No article text was recorded for this version.
sequential architecture dependency
Version 1 of 139 papers41 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch
- Blog: GPU memory usage optimization for backward propagation in deep network training
- Blog: ConformalLayers: A non-linear sequential neural network with associative layers
- Blog: Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch
- Blog: Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving
- Blog: DiviML: A Module-based Heuristic for Mapping Neural Networks onto Heterogeneous Platforms
- Blog: BackPACK: Packing more into Backprop
- Blog: Challenges in Energy-Efficient Deep Neural Network Training with FPGA
- Blog: LISSNAS: Locality-based Iterative Search Space Shrinkage for Neural Architecture Search
- Blog: FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters
- Blog: PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks
- Blog: MSE-Optimal Neural Network Initialization via Layer Fusion
- Blog: EinDecomp: Decomposition of Declaratively-Specified Machine Learning and Numerical Computations for Parallel Execution
- Blog: Convolutional neural networks at constrained time cost
- Blog: Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning
- Blog: DLFusion: An Auto-Tuning Compiler for Layer Fusion on Deep Neural Network Accelerator
- Blog: Efficient Rematerialization for Deep Networks
- Blog: HiRemate: Hierarchical Approach for Efficient Re-materialization of Neural Networks
- Blog: HyPar: Towards Hybrid Parallelism for Deep Learning Accelerator Array
- Blog: Bandit Limited Discrepancy Search and Application to Machine Learning Pipeline Optimization
- Blog: Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally
- Blog: Efficient Pipeline Planning for Expedited Distributed DNN Training
- Blog: Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models
- Blog: FMM-X3D: FPGA-based modeling and mapping of X3D for Human Action Recognition
- Blog: A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation
- Blog: Deep Pipeline Embeddings for AutoML
- Blog: From NeurODEs to AutoencODEs: A mean-field control framework for width-varying neural networks
- Blog: Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs
- Blog: Distributed CNN Inference on Resource-Constrained UAVs for Surveillance Systems: Design and Optimization
- Blog: Hardware-Aware Machine Learning: Modeling and Optimization
- Blog: SAPipe: Staleness-Aware Pipeline for Data Parallel DNN Training
- Blog: FAIRER: Fairness as Decision Rationale Alignment
- Blog: Automatically Composing Representation Transformations as a Means for Generalization
- Blog: NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
- Blog: Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
- Blog: Survey on Efficient Training of Large Neural Networks
- Blog: QuantPipe: Applying Adaptive Post-Training Quantization for Distributed Transformer Pipelines in Dynamic Edge Environments
- Blog: Pfeife: Automatic Pipeline Parallelism for PyTorch
- Blog: Optimus: Accelerating Large-Scale Multi-Modal LLM Training by Bubble Exploitation
History & citation
Current · Permanent link
- This direction split from Optimization for Non-Linear Computation Graphs (56% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_sequential_architecture_dependency_afef4796,
title = {sequential architecture dependency},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sequential-architecture-dependency/rdr_afef4796f5a24b67a36ae5aa41c238ff},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_sequential_architecture_dependency_afef4796_v1,
title = {sequential architecture dependency},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sequential-architecture-dependency/rdr_afef4796f5a24b67a36ae5aa41c238ff/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}