This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

Workshop: Learning Meets Combinatorial Algorithms

Marin Vlastelica, Jialin Song, Aaron Ferber, Brandon Amos, Georg Martius, Bistra Dilkina, Yisong Yue

2020-12-12T03:00:00-08:00 - 2020-12-12T16:00:00-08:00
Abstract: We propose to organize a workshop on machine learning and combinatorial algorithms. The combination of methods from machine learning and classical AI is an emerging trend. Many researchers have argued that “future AI” methods somehow need to incorporate discrete structures and symbolic/algorithmic reasoning. Additionally, learning-augmented optimization algorithms can impact the broad range of difficult but impactful optimization settings. Coupled learning and combinatorial algorithms have the ability to impact real-world settings such as hardware & software architectural design, self-driving cars, ridesharing, organ matching, supply chain management, theorem proving, and program synthesis among many others. We aim to present diverse perspectives on the integration of machine learning and combinatorial algorithms.

This workshop aims to bring together academic and industrial researchers in order to describe recent advances and build lasting communication channels for the discussion of future research directions pertaining the integration of machine learning and combinatorial algorithms. The workshop will connect researchers with various relevant backgrounds, such as those working on hybrid methods, have particular expertise in combinatorial algorithms, work on problems whose solution likely requires new approaches, as well as everyone interested in learning something about this emerging field of research. We aim to highlight open problems in bridging the gap between machine learning and combinatorial optimization in order to facilitate new research directions.
The workshop will foster the collaboration between the communities by curating a list of problems and challenges to promote the research in the field.

Our technical topics of interest include (but are not limited to):
- Hybrid architectures with combinatorial building blocks
- Attacking hard combinatorial problems with learning
- Neural architectures mimicking combinatorial algorithms

Further information about speakers, paper submissions and schedule are available at the workshop website: https://sites.google.com/view/lmca2020/home .

Chat

To ask questions please use rocketchat, available only upon registration and login.

Schedule

2020-12-12T03:00:00-08:00 - 2020-12-12T04:30:00-08:00
Poster Session A: 3:00 AM - 4:30 AM PST
Taras Khakhulin, Ravichandra Addanki, Jinhwi Lee, Jungtaek Kim, Piotr Januszewski, Konrad Czechowski, Francesco Landolfi, Lovro Vrček, Oren Neumann, Claudius Gros, Betty Fabre, Lukas Faber, Lucas Anquetil, Alberto Franzin, Tommaso Bendinelli, Sergey Bartunov
2020-12-12T06:50:00-08:00 - 2020-12-12T07:00:00-08:00
Opening
Marin Vlastelica Pogančić, Georg Martius
2020-12-12T07:00:00-08:00 - 2020-12-12T07:25:00-08:00
Invited Talk (Ellen Vitercik)
Ellen Vitercik
2020-12-12T07:25:00-08:00 - 2020-12-12T07:50:00-08:00
Invited Talk (Petar Veličković)
Petar Veličković
2020-12-12T07:50:00-08:00 - 2020-12-12T08:10:00-08:00
Q&A for Session
2020-12-12T08:10:00-08:00 - 2020-12-12T08:18:00-08:00
Contributed Talk: A Framework For Differentiable Discovery Of Graph Algorithms
Hanjun Dai
2020-12-12T08:18:00-08:00 - 2020-12-12T08:26:00-08:00
Contributed Talk: Learning To Select Nodes In Bounded Suboptimal Conflict-Based Search For Multi-Agent Path Finding
Taoan Huang
2020-12-12T08:26:00-08:00 - 2020-12-12T08:35:00-08:00
Contributed Talk: Neural Algorithms For Graph Navigation
Aaron Zweig
2020-12-12T08:35:00-08:00 - 2020-12-12T08:44:00-08:00
Contributed Talk: Fit The Right Np-Hard Problem: End-To-End Learning Of Integer Programming Constraints
Anselm Paulus
2020-12-12T08:44:00-08:00 - 2020-12-12T08:52:00-08:00
Contributed Talk: Language Generation Via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach
Nan Jiang
2020-12-12T08:52:00-08:00 - 2020-12-12T09:05:00-08:00
Q&A for Contributed Talks
2020-12-12T09:05:00-08:00 - 2020-12-12T09:10:00-08:00
Break
2020-12-12T09:10:00-08:00 - 2020-12-12T10:40:00-08:00
Poster Session B
Ravichandra Addanki, Andreea Deac, Yujia Xie, Francesco Landolfi, Antoine Prouvost, Claudius Gros, Renzo Massobrio, Abhishek Cauligi, Simon Alford, Hanjun Dai, Alberto Franzin, Nitish Kumar Panigrahy, Brandon J Kates, Iddo Drori, Taoan Huang, Zhou Zhou, Marin Vlastelica, Anselm Paulus, Aaron Zweig, Minsu Cho, Haiyan Yin, Michal Lisicki, Nan Jiang, Haoran Sun
2020-12-12T10:40:00-08:00 - 2020-12-12T11:10:00-08:00
Break
2020-12-12T11:10:00-08:00 - 2020-12-12T11:35:00-08:00
Invited Talk (Zico Kolter)
J. Zico Kolter
2020-12-12T11:35:00-08:00 - 2020-12-12T12:00:00-08:00
Invited Talk (Katherine Bouman)
Katherine Bouman
2020-12-12T12:00:00-08:00 - 2020-12-12T12:25:00-08:00
Invited Talk (Michal Rolinek)
Michal Rolinek
2020-12-12T12:25:00-08:00 - 2020-12-12T12:55:00-08:00
Q&A for Session 2
2020-12-12T12:55:00-08:00 - 2020-12-12T13:25:00-08:00
Break
2020-12-12T13:25:00-08:00 - 2020-12-12T13:50:00-08:00
Invited Talk (Armando Solar-Lezama)
Armando Solar-Lezama
2020-12-12T13:50:00-08:00 - 2020-12-12T14:15:00-08:00
Invited Talk (Kevin Ellis)
Kevin Ellis
2020-12-12T14:15:00-08:00 - 2020-12-12T14:40:00-08:00
Invited Talk (Yuandong Tian)
Yuandong Tian
2020-12-12T14:40:00-08:00 - 2020-12-12T15:10:00-08:00
Q&A for Session 3
2020-12-12T15:10:00-08:00 - 2020-12-12T16:00:00-08:00
Guided Discussion and Closing
Session B, Poster 21: Towards Transferring Algorithm Configurations Across Problems
Alberto Franzin
Session B, Poster 4: Differentiable Top-k With Optimal Transport
Yujia Xie
Session B, Poster 28: Fit The Right Np-Hard Problem: End-To-End Learning Of Integer Programming Constraints
Anselm Paulus
Session B, Poster 22: Matching Through Embedding In Dense Graphs
Nitish Kumar Panigrahy
Session B, Poster 12: Virtual Savant: Learning For Optimization
Renzo Massobrio
Session A, Poster 21: Towards Transferring Algorithm Configurations Across Problems
Alberto Franzin
Session B, Poster 24: Learning To Select Nodes In Bounded Suboptimal Conflict-Based Search For Multi-Agent Path Finding
Taoan Huang
Session B, Poster 2: Neural Large Neighborhood Search
Ravichandra Addanki
Session B, Poster 25: Learning For Integer-Constrained Optimization Through Neural Networks With Limited Training
Zhou Zhou
Session B, Poster 20: A Framework For Differentiable Discovery Of Graph Algorithms
Hanjun Dai
Session B, Poster 34: Language Generation Via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach
Nan Jiang
Session B, Poster 19: Dreaming With ARC
Simon Alford
Session A, Poster 31: Continuous Latent Search For Combinatorial Optimization
Sergey Bartunov
Session B, Poster 18: Improving Learning To Branch Via Reinforcement Learning
Haoran Sun
Session A, Poster 5: Fragment Relation Networks For Geometric Shape Assembly
Jinhwi Lee
Session A, Poster 11: Investment Vs. Reward In A Competitive Knapsack Problem
Claudius Gros
Session A, Poster 6: Structure And Randomness In Planning And Reinforcement Learning
Piotr Januszewski
Session B, Poster 11: Investment Vs. Reward In A Competitive Knapsack Problem
Claudius Gros
Session A, Poster 16: Learning Lower Bounds For Graph Exploration With Reinforcement Learning
Lukas Faber
Session B, Poster 8: K-Plex Cover Pooling For Graph Neural Networks
Francesco Landolfi
Session A, Poster 17: Wasserstein Learning Of Determinantal Point Processes
Lucas Anquetil
Session B, Poster 23: Galaxytsp: A New Billion-Node Benchmark For Tsp
Brandon J Kates
Session B, Poster 10: Ecole: A Gym-Like Library For Machine Learning In Combinatorial Optimization Solvers
Antoine Prouvost
Session B, Poster 33: Evaluating Curriculum Learning Strategies In Neural Combinatorial Optimization
Michal Lisicki
Session A, Poster 1: Learning Elimination Ordering For Tree Decomposition Problem
Taras Khakhulin
Session A, Poster 7: Trust, But Verify: Model-Based Exploration In Sparse Reward Environments
Konrad Czechowski
Session B, Poster 15: CoCo: Learning Strategies For Online Mixed-Integer Control
Abhishek Cauligi
Session B, Poster 26: Discrete Planning With Neuro-Algorithmic Policies
Marin Vlastelica
Session A, Poster 11: Investment Vs. Reward In A Competitive Knapsack Problem
Oren Neumann
Session B, Poster 3: Xlvin: Executed Latent Value Iteration Nets
Andreea Deac
Session A, Poster 27: A Seq2Seq Approach To Symbolic Regression
Tommaso Bendinelli
Session A, Poster 5: Fragment Relation Networks For Geometric Shape Assembly
Jungtaek Kim
Session B, Poster 32: Reinforcement Learning With Efficient Active Feature Acquisition
Haiyan Yin
Session B, Poster 29: Neural Algorithms For Graph Navigation
Aaron Zweig
Session A, Poster 2: Neural Large Neighborhood Search
Ravichandra Addanki
Session B, Poster 30: Differentiable Programming For Piecewise Polynomial Functions
Minsu Cho
Session A, Poster 9: A Step Towards Neural Genome Assembly
Lovro Vrček
Session A, Poster 8: K-Plex Cover Pooling For Graph Neural Networks
Francesco Landolfi
Session B, Poster 23: Galaxytsp: A New Billion-Node Benchmark For TSP
Iddo Drori
Session A, Poster 13: Neural-Driven Multi-Criteria Tree Search For Paraphrase Generation
Betty Fabre