Location: Room A5 @ ICML 2018, Stockholmsmässan, Stockholm SWEDEN
Session 1
8:00 - 8:30 Registration
8:30 - 8:40 Opening Remarks
8:40 - 9:20 Opening Talk: Eric Xing - A Unified View of Deep Generative Models
9:20 - 10:00 Invited Talk: Yoshua Bengio - Capturing Dependencies Implicitly
10:00 - 10:30 Coffee Break
Session 2
10:30 - 11:10 Invited Talk: Arthur Gretton - Better gradient regularisation for MMD GANs
11:10 - 11:20 Contributed Oral: Associative Compression Networks for Representation Learning
11:20 - 11:30 Contributed Oral: TherML: Thermodynamics of Machine Learning
11:30 - 11:40 Contributed Oral: Connections with Robust PCA and the Role of Emergent Sparsity in Variational Autoencoder Models
11:40 - 12:30 Poster Session
12:30 - 14:00 Lunch Break
Session 3
14:00 - 14:40 Invited Talk: Pushmeet Kohli - Interpretable and Semantics-aware Generative Models
14:40 - 15:20 Invited Talk: Percy Liang - Editing is Easier than Generation
15:20 - 15:30 Contributed Oral: Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
15:30 - 16:00 Coffee Break
Session 4
16:00 - 16:10 Contributed Oral: InfoVAE: Balancing Learning and Inference in Variational Autoencoders
16:10 - 16:20 Contributed Oral: Neural Processes
16:20 - 16:30 Contributed Oral: Assessing Generative Models via Precision and Recall
16:30 - 17:10 Panel: Yoshua Bengio, Kamalika Chaudhuri, Arthur Gretton, Percy Liang
17:10 - 18:00 Poster Session
Session 5
8:00 - 8:30 Registration
8:30 - 9:10 Invited Talk: Honglak Lee - Learning hierarchical generative models with structured representations
9:10 - 9:50 Invited Talk: Juergen Schmidhuber - Unsupervised Minimax
9:50 - 10:00 Contributed Oral: Probabilistic Model-Agnostic Meta-Learning
10:00 - 10:30 Coffee break
Session 6
10:30 - 11:10 Invited Talk: Kamalika Chaudhuri - Learning with Adversarial Divergences for Generative Modeling
11:10 - 11:20 Contributed Oral: Are Generative Classifiers More Robust to Adversarial Attacks?
11:20 - 11:30 Contributed Oral: Deep Homogeneous Mixture Models : Representation, Separation, and Approximation
11:30 - 11:40 Contributed Oral: Solving Inverse Problems in Compressive Imaging using Deep Autoregressive Model
11:40 - 12:30 Poster Session
1. Yifeng Li and Xiaodan Zhu, Exploring Helmholtz Machine and Deep Belief Net in the Exponential Family Perspective
2. Biswa Sengupta and Karl Friston, How Robust are Deep Neural Networks?
3. Alex Graves, Jacob Menick and Aaron van den Oord, Associative Compression Networks for Representation Learning
4. Amartya Sanyal, Varun Kanade and Philip Torr, Intriguing Properties of Learned Representations
5. Giovanni Mariani, Florian Scheldegger, Roxana Istrate, Costas Bekas and Cristiano Malossi, BAGAN: Data Augmentation with Balancing GAN
6. Guokun Lai, Bohan Li, Guoqing Zheng and Yiming Yang, Stochastic WaveNet: A Generative Latent Variable Model for Sequential Data
7. Emilien Dupont, Tuanfeng Zhang, Peter Tilke, Lin Liang and William Bailey, Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks
8. Jiaming Song, Pratyusha Kalluri, Aditya Grover, Shengjia Zhao and Stefano Ermon, Learning Controllable Fair Representations via Latent Variable Generative Models
9. Maciej Zieba, Piotr Semberecki, Tarek El-Gaaly and Tomasz Trzcinski, BinGAN: Learning Compact Binary Descriptors with a Regularized GAN
10. Shengjia Zhao, Hongyu Ren, Arianna Yuan, Jiaming Song, Noah Goodman and Stefano Ermon, Bias and Generalization in Deep Generative Models: An Empirical Study
11. Bidisha Samanta, Abir De, Niloy Ganguly and Manuel Gomez-Rodriguez, Designing Random Graph Models Using Variational Autoencoders With Applications to Chemical Design
12. Michael Tschannen, Eirikur Agustsson and Mario Lucic, Deep Generative Models for Distribution-Preserving Lossy Compression
13. Arash Mehrjou and Bernhard Schölkopf, Nonstationary GANs: Analysis as Nonautonomous Dynamical Systems
15. Akifumi Okuno and Hidetoshi Shimodaira, On representation power of neural network-based graph embedding and beyond
16. Shengjia Zhao, Jiaming Song and Stefano Ermon, Lagrangian VAE: Dual Optimization for Latent Variable Generative Models
17. Nhat Ho, Tan Nguyen, Ankit Patel, Anima Anandkumar, Michael Jordan and Richard Baraniuk, The Latent-Dependent Deep Rendering Model
18. Kun Xu, Haoyu Liang, Jun Zhu and Bo Zhang, Deep Structured Generative Models
19. Nicola De Cao and Thomas Kipf, MolGAN: An implicit generative model for small molecular graphs
20. Bin Dai, Yu Wang, John Aston, Gang Hua and David Wipf, Connections with Robust PCA and the Role of Emergent Sparsity in Variational Autoencoder Models
21. Alexander Alemi and Ian Fischer, TherML: Thermodynamics of Machine Learning
22. Joseph Marino, Milan Cvitkovic and Yisong Yue, A General Framework for Amortizing Variational Filtering
23. Shane Barratt and Rishi Sharma, A Note on the Inception Score
1. Ramiro Camino, Christian Hammerschmidt and Radu State, Generating Multi-Categorical Samples with Generative Adversarial Networks
2. Shengjia Zhao, Jiaming Song and Stefano Ermon, InfoVAE: Balancing Learning and Inference in Variational Autoencoders
3. Stanislau Semeniuta, Aliaksei Severyn and Sylvain Gelly, On Accurate Evaluation of GANs for Language Generation
4. Tatjana Chavdarova, Sebastian Stich, Martin Jaggi and Francois Fleuret, Stochastic Variance Reduced Gradient Optimization of Generative Adversarial Networks
5. Philip Botros and Jakub Tomczak, Hierarchical VampPrior Variational Fair Auto-Encoder
6. Adji Bousso Dieng, Yoon Kim, Alexander Rush and David Blei, Avoiding Latent Variable Collapse with Generative Skip Models
7. Dhruv Madeka, Lucas Swiniarski, Dean Foster, Leonid Razoumov, Ruofeng Wen and Kari Torkkola, Sample Path Generation for Probabilistic Demand Forecasting
8. Kimin Lee, Kibok Lee, Honglak Lee and Jinwoo Shin, A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
9. Alejandro Mottini, Alix Lhéritier and Rodrigo Acuna-Agost, Airline Passenger Name Record Generation using Generative Adversarial Networks
10. Hao He, Hao Wang, Guang-He Lee and Yonglong Tian, Bayesian Modelling and Monte Carlo Inference for GAN
11. Yu Bai, Tengyu Ma and Andrej Risteski, Approximability of Discriminators Implies Diversity in GANs
12. Robin Tibor Schirrmeister, Patryk Chrabaszcz, Frank Hutter and Tonio Ball, Generative Reversible Networks
13. Thanh-Tung Hoang, Truyen Tran and Svetha Venkatesh, On catastrophic forgetting and mode collapse in Generative Adversarial Networks
14. Louis Tiao, Edwin Bonilla and Fabio Ramos, Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
15. Yucen Luo, Tian Tian, Jiaxin Shi, Jun Zhu and Bo Zhang, Semi-crowdsourced Clustering with Deep Generative Models
16. Michel Besserve, Remy Sun and Bernhard Schoelkopf, Intrinsic disentanglement: an invariance view for deep generative models
17. Negar Rostamzadeh, Seyedarian Hosseini, Thomas Boquet, Wojciech Stokowiec, Ying Zhang and Christopher Pal, The Generative Fashion Dataset and Challenge
18. Mahdi Azarafrooz, Xuan Zhao and Sepehr Masouleh, On the Information Theoretic Distance Measures and Bidirectional Helmholtz Machines
19. Chao Du, Kun Xu, Chongxuan Li, Jun Zhu and Bo Zhang, Learning Implicit Generative Models by Teaching Explicit Ones
20. Mehdi S. M. Sajjadi, Olivier Bachem, Mario Lucic, Olivier Bousquet and Sylvain Gelly, Assessing Generative Models via Precision and Recall
21. Marta Garnelo, Jonathan Schwarz, Dan Rosenbaum, Fabio Viola, Danilo J. Rezende, S. M. Ali Eslami and Yee Whye Teh, Neural Processes
22. Laëtitia Shao, Jiaming Song, Aditya Grover and Stefano Ermon, Markov Chain Monte Carlo for Learning Belief Networks
1. Priyank Jaini, Pascal Poupart and Yaoliang Yu, Deep Homogeneous Mixture Models : Representation, Separation, and Approximation
2. Andrew Jesson, Cecile Low-Kam, Florian Soudan and Nicolas Chapados, Adversarially Learned Mixture Model
3. Yingzhen Li, John Bradshaw and Yash Sharma, Are Generative Classifiers More Robust to Adversarial Attacks?
4. Sachin Kumar and Yulia Tsvetkov, Machine Translation with Continuous Outputs
5. Mohamed Ishmael Diwan Belghazi, Sai Rajeswar Mudumba, Olivier Mastropietro, Jovana Mitrovic, Negar Rostamzadeh and Aaron Courville, Hierarchical Adversarially Learned Inference
6. Hareesh Bahuleyan, Lili Mou, Olga Vechtomova and Pascal Poupart, Variational Attention for Sequence-to-Sequence Models
7. Guoqing Zheng, Yiming Yang and Jamie Carbonell, Convolutional Normalizing Flows
8. Guoqing Zheng, Yiming Yang and Jaime Carbonell, Asymmetric Variational Autoencoders
9. Septimia Sarbu, Riccardo Volpi, Alexandra Peste and Luigi Malagò, Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds
10. Xianglei Xing, Ruiqi Gao, Tian Han, Songchun Zhu and Yingnian Wu, Deformable Generator Network: Unsupervised Disentanglement of Appearance and Geometry
11. Rui Shu, Hung Bui, Shengjia Zhao, Mykel Kochenderfer and Stefano Ermon, Amortized Inference Regularization
12. Danijar Hafner, Dustin Tran, Alex Irpan, Timothy Lillicrap and James Davidson, Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors
13. Zichao Wang, Andrew Lan, Weili Nie, Andrew Waters, Phillip Grimaldi and Richard Baraniuk, QG-Net: A Data-Driven Question Generation Model for Educational Content
14. Aditya Grover and Stefano Ermon, Variational Compressive Sensing using Uncertainty Autoencoders
15. Zain Shah, Generative Buyer-Seller Adversarial Networks
16. Tian Qi Chen, Yulia Rubanova, Jesse Bettencourt and David Duvenaud, Black-box ODE Solvers as a Modeling Primitive
17. Rajesh Chidambaram, Michael Kampffmeyer, Willie Neiswanger, Xiaodan Liang, Thomas Lachmann and Eric Xing, 2d-Geometric Generalization Based Zero-Shot Intelligence Metric for Internal Consistency Evaluation
18. Chelsea Finn, Kelvin Xu and Sergey Levine, Probabilistic Model-Agnostic Meta-Learning
19. Luca Falorsi, Pim de Haan, Tim R. Davidson, Nicola De Cao, Maurice Weiler, Patrick Forré and Taco S. Cohen, Explorations in Homeomorphic Variational Auto-Encoding
20. Ishaan Gulrajani, Colin Raffel and Luke Metz, Towards GAN Benchmarks Which Require Generalization
21. Akshat Dave, Anil Kumar Vadathya, Ramana Subramanyam and Kaushik Mitra, Solving Inverse Problems in Compressive Imaging using Deep Autoregressive Model
22. Thanh Nguyen, Raymond Wong and Chinmay Hegde, Autoencoders Learn Generative Linear Models