Sizhe Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sizhe Li has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Nicolas Christianson
Stanford University, Stanford, California, USA
3 shared publications - Tongxin Li
The Chinese University of Hong Kong, Shenzhen, Shenzhen, Guangdong, China
3 shared publications
Latest Publications
- Open Access
- 20 July 2026
- Published by Association for Computing Machinery (ACM) in ACM SIGMETRICS Performance Evaluation Review
- Vol. 54 (1) , 82-84
Prediction-Specific Design of Learning-Augmented Algorithms
Algorithms with predictions have emerged as a powerful framework to combine the robustness of traditional online algorithms with the data-driven performance benefits of machine-learned (ML) predictions. However, most existing approaches in this paradigm are overly conservative, as they do not leverage problem structure to optimize performance in a prediction-specific manner. In this paper, we show that prediction-specific performance criteria can enable significant improvements over the coarser notions of consistency and robustness considered in prior work. We propose a notion of strongly-optimal algorithms with predictions, which obtain Pareto optimality not just in the worst-case tradeoff between robustness and consistency, but also in the prediction-specific tradeoff between these metrics. We develop a general bi-level optimization framework that enables systematically designing strongly-optimal algorithms in a wide variety of problem settings, and we propose explicit strongly-optimal algorithms for several classic online problems: deterministic and randomized ski rental, and one-max search. Our analysis reveals new structural insights into how predictions can be optimally integrated into online algorithms by leveraging a prediction-specific design. Empirical evaluations on dynamic power management and VIX trading validate the practical benefits of our framework.
- 20 July 2026
- Published by Association for Computing Machinery (ACM) in ACM SIGMETRICS Performance Evaluation Review
- Vol. 54 (1) , 82-84
Open AccessPrediction-Specific Design of Learning-Augmented Algorithms
Algorithms with predictions have emerged as a powerful framework to combine the robustness of traditional online algorithms with the data-driven performance benefits of machine-learned (ML) predictions. However, most existing approaches in this paradigm are overly conservative, as they do not leverage problem structure to optimize performance in a prediction-specific manner. In this paper, we show that prediction-specific performance criteria can enable significant improvements over the coarser notions of consistency and robustness considered in prior work. We propose a notion of strongly-optimal algorithms with predictions, which obtain Pareto optimality not just in the worst-case tradeoff between robustness and consistency, but also in the prediction-specific tradeoff between these metrics. We develop a general bi-level optimization framework that enables systematically designing strongly-optimal algorithms in a wide variety of problem settings, and we propose explicit strongly-optimal algorithms for several classic online problems: deterministic and randomized ski rental, and one-max search. Our analysis reveals new structural insights into how predictions can be optimally integrated into online algorithms by leveraging a prediction-specific design. Empirical evaluations on dynamic power management and VIX trading validate the practical benefits of our framework.
- Open Access
- 8 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 82-84
Prediction-Specific Design of Learning-Augmented Algorithms
- 8 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 82-84
Open AccessPrediction-Specific Design of Learning-Augmented Algorithms
- Open Access
- 26 March 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Measurement and Analysis of Computing Systems
- Vol. 10 (1) , 1-57
Prediction-Specific Design of Learning-Augmented Algorithms
Algorithms with predictions have emerged as a powerful framework to combine the robustness of traditional online algorithms with the data-driven performance benefits of machine-learned (ML) predictions. However, most existing approaches in this paradigm are overly conservative, as they do not leverage problem structure to optimize performance in a prediction-specific manner. In this paper, we show that such prediction-specific performance criteria can enable significant performance improvements over the coarser notions of consistency and robustness considered in prior work. Specifically, we propose a notion of strongly-optimal algorithms with predictions, which obtain Pareto optimality not just in the worst-case tradeoff between robustness and consistency, but also in the prediction-specific tradeoff between these metrics. We develop a general bi-level optimization framework that enables systematically designing strongly-optimal algorithms in a wide variety of problem settings, and we propose explicit strongly-optimal algorithms for several classic online problems: deterministic and randomized ski rental, and one-max search. Our analysis reveals new structural insights into how predictions can be optimally integrated into online algorithms by leveraging a prediction-specific design. To validate the benefits of our proposed framework, we empirically evaluate our algorithms in case studies on problems including dynamic power management and volatility-based index trading. Our results demonstrate that prediction-specific, strongly-optimal algorithms can significantly improve performance across a variety of online decision-making settings.
- 26 March 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Measurement and Analysis of Computing Systems
- Vol. 10 (1) , 1-57
Open AccessPrediction-Specific Design of Learning-Augmented Algorithms
Algorithms with predictions have emerged as a powerful framework to combine the robustness of traditional online algorithms with the data-driven performance benefits of machine-learned (ML) predictions. However, most existing approaches in this paradigm are overly conservative, as they do not leverage problem structure to optimize performance in a prediction-specific manner. In this paper, we show that such prediction-specific performance criteria can enable significant performance improvements over the coarser notions of consistency and robustness considered in prior work. Specifically, we propose a notion of strongly-optimal algorithms with predictions, which obtain Pareto optimality not just in the worst-case tradeoff between robustness and consistency, but also in the prediction-specific tradeoff between these metrics. We develop a general bi-level optimization framework that enables systematically designing strongly-optimal algorithms in a wide variety of problem settings, and we propose explicit strongly-optimal algorithms for several classic online problems: deterministic and randomized ski rental, and one-max search. Our analysis reveals new structural insights into how predictions can be optimally integrated into online algorithms by leveraging a prediction-specific design. To validate the benefits of our proposed framework, we empirically evaluate our algorithms in case studies on problems including dynamic power management and volatility-based index trading. Our results demonstrate that prediction-specific, strongly-optimal algorithms can significantly improve performance across a variety of online decision-making settings.