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 3591–3600 of 4891 papers

TitleStatusHype
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions—0
SpecNet2: Orthogonalization-free spectral embedding by neural networksCode0
Scalable Exploration for Neural Online Learning to Rank with Perturbed Feedback—0
Stochastic Gradient Descent without Full Data ShuffleCode0
Geometric Policy Iteration for Markov Decision Processes—0
Discovery and density estimation of latent confounders in Bayesian networks with evidence lower bound—0
Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd CountingCode0
How Much is Enough? A Study on Diffusion Times in Score-based Generative Models—0
An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training—0
8-bit Numerical Formats for Deep Neural Networks—0
Show:102550
← PrevPage 360 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified