Dongsheng Ding

34 papers A* 6A 2C 5Journal 15Unranked 6

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Alignment of large language models with constrained learning. CoRR Botong Zhang, Shuo Li, Ignacio Hounie, Osbert Bastani, Dongsheng Ding, Alejandro Ribeiro
2025	J	`jnl`	Composition and Alignment of Diffusion Models using Constrained Learning. CoRR Shervin Khalafi, Ignacio Hounie, Dongsheng Ding, Alejandro Ribeiro
2025	J	`jnl`	Convergence and Sample Complexity of Natural Policy Gradient Primal-Dual Methods for Constrained MDPs. J. Mach. Learn. Res. Dongsheng Ding, Kaiqing Zhang, Jiali Duan, Tamer Basar, Mihailo R. Jovanovic
2025	A*	`conf`	Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs. AAAI Sergio Rozada, Dongsheng Ding, Antonio G. Marques, Alejandro Ribeiro
2024	A*	`conf`	Constrained Diffusion Models via Dual Training. NeurIPS Shervin Khalafi, Dongsheng Ding, Alejandro Ribeiro
2024	J	`jnl`	Constrained Diffusion Models via Dual Training. CoRR Shervin Khalafi, Dongsheng Ding, Alejandro Ribeiro
2024	J	`jnl`	Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs. CoRR Sergio Rozada, Dongsheng Ding, Antonio G. Marques, Alejandro Ribeiro
2024	A*	`conf`	One-Shot Safety Alignment for Large Language Models via Optimal Dualization. NeurIPS Xinmeng Huang, Shuo Li, Edgar Dobriban, Osbert Bastani, Hamed Hassani, Dongsheng Ding
2024	J	`jnl`	One-Shot Safety Alignment for Large Language Models via Optimal Dualization. CoRR Xinmeng Huang, Shuo Li, Edgar Dobriban, Osbert Bastani, Hamed Hassani, Dongsheng Ding
2024	A	`conf`	Resilient Constrained Reinforcement Learning. AISTATS Dongsheng Ding, Zhengyan Huan, Alejandro Ribeiro
2023	A*	`conf`	Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs. NeurIPS Dongsheng Ding, Chen-Yu Wei, Kaiqing Zhang, Alejandro Ribeiro
2023	J	`jnl`	Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs. CoRR Dongsheng Ding, Chen-Yu Wei, Kaiqing Zhang, Alejandro Ribeiro
2023	—	`conf`	Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning. L4DC Dongsheng Ding, Xiaohan Wei, Zhuoran Yang, Zhaoran Wang, Mihailo R. Jovanovic
2023	J	`jnl`	Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning. CoRR Dongsheng Ding, Xiaohan Wei, Zhuoran Yang, Zhaoran Wang, Mihailo R. Jovanovic
2023	J	`jnl`	Resilient Constrained Reinforcement Learning. CoRR Dongsheng Ding, Zhengyan Huan, Alejandro Ribeiro
2022	C	`conf`	Convergence and optimality of policy gradient primal-dual method for constrained Markov decision processes. ACC Dongsheng Ding, Kaiqing Zhang, Tamer Basar, Mihailo R. Jovanovic
2022	J	`jnl`	Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs. CoRR Dongsheng Ding, Kaiqing Zhang, Jiali Duan, Tamer Basar, Mihailo R. Jovanovic
2022	A*	`conf`	Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence. ICML Dongsheng Ding, Chen-Yu Wei, Kaiqing Zhang, Mihailo R. Jovanovic
2022	J	`jnl`	Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence. CoRR Dongsheng Ding, Chen-Yu Wei, Kaiqing Zhang, Mihailo R. Jovanovic
2022	—	`conf`	Policy gradient primal-dual mirror descent for constrained MDPs with large state spaces. CDC Dongsheng Ding, Mihailo R. Jovanovic
2021	C	`conf`	Byzantine-resilient distributed learning under constraints. ACC Dongsheng Ding, Xiaohan Wei, Hao Yu, Mihailo R. Jovanovic
2021	C	`conf`	Discounted online Newton method for time-varying time series prediction. ACC Dongsheng Ding, Jianjun Yuan, Mihailo R. Jovanovic
2021	A	`conf`	Provably Efficient Safe Exploration via Primal-Dual Policy Optimization. AISTATS Dongsheng Ding, Xiaohan Wei, Zhuoran Yang, Zhaoran Wang, Mihailo R. Jovanovic
2020	—	`conf`	Global exponential stability of primal-dual gradient flow dynamics based on the proximal augmented Lagrangian: A Lyapunov-based approach. CDC Dongsheng Ding, Mihailo R. Jovanovic
2020	A*	`conf`	Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes. NeurIPS Dongsheng Ding, Kaiqing Zhang, Tamer Basar, Mihailo R. Jovanovic
2020	J	`jnl`	Provably Efficient Safe Exploration via Primal-Dual Policy Optimization. CoRR Dongsheng Ding, Xiaohan Wei, Zhuoran Yang, Zhaoran Wang, Mihailo R. Jovanovic
2019	—	`conf`	Distributed robust statistical learning: Byzantine mirror descent. CDC Dongsheng Ding, Xiaohan Wei, Mihailo R. Jovanovic
2019	J	`jnl`	Fast Multi-Agent Temporal-Difference Learning via Homotopy Stochastic Primal-Dual Optimization. CoRR Dongsheng Ding, Xiaohan Wei, Zhuoran Yang, Zhaoran Wang, Mihailo R. Jovanovic
2019	C	`conf`	Global exponential stability of primal-dual gradient flow dynamics based on the proximal augmented Lagrangian. ACC Dongsheng Ding, Mihailo R. Jovanovic
2019	J	`jnl`	Global exponential stability of primal-dual gradient flow dynamics based on the proximal augmented Lagrangian: A Lyapunov-based approach. CoRR Dongsheng Ding, Mihailo R. Jovanovic
2018	C	`conf`	A primal-dual laplacian gradient flow dynamics for distributed resource allocation problems. ACC Dongsheng Ding, Mihailo R. Jovanovic
2018	—	`conf`	An Exponentially Convergent Primal-Dual Algorithm for Nonsmooth Composite Minimization. CDC Dongsheng Ding, Bin Hu, Neil K. Dhingra, Mihailo R. Jovanovic
2014	—	`conf`	Adaptive Mittag-Leffler stabilization of commensurate fractional-order nonlinear systems. CDC Dongsheng Ding, Donglian Qi, Yao Meng, Li Xu
2012	J	`jnl`	Convergence analysis and performance of an extended central force optimization algorithm. Appl. Math. Comput. Dongsheng Ding, Donglian Qi, Xiaoping Luo, Jinfei Chen, Xuejie Wang, Pengying Du