Songtao Lu

Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity JMLR 2025 DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity ICLR 2025 Q-function Decomposition with Intervention Semantics for Factored Action Spaces AISTATS 2025 Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis ICLR 2025 TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization ICML 2025 Distributed Bilevel Optimization with Communication Compression ICML 2024 FADAS: Towards Federated Adaptive Asynchronous Optimization ICML 2024 Federated Neuro-Symbolic Learning ICML 2024 How Do Nonlinear Transformers Learn and Generalize in In-Context Learning? ICML 2024 M2ASR: Multilingual Multi-task Automatic Speech Recognition via Multi-objective Optimization Interspeech 2024 PILOT: An O(1/K)-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation ICLR 2024 SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning ICML 2024 SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization NeurIPS 2024 An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition NeurIPS 2023 Bilevel Optimization with Coupled Decision-Dependent Distributions ICML 2023 Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data ICML 2023 Distributed Offline Policy Optimization Over Batch Data AISTATS 2023 Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks ICLR 2023 Min-Max Multi-objective Bilevel Optimization with Applications in Robust Machine Learning ICLR 2023 On the Convergence and Sample Complexity Analysis of Deep Q-Networks with ε-Greedy Exploration NeurIPS 2023 Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning ICML 2023 SLM: A Smoothed First-Order Lagrangian Method for Structured Constrained Nonconvex Optimization NeurIPS 2023 Adversarial Examples Can Be Effective Data Augmentation for Unsupervised Machine Learning AAAI 2022 A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization ICML 2022 A Stochastic Linearized Augmented Lagrangian Method for Decentralized Bilevel Optimization NeurIPS 2022 Distributed adversarial training to robustify deep neural networks at scale UAI 2022 Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward ICLR 2022 Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations IJCAI 2022 Understanding Benign Overfitting in Gradient-Based Meta Learning NeurIPS 2022 Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective ICLR 2022 Zeroth-Order Optimization for Composite Problems with Functional Constraints AAAI 2022 Decentralized Policy Gradient Descent Ascent for Safe Multi-Agent Reinforcement Learning AAAI 2021 Rate-improved inexact augmented Lagrangian method for constrained nonconvex optimization AISTATS 2021 Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning NeurIPS 2021 Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis NeurIPS 2020 Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems NeurIPS 2020 Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking ICML 2020 Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks ICML 2020 ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training NeurIPS 2020 PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex Optimization ICML 2019 A Stochastic Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization AISTATS 2017