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 151–200 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
Task-Agnostic Amortized Inference of Gaussian Process HyperparametersCode1
A Survey and Implementation of Performance Metrics for Self-Organized MapsCode1
Online Active Model Selection for Pre-trained ClassifiersCode1
Cardea: An Open Automated Machine Learning Framework for Electronic Health RecordsCode1
Automating Outlier Detection via Meta-LearningCode1
An information criterion for automatic gradient tree boostingCode1
Machine Learning for Dynamic Resource Allocation in Network Function VirtualizationCode1
Duality Diagram Similarity: a generic framework for initialization selection in task transfer learningCode1
Tighter risk certificates for neural networksCode1
Extended Stochastic Block Models with Application to Criminal NetworksCode1
An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter OptimizationCode1
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and DatasetsCode1
Robust pricing and hedging via neural SDEsCode1
Estimating Generalization under Distribution Shifts via Domain-Invariant RepresentationsCode1
In Search of Lost Domain GeneralizationCode1
Assumption-lean inference for generalised linear model parametersCode1
Selecting the Number of Clusters K with a Stability Trade-off: an Internal Validation CriterionCode1
TensorFlow with user friendly Graphical Framework for object detection APICode1
Fuzzy c-Means Clustering for Persistence DiagramsCode1
Learning Opinion Dynamics From Social TracesCode1
Uncertainty Based Camera Model SelectionCode1
A Concise yet Effective model for Non-Aligned Incomplete Multi-view and Missing Multi-label LearningCode1
DriveML: An R Package for Driverless Machine LearningCode1
BayesOpt Adversarial AttackCode1
Counterfactual Learning of Stochastic Policies with Continuous Actions: from Models to Offline EvaluationCode1
SINDy-PI: A Robust Algorithm for Parallel Implicit Sparse Identification of Nonlinear DynamicsCode1
DEPARA: Deep Attribution Graph for Deep Knowledge TransferabilityCode1
Deep Learning Algorithms for Rotating Machinery Intelligent Diagnosis: An Open Source Benchmark StudyCode1
Rethinking Parameter Counting in Deep Models: Effective Dimensionality RevisitedCode1
LIBTwinSVM: A Library for Twin Support Vector MachinesCode1
Evaluating Weakly Supervised Object Localization Methods RightCode1
Source Model Selection for Deep Learning in the Time Series DomainCode1
InfoGAN-CR: Disentangling Generative Adversarial Networks with Contrastive RegularizersCode1
One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image SegmentationCode1
Exploiting BERT for End-to-End Aspect-based Sentiment AnalysisCode1
InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANsCode1
Interpretable multiclass classification by MDL-based rule listsCode1
BERTScore: Evaluating Text Generation with BERTCode1
Forecasting with time series imagingCode1
Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible EvaluationCode1
Show:102550
← PrevPage 4 of 41Next →

No leaderboard results yet.