α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Mingyi Hong
Mingyi Hong
23
papers
906
total citations
papers (23)
Understanding Gradient Clipping in Private SGD: A Geometric Perspective
NEURIPS 2020
arXiv
231
citations
A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum
NEURIPS 2021
arXiv
156
citations
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
ICML 2024
arXiv
107
citations
Advancing Model Pruning via Bi-level Optimization
NEURIPS 2022
arXiv
86
citations
Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
NEURIPS 2020
arXiv
83
citations
STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
NEURIPS 2021
arXiv
72
citations
Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees
NEURIPS 2022
arXiv
51
citations
When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning
NEURIPS 2023
arXiv
25
citations
Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence
NEURIPS 2022
arXiv
24
citations
Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
NEURIPS 2023
arXiv
14
citations
VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
NEURIPS 2023
arXiv
10
citations
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work
NEURIPS 2021
arXiv
10
citations
Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
ICLR 2024
arXiv
10
citations
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
ICML 2025
arXiv
9
citations
MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent
ICML 2024
arXiv
6
citations
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
ICML 2025
arXiv
5
citations
InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction
NEURIPS 2025
arXiv
5
citations
EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
ICML 2024
arXiv
2
citations
Distributed Optimization for Overparameterized Problems: Achieving Optimal Dimension Independent Communication Complexity
NEURIPS 2022
0
citations
Provably Efficient Neural GTD for Off-Policy Learning
NEURIPS 2020
0
citations
Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems
NEURIPS 2020
0
citations
A Stochastic Linearized Augmented Lagrangian Method for Decentralized Bilevel Optimization
NEURIPS 2022
0
citations
A Unified Detection Framework for Inference-Stage Backdoor Defenses
NEURIPS 2023
0
citations
