No article text was recorded for this version.
resource-constrained optimization
Version 1 of 1213 papers236 conceptsfrozen 2026-10-04
Papers in this version
- Blog: FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks
- Blog: LESS: LEARNING TO SELECT A STRUCTURED ARCHITECTURE OVER FILTER PRUNING AND LOW-RANK DECOMPOSITION
- Blog: Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems
- Blog: ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations
- Blog: DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection
- Blog: Learning strides in convolutional neural networks
- Blog: DMCP: Differentiable Markov Channel Pruning for Neural Networks
- Blog: CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion
- Blog: DNArch: Learning Convolutional Neural Architectures by Backpropagation
- Blog: Dynamic Multimodal Fusion
- Blog: Dynamic Routing Networks
- Blog: Coverage-Constrained Human-AI Cooperation with Multiple Experts
- Blog: Bayesian Bits: Unifying Quantization and Pruning
- Blog: Masking Kernel for Learning Energy-Efficient Representations for Speaker Recognition and Mobile Health
- Blog: Dynamic Feature Pyramid Networks for Object Detection
- Blog: Structured Pruning of Neural Networks With Budget-Aware Regularization
- Blog: Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
- Blog: Muon Trigger for Mobile Phones
- Blog: DMCP: Differentiable Markov Channel Pruning for Neural Networks
- Blog: Learning with few bits on small-scale devices: From regularization to energy efficiency
- Blog: ∇QDARTS: Quantization as an Elastic Dimension to Differentiable NAS
- Blog: Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
- Blog: Understanding Dynamic Compute Allocation in Recurrent Transformers
- Blog: Dynamic Multi-path Neural Network
- Blog: I3D: Transformer architectures with input-dependent dynamic depth for speech recognition
- Blog: E2-Train: Training State-of-the-art CNNs with Over 80% Less Energy
- Blog: AR-Net: Adaptive Frame Resolution for Efficient Action Recognition
- Blog: AdaViT: Adaptive Vision Transformers for Efficient Image Recognition
- Blog: When Edge Meets Learning: Adaptive Control for Resource-Constrained Distributed Machine Learning
- Blog: Learning Tree-Structured Detection Cascades for Heterogeneous Networks of Embedded Devices
- Blog: A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression
- Blog: Should All Proposals Be Treated Equally in Object Detection?
- Blog: Multi-Tailed Vision Transformer for Efficient Inference
- Blog: Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization
- Blog: Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization
- Blog: Mixed Precision DNNs: All you need is a good parametrization
- Blog: Dynamic Multimodal Fusion
- Blog: Fine-Grained Dynamic Head for Object Detection
- Blog: Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
- Blog: AdaS&S: a One-Shot Supernet Approach for Automatic Embedding Size Search in Deep Recommender System
- Blog: Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting
- Blog: Dynamic Grained Encoder for Vision Transformers
- Blog: Learning Dynamic Network Using a Reuse Gate Function in Semi-Supervised Video Object Segmentation
- Blog: Budget-Aware Adapters for Multi-Domain Learning
- Blog: TrajGNAS: Heterogeneous Multiagent Trajectory Prediction Based on a Graph Neural Architecture Search
- Blog: Compute Cost Amortized Transformer for Streaming ASR
- Blog: FPG-NAS: FLOPs-Aware Gated Differentiable Neural Architecture Search for Efficient 6DoF Pose Estimation
- Blog: Model Complexity of Program Phases
- Blog: Budget-aware pruning: Handling multiple domains with less parameters
- Blog: Toward Carbon-Neutral Human AI: Rethinking Data, Computation, and Learning Paradigms for Sustainable Intelligence
- Blog: DetOFA: Efficient Training of Once-for-All Networks for Object Detection using Path Filter
- Blog: Adaptively Aligned Image Captioning via Adaptive Attention Time
- Blog: AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition
- Blog: Improving Search Engine Efficiency through Contextual Factor Selection
- Blog: AdaFuse: Adaptive Temporal Fusion Network for Efficient Action\n Recognition
- Blog: ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models
- Blog: Dynamic Resolution Network
- Blog: Enhancing Neural Architecture Search With Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices
- Blog: Branched Multi-Task Networks: Deciding what layers to share
- Blog: Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference
Showing 60 of 213 papers.
History & citation
Current · Permanent link
- Budget-Aware Optimization for Efficient Deep Learning merged into this direction (75% overlap)
- Complexity-Aware Differentiable Optimization for Efficient Neural Networks merged into this direction (100% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_resource_constrained_optimization_efb25bc1,
title = {resource-constrained optimization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/resource-constrained-optimization/rdr_efb25bc145f74a839767a749ac1384a6},
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_resource_constrained_optimization_efb25bc1_v1,
title = {resource-constrained optimization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/resource-constrained-optimization/rdr_efb25bc145f74a839767a749ac1384a6/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}