Timezone: »
Poster
MMD GAN: Towards Deeper Understanding of Moment Matching Network
Chun-Liang Li · Wei-Cheng Chang · Yu Cheng · Yiming Yang · Barnabas Poczos
Generative moment matching network (GMMN) is a deep generative model that differs from Generative Adversarial Network (GAN) by replacing the discriminator in GAN with a two-sample test based on kernel maximum mean discrepancy (MMD). Although some theoretical guarantees of MMD have been studied, the empirical performance of GMMN is still not as competitive as that of GAN on challenging and large benchmark datasets. The computational efficiency of GMMN is also less desirable in comparison with GAN, partially due to its requirement for a rather large batch size during the training. In this paper, we propose to improve both the model expressiveness of GMMN and its computational efficiency by introducing {\it adversarial kernel learning} techniques, as the replacement of a fixed Gaussian kernel in the original GMMN. The new approach combines the key ideas in both GMMN and GAN, hence we name it MMD-GAN. The new distance measure in MMD-GAN is a meaningful loss that enjoys the advantage of weak$^*$ topology and can be optimized via gradient descent with relatively small batch sizes. In our evaluation on multiple benchmark datasets, including MNIST, CIFAR-10, CelebA and LSUN, the performance of MMD-GAN significantly outperforms GMMN, and is competitive with other representative GAN works.
Author Information
Chun-Liang Li (Carnegie Mellon University)
Wei-Cheng Chang (Carnegie Mellon University)
Yu Cheng (AI Foundations, IBM Research)
Yiming Yang (CMU)
Barnabas Poczos (Carnegie Mellon University)
More from the Same Authors
-
2020 Poster: Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction »
Mariya Toneva · Otilia Stretcu · Barnabas Poczos · Leila Wehbe · Tom Mitchell -
2020 Poster: Robust Density Estimation under Besov IPM Losses »
Ananya Uppal · Shashank Singh · Barnabas Poczos -
2020 Spotlight: Robust Density Estimation under Besov IPM Losses »
Ananya Uppal · Shashank Singh · Barnabas Poczos -
2020 Poster: Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing »
Zihang Dai · Guokun Lai · Yiming Yang · Quoc V Le -
2019 Workshop: Sets and Partitions »
Nicholas Monath · Manzil Zaheer · Andrew McCallum · Ari Kobren · Junier Oliva · Barnabas Poczos · Ruslan Salakhutdinov -
2019 Poster: XLNet: Generalized Autoregressive Pretraining for Language Understanding »
Zhilin Yang · Zihang Dai · Yiming Yang · Jaime Carbonell · Russ Salakhutdinov · Quoc V Le -
2019 Poster: Nonparametric Density Estimation & Convergence Rates for GANs under Besov IPM Losses »
Ananya Uppal · Shashank Singh · Barnabas Poczos -
2019 Oral: Nonparametric Density Estimation & Convergence Rates for GANs under Besov IPM Losses »
Ananya Uppal · Shashank Singh · Barnabas Poczos -
2019 Oral: XLNet: Generalized Autoregressive Pretraining for Language Understanding »
Zhilin Yang · Zihang Dai · Yiming Yang · Jaime Carbonell · Russ Salakhutdinov · Quoc V Le -
2019 Poster: Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels »
Simon Du · Kangcheng Hou · Russ Salakhutdinov · Barnabas Poczos · Ruosong Wang · Keyulu Xu -
2019 Poster: Re-examination of the Role of Latent Variables in Sequence Modeling »
Guokun Lai · Zihang Dai · Yiming Yang · Shinjae Yoo -
2019 Poster: Learning Local Search Heuristics for Boolean Satisfiability »
Emre Yolcu · Barnabas Poczos -
2018 Poster: Nonparametric Density Estimation under Adversarial Losses »
Shashank Singh · Ananya Uppal · Boyue Li · Chun-Liang Li · Manzil Zaheer · Barnabas Poczos -
2018 Poster: Neural Architecture Search with Bayesian Optimisation and Optimal Transport »
Kirthevasan Kandasamy · Willie Neiswanger · Jeff Schneider · Barnabas Poczos · Eric Xing -
2018 Spotlight: Neural Architecture Search with Bayesian Optimisation and Optimal Transport »
Kirthevasan Kandasamy · Willie Neiswanger · Jeff Schneider · Barnabas Poczos · Eric Xing -
2017 Oral: Deep Sets »
Manzil Zaheer · Satwik Kottur · Siamak Ravanbakhsh · Barnabas Poczos · Ruslan Salakhutdinov · Alexander Smola -
2017 Poster: Hypothesis Transfer Learning via Transformation Functions »
Simon Du · Jayanth Koushik · Aarti Singh · Barnabas Poczos -
2017 Poster: Deep Sets »
Manzil Zaheer · Satwik Kottur · Siamak Ravanbakhsh · Barnabas Poczos · Ruslan Salakhutdinov · Alexander Smola -
2017 Poster: Gradient Descent Can Take Exponential Time to Escape Saddle Points »
Simon Du · Chi Jin · Jason D Lee · Michael Jordan · Aarti Singh · Barnabas Poczos -
2017 Spotlight: Gradient Descent Can Take Exponential Time to Escape Saddle Points »
Simon Du · Chi Jin · Jason D Lee · Michael Jordan · Aarti Singh · Barnabas Poczos -
2016 Poster: Variance Reduction in Stochastic Gradient Langevin Dynamics »
Kumar Avinava Dubey · Sashank J. Reddi · Sinead Williamson · Barnabas Poczos · Alexander Smola · Eric Xing -
2016 Poster: The Multi-fidelity Multi-armed Bandit »
Kirthevasan Kandasamy · Gautam Dasarathy · Barnabas Poczos · Jeff Schneider -
2016 Poster: Finite-Sample Analysis of Fixed-k Nearest Neighbor Density Functional Estimators »
Shashank Singh · Barnabas Poczos -
2016 Poster: Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization »
Sashank J. Reddi · Suvrit Sra · Barnabas Poczos · Alexander Smola -
2016 Poster: Adaptive Smoothed Online Multi-Task Learning »
Keerthiram Murugesan · Hanxiao Liu · Jaime Carbonell · Yiming Yang -
2016 Poster: Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations »
Kirthevasan Kandasamy · Gautam Dasarathy · Junier B Oliva · Jeff Schneider · Barnabas Poczos -
2016 Poster: Efficient Nonparametric Smoothness Estimation »
Shashank Singh · Simon Du · Barnabas Poczos -
2016 Poster: Doubly Convolutional Neural Networks »
Shuangfei Zhai · Yu Cheng · Weining Lu · Zhongfei (Mark) Zhang -
2015 Poster: Nonparametric von Mises Estimators for Entropies, Divergences and Mutual Informations »
Kirthevasan Kandasamy · Akshay Krishnamurthy · Barnabas Poczos · Larry Wasserman · james m robins -
2015 Poster: On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants »
Sashank J. Reddi · Ahmed Hefny · Suvrit Sra · Barnabas Poczos · Alexander Smola -
2014 Poster: Exponential Concentration of a Density Functional Estimator »
Shashank Singh · Barnabas Poczos -
2012 Poster: Bayesian models for Large-scale Hierarchical Classification »
Siddharth Gopal · Yiming Yang · Bing Bai · Alexandru Niculescu-Mizil -
2011 Poster: Group Anomaly Detection using Flexible Genre Models »
Liang Xiong · Barnabas Poczos · Jeff Schneider -
2010 Poster: Estimation of Renyi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs »
David Pal · Barnabas Poczos · Csaba Szepesvari