SOTAVerified

Computational Efficiency

Methods and optimizations to reduce the computational resources (e.g., time, memory, or power) needed for training and inference in models. This involves techniques that streamline processing, optimize algorithms, or leverage hardware to enhance performance without compromising accuracy.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 3861–3870 of 4891 papers

TitleStatusHype
Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis—0
Boundary Graph Neural Networks for 3D SimulationsCode0
Algorithm Unrolling for Massive Access via Deep Neural Network with Theoretical Guarantee—0
Training or Architecture? How to Incorporate Invariance in Neural Networks—0
Pre-Trained Models: Past, Present and Future—0
Precise phase retrieval for propagation-based images using discrete mathematics—0
Quantum Speedup of Natural Gradient for Variational Bayes—0
Ex uno plures: Splitting One Model into an Ensemble of Subnetworks—0
ZoPE: A Fast Optimizer for ReLU Networks with Low-Dimensional Inputs—0
Fast and More Powerful Selective Inference for Sparse High-order Interaction Model—0
Show:102550
← PrevPage 387 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified