Optimization for Machine Learning and AI
OptMAI Lab at Texas A&M University directed by Professor Tianbao Yang
Pinned Repositories
ICCV2021_DeepAUC
Official implementation of the paper "Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification, ICCV2021"
ICML2021_FedDeepAUC_CODASCA
Official implementation: "Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity", ICML2021.
ICML2023_BSVRB
Official implementation of the paper "Blockwise Stochastic Variance-Reduced Methods with Parallel Speedup for Multi-Block Bilevel Optimization", ICML 2023
ICML2023_FeDXL
Official implementation of ICML 2023 paper "FeDXL: Provable Federated Learning for Deep X-Risk Optimization".
ICML2023_LDR
The official implementation from 'Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity' ICML2023
LibAUC
LibAUC: A Deep Learning Library for X-Risk Optimization
NDCG-Optimization
Official implementation of the paper "Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence" ICML2022.
NeurIPS2021_SOAP
Official implementation of the paper "Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence" published on Neurips2021.
SogCLR
Official implementation of the paper "Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance", ICML2022.
Optimization for Machine Learning and AI's Repositories
Optimization-AI/LibAUC
LibAUC: A Deep Learning Library for X-Risk Optimization
Optimization-AI/ICCV2021_DeepAUC
Official implementation of the paper "Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification, ICCV2021"
Optimization-AI/NeurIPS2021_SOAP
Official implementation of the paper "Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence" published on Neurips2021.
Optimization-AI/SogCLR
Official implementation of the paper "Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance", ICML2022.
Optimization-AI/ICML2021_FedDeepAUC_CODASCA
Official implementation: "Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity", ICML2021.
Optimization-AI/ICML2023_BSVRB
Official implementation of the paper "Blockwise Stochastic Variance-Reduced Methods with Parallel Speedup for Multi-Block Bilevel Optimization", ICML 2023
Optimization-AI/ICML2023_FeDXL
Official implementation of ICML 2023 paper "FeDXL: Provable Federated Learning for Deep X-Risk Optimization".
Optimization-AI/NDCG-Optimization
Official implementation of the paper "Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence" ICML2022.
Optimization-AI/ICML2023_LDR
The official implementation from 'Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity' ICML2023