Dec 10, 2023
Speaker · 2 followers
Speaker · 1 follower
Speaker · 1 follower
Speaker · 3 followers
Speaker · 23 followers
Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning methods. The highly structured constraints in these problems can hinder either optimization or sampling directly in the solution space.On the other hand, GFlowNets have recently emerged as a powerful machinery to efficiently sample from composite unnormalized densities sequentially and have the potential to amortize such solution-searching processes in CO, as well as generate diverse solution candidates.In this paper, we design Markov decision processes (MDPs) for different combinatorial problems and propose to train conditional GFlowNets to sample from the solution space. Efficient training techniques are also developed to benefit long-range credit assignment.Through extensive experiments on a variety of different CO tasks with synthetic and realistic data, we demonstrate that GFlowNet policies can efficiently find high-quality solutions.Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning methods. The highly structured constraints in these problems can hinder either optimization or sampling directly in the solution space.On the other hand, GFlowNets have recently emerged as a powerful machinery to efficiently sample from composite unnormalized densities sequentially and have the potential to amortize such solution-searching…
Account · 617 followers
Professional recording and live streaming, delivered globally.
Presentations on similar topic, category or speaker
Haiteng Zhao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Xinyu Ma, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Yingbin Bai, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Kevin Clark, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Bochen Lyu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%