Yunus Saatchi

ICML Conference 2019 Conference Paper

Metropolis-Hastings Generative Adversarial Networks

• Ryan D. Turner
• Jane Hung
• Eric Frank
• Yunus Saatchi
• Jason Yosinski

We introduce the Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs. The MH-GAN draws samples from the distribution implicitly defined by a GAN’s discriminator-generator pair, as opposed to standard GANs which draw samples from the distribution defined only by the generator. It uses the discriminator from GAN training to build a wrapper around the generator for improved sampling. With a perfect discriminator, this wrapped generator samples from the true distribution on the data exactly even when the generator is imperfect. We demonstrate the benefits of the improved generator on multiple benchmark datasets, including CIFAR-10 and CelebA, using the DCGAN, WGAN, and progressive GAN.

JMLR Journal 2017 Journal Article

Learning Scalable Deep Kernels with Recurrent Structure

• Maruan Al-Shedivat
• Andrew Gordon Wilson
• Yunus Saatchi
• Zhiting Hu
• Eric P. Xing

Many applications in speech, robotics, finance, and biology deal with sequential data, where ordering matters and recurrent structures are common. However, this structure cannot be easily captured by standard kernel functions. To model such structure, we propose expressive closed-form kernel functions for Gaussian processes. The resulting model, GP-LSTM, fully encapsulates the inductive biases of long short-term memory (LSTM) recurrent networks, while retaining the non-parametric probabilistic advantages of Gaussian processes. We learn the properties of the proposed kernels by optimizing the Gaussian process marginal likelihood using a new provably convergent semi-stochastic gradient procedure, and exploit the structure of these kernels for scalable training and prediction. This approach provides a practical representation for Bayesian LSTMs. We demonstrate state-of-the-art performance on several benchmarks, and thoroughly investigate a consequential autonomous driving application, where the predictive uncertainties provided by GP- LSTM are uniquely valuable. [abs] [ pdf ][ bib ] &copy JMLR 2017. ( edit, beta )

ICML Conference 2013 Conference Paper

Scaling Multidimensional Gaussian Processes using Projected Additive Approximations

• Elad Gilboa
• Yunus Saatchi
• John P. Cunningham

Exact Gaussian Process (GP) regression has O(N^3) runtime for data size N, making it intractable for large N. Advances in GP scaling have not been extended to the multidimensional input setting, despite the preponderance of multidimensional applications. This paper introduces and tests a novel method of projected additive approximation to multidimensional GPs. We thoroughly illustrate the power of this method on several datasets, achieving close performance to the naive Full GP at orders of magnitude less cost.

ICML Conference 2010 Conference Paper

Gaussian Process Change Point Models

• Yunus Saatchi
• Ryan D. Turner
• Carl E. Rasmussen

ICML Conference 2008 Conference Paper

Beam sampling for the infinite hidden Markov model

• Jurgen Van Gael
• Yunus Saatchi
• Yee Whye Teh
• Zoubin Ghahramani

The infinite hidden Markov model is a non-parametric extension of the widely used hidden Markov model. Our paper introduces a new inference algorithm for the infinite Hidden Markov model called beam sampling . Beam sampling combines slice sampling, which limits the number of states considered at each time step to a finite number, with dynamic programming, which samples whole state trajectories efficiently. Our algorithm typically outperforms the Gibbs sampler and is more robust. We present applications of iHMM inference using the beam sampler on changepoint detection and text prediction problems.