← Authors

Songtao Lu

41 papers · 2017–2025 · 9 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (9) πŸƒ Academic Marathon (8) 🐝 Cross-Pollinator (12) πŸ—ΊοΈ Taxonomy Completionist (37) 🐺 Lone Wolf (4) 🀝 Dynamic Duo (11) πŸ† Keyword Champion (4) πŸ† Grand Slam πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (17) πŸ’Ž Century Club (41) ⚑ Prolific Year (9) πŸ—ƒοΈ Keyword Collector (107) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (7) ❓ The Questioner

Conferences

ICML (13) NIPS (10) ICLR (7) AISTATS (4) AAAI (3) IJCAI (1) INTERSPEECH (1) JMLR (1) UAI (1)

Top co-authors

Pin-Yu Chen (11) Sijia Liu (8) Xiaodong Cui (7) Mingyi Hong (7) Jia Liu (6) Tianyi Chen (6) Meng Wang (5) Miao Liu (4) Zhuqing Liu (4) Yangyang Xu (3)

Keywords

bilevel optimization (9) decentralized optimization (7) nonconvex optimization (7) stochastic optimization (6) gradient tracking (4) multi-agent reinforcement learning (3) adversarial attack (3) sample complexity (3) communication complexity (3) constrained optimization (3) distributed learning (3) augmented lagrangian method (3) zeroth-order optimization (2) few-shot learning (2) gradient compression (2) first-order method (2) federated learning (2) primal-dual algorithm (2) reinforcement learning (2) black-box optimization (2)

Papers

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