
Version 1 of 152 papers52 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Feed-Forward On-Edge Fine-Tuning Using Static Synthetic Gradient Modules
- Blog: Non-Discriminative Data or Weak Model? On the Relative Importance of Data and Model Resolution
- Blog: Loop Unrolled Shallow Equilibrium Regularizer (LUSER) - A Memory-Efficient Inverse Problem Solver
- Blog: Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures
- Blog: A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration
- Blog: Gradient-free Decoder Inversion in Latent Diffusion Models
- Blog: Momentum Auxiliary Network for Supervised Local Learning
- Blog: Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning
- Blog: Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
- Blog: TinyFoA: Memory Efficient Forward-Only Algorithm for On-Device Learning
- Blog: SubZero: Random Subspace Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning
- Blog: Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
- Blog: Deep Neural Networks motivated by Partial Differential Equations
- Blog: Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
- Blog: BAFFLE: A Baseline of Backpropagation-Free Federated Learning
- Blog: FedFwd: Federated Learning without Backpropagation
- Blog: Stepping Forward on the Last Mile
- Blog: BP-Modified Local Loss for Efficient Training of Deep Neural Networks
- Blog: Initialized Equilibrium Propagation for Backprop-Free Training
- Blog: Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer
- Blog: DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training
- Blog: Dynamic Stashing Quantization for Efficient Transformer Training
- Blog: Learning with Auxiliary Activation for Memory-Efficient Training
- Blog: VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
- Blog: Moonwalk: Inverse-Forward Differentiation
- Blog: Training Neural Networks Using Features Replay
- Blog: FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters
- Blog: ActMAD: Activation Matching to Align Distributions for Test-Time-Training
- Blog: Exploring Selective Layer Fine-Tuning in Federated Learning
- Blog: ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces
- Blog: Blockwise Self-Supervised Learning at Scale
- Blog: Forward-Forward Algorithm for Hyperspectral Image Classification
- Blog: Multi-split Reversible Transformers Can Enhance Neural Machine Translation
- Blog: Learning Light-Weight Translation Models from Deep Transformer
- Blog: Efficient ConvBN Blocks for Transfer Learning and Beyond
- Blog: Momentum Residual Neural Networks
- Blog: Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
- Blog: HetPipe: Enabling Large DNN Training on (Whimpy) Heterogeneous GPU Clusters through Integration of Pipelined Model Parallelism and Data Parallelism
- Blog: FoCTTA: Low-Memory Continual Test-Time Adaptation with Focus
- Blog: GPU memory usage optimization for backward propagation in deep network training
- Blog: Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism
- Blog: DA3: Dynamic Additive Attention Adaption for Memory-Efficient On-Device Multi-Domain Learning
- Blog: Memory-efficient Learning for Large-scale Computational Imaging
- Blog: HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion
- Blog: Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes
- Blog: LION: Implicit Vision Prompt Tuning
- Blog: Study of Training Dynamics for Memory-Constrained Fine-Tuning
- Blog: Asynchronous Event Processing with Local-Shift Graph Convolutional Network
- Blog: HyC-LoRA: Memory Efficient LoRA Fine-tuning with Hybrid Activation Compression
- Blog: LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning
- Blog: MobileTL: On-Device Transfer Learning with Inverted Residual Blocks
- Blog: Forward Learning of Graph Neural Networks
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_backpropagation_memory_overhead_c049b217,
title = {backpropagation memory overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/backpropagation-memory-overhead/rdr_c049b2177b9a4628a1ab9465114f1cbd},
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_backpropagation_memory_overhead_c049b217_v1,
title = {backpropagation memory overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/backpropagation-memory-overhead/rdr_c049b2177b9a4628a1ab9465114f1cbd/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}