research SCALE Optimizer A memory-efficient LLM pretraining optimizer following a minimalist design. EMA-Nesterov Nesterov's acceleration as an optimizer plugin. EMA-Nesterov applies low-pass filtered lookahead before each optimization step to accelerate convergence. Leak@k A meta-metric evaluation framework to evaluate robustness of LLM unlearning Large-Scale Optimization Design and analysis of modern optimization algorithms for large-scale problems Machine Learning Optimization approaches for machine learning problems Distributed Multi-Agent Systems Distributed in-network data processing and parallel optimization algorithms Next Generation Communication Networks Cross-layer optimization for 5G and beyond wireless networks Bilevel and Min-Max Optimization Theory and algorithms for bilevel and minimax optimization problems Federated Learning Distributed and federated learning algorithms for heterogeneous data
