Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Chao Gao's personal page
About me
Page not in menu
This is a page not in th emain menu
Posts
Some thought on AlphaTensor
Published:
Recently, there is a heated attention on newly released paper AlphaTensor from DeepMind. The claim in the Abstract seems to imply that there is a great advancement for a 50 year old problem that Strassen’s algorithm was trying to address. This is really an intriguing claim, thus I spared myself some time trying to fully understand to what extent these claims are true, and how the algorithm they use looks like for such achievements.
Deep Learning Frameworks and Compilers
Published:
In previous blogs, we have covered the topic of scheduling tensor programs. This task might be viewed as one step in machine learning compilers, which I will provide an introduction in this blog.
Reinforcement Learning for Scheduling Tensor Programs
Published:
The idea of reinforcement learning has been applied for scheduling tensor programs, but so far, the RL algorithms being used are largely different from those being developed in the RL community. In this blog, I briefly summarize the existing methods, and dicuss potential and interesting working directions.
AI-Aided Problem Solving
Published:
AI techniques/algorithms keep advancing these days, along with that is an increasing interest on the question how these techniques and algorithms shall be harnessed for solving real-world problems. In this blog, I provide some of my thoughts on problem-solving and artificial intelligence.
Scheduling tensor programs
Published:
Tensor programs are ubiquitous, ranging from general matrix muliplication to deep neural networks. However, due to extensive float number computation, execution them can incur high latency. Indeed, it is well-known that the rejuvenation of neural networks is very much due to the use of GPUs for these computation — thus accelerating tensor programs is of great importance.
Multi-agent Reinforcement Learning
Published:
In this blog I provide an introduction to the game of Pommerman, a game designed for studying multi-agent learning.
The game of Hex
Published:
In this blog, I give an introduction to the game’s origin and key properities of the game.
projects
Scheduling tensor programs using heuristic search and reinforcement learning
Published:
2020 – Now 
Search and learning for playing and solving the game of Hex
Published:
2015 – 2019 
Reinforcement learning for the game of Pommerman
Published:
2018 – 2019 
Solving the multi-dimensional multiple-choice knapsack problems
Published:
2014 – 2015 
Solving the set covering problems
Published:
2013 – 2014 
publications
An efficient local search heuristic with row-weighting for the unicost set covering problem
Published in European Journal of Operational Research, 2015
Recommended citation: Gao, C., Yao, X., Weise, T. and Li, J., 2015. An efficient local search heuristic with row weighting for the unicost set covering problem. European Journal of Operational Research, 246(3), pp.750-761. https://www.sciencedirect.com/science/article/abs/pii/S0377221715004282
A Pseudo-gap Enumeration Approach for the Multidimensional Multiple-choice Knapsack Problem
Published in European Journal of Operational Research, 2017
Recommended citation: Gao, C., Lu, G., Yao, X. and Li, J., 2017. An iterative pseudo-gap enumeration approach for the Multidimensional Multiple-choice Knapsack Problem. European Journal of Operational Research, 260(1), pp.1-11. https://www.sciencedirect.com/science/article/abs/pii/S0377221716309675
Focused depth-first proof number search using convolutional neural networks for the game of Hex
Published in IJCAI 2017, 2017
Recommended citation: Gao, C., Müller, M. and Hayward, R., 2017, January. Focused Depth-first Proof Number Search using Convolutional Neural Networks for the Game of Hex. In IJCAI (pp. 3668-3674). https://www.ijcai.org/proceedings/2017/513
Move Prediction Using Deep Convolutional Neural Networks in Hex
Published in IEEE Transaction on Games, 2017
Recommended citation: Gao, C., Hayward, R. and Müller, M., 2017. Move prediction using deep convolutional neural networks in Hex. IEEE Transactions on Games, 10(4), pp.336-343. https://ieeexplore.ieee.org/abstract/document/8226781
Three-Head Neural Network Architecture for Monte Carlo Tree Search
Published in IJCAI 2018, 2018
Recommended citation: Gao, C., Müller, M. and Hayward, R., 2018, January. Three-Head Neural Network Architecture for Monte Carlo Tree Search. In IJCAI (pp. 3762-3768). https://www.ijcai.org/proceedings/2018/0523.pdf
Basnet: Boundary-aware salient object detection
Published in CVPR 2019, 2019
Recommended citation: Qin, X., Zhang, Z., Huang, C., Gao, C., Dehghan, M. and Jagersand, M., 2019. Basnet: Boundary-aware salient object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7479-7489). https://openaccess.thecvf.com/content_CVPR_2019/papers/Qin_BASNet_Boundary-Aware_Salient_Object_Detection_CVPR_2019_paper.pdf
On Hard Exploration for Reinforcement Learning: A Case Study in Pommerman
Published in AAAI Conference on AI and Interactive Digital Entertainment, 2019
Recommended citation: Gao, C., Kartal, B., Hernandez-Leal, P. and Taylor, M.E., 2019, October. On hard exploration for reinforcement learning: A case study in pommerman. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (Vol. 15, No. 1, pp. 24-30). https://ojs.aaai.org/index.php/AIIDE/article/view/5220/5076
Pommerman and neurips 2018
Published in Springer, 2020
This describes the pommmerman competition at neurips 2018.
Recommended citation: Resnick, C., Gao, C., Marton, G., Osogami, T., Pang, L. and Takahashi, T., 2020. Pommerman & neurips 2018. In The NeurIPS-18 Competition (pp. 11-36). Springer, Cham. https://link.springer.com/chapter/10.1007/978-3-030-29135-8_2
Bansor: Improving Tensor Program Auto-Scheduling with Bandit Based Reinforcement Learning
Published in ICTAI, 2021
This describes our work of improving TVM auto-scheduler using Bandit-based RL.
Recommended citation: Gao et al., Bansor: Improving Tensor Program Auto-Scheduling with Bandit Based Reinforcement Learning #
Sample Average Approximation for Stochastic Optimization with Dependent Data: Performance Guarantees and Tractability
Published in AAAI, 2022
This paper studies sample average approximation for stochastic optimization.
Recommended citation: Wang et al., Sample Average Approximation for Stochastic Optimization with Dependent Data: Performance Guarantees and Tractability https://arxiv.org/abs/2112.05368
A Memory-Bounded Best-First Beam Search and Its Application to Scheduling Halide Programs
Published in The Fifteenth International Symposium on Combinatorial Search 2022, 2022
This paper revisits beam search from the perspective of memory-bounded search and proposes a strategy for improving it.
Recommended citation: Chao Gao et al., A Memory-Bounded Best-First Beam Search and Its Application to Scheduling Halide Programs http://search-conference.org/`
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 2
Workshop, University of Alberta, Department of Computing Science, 2015
This is a description of a teaching experience. To be filled.