SOTAVerified

Model Selection

Given a set of candidate models, the goal of Model Selection is to select the model that best approximates the observed data and captures its underlying regularities. Model Selection criteria are defined such that they strike a balance between the goodness of fit, and the generalizability or complexity of the models.

Source: Kernel-based Information Criterion

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–160 of 2050 papers

TitleStatusHype
Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD GeneralizationCode1
Unsupervised Offline Changepoint Detection EnsemblesCode1
Where and What? Examining Interpretable Disentangled RepresentationsCode1
OTCE: A Transferability Metric for Cross-Domain Cross-Task RepresentationsCode1
Modeling the Second Player in Distributionally Robust OptimizationCode1
CNN Model & Tuning for Global Road Damage DetectionCode1
LogME: Practical Assessment of Pre-trained Models for Transfer LearningCode1
Adversarial Branch Architecture Search for Unsupervised Domain AdaptationCode1
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models CascadeCode1
Robustness of Accuracy Metric and its Inspirations in Learning with Noisy LabelsCode1
Show:102550
← PrevPage 16 of 205Next →

No leaderboard results yet.