Timezone: »

 
Workshop
Learning Meets Combinatorial Algorithms
Marin Vlastelica · Jialin Song · Aaron Ferber · Brandon Amos · Georg Martius · Bistra Dilkina · Yisong Yue

Sat Dec 12 03:00 AM -- 04:00 PM (PST) @ None
Event URL: https://sites.google.com/view/lmca2020/home »

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 .

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

Author Information

Marin Vlastelica (Max Planck Institute for Intelligent Systems)

Marin Vlastelica is a PhD student in the Autonomous Learning group at the Max Planck Institute for Intelligent Systems in Tübingen, Germany. His research interests involve the interplay between combinatorial algorithms and ML, reinforcement learning, and causality with the goal of improving sample efficiency in sequential decision making processes.

Jialin Song (Caltech)
Aaron Ferber (University of Southern California)
Brandon Amos (Facebook AI)
Georg Martius (MPI for Intelligent Systems)
Bistra Dilkina (University of Southern California)
Yisong Yue (Caltech)

More from the Same Authors