Search Results for author: John Peebles

Found 8 papers, 1 papers with code

Optimal Testing of Discrete Distributions with High Probability

no code implementations14 Sep 2020 Ilias Diakonikolas, Themis Gouleakis, Daniel M. Kane, John Peebles, Eric Price

To illustrate the generality of our methods, we give optimal algorithms for testing collections of distributions and testing closeness with unequal sized samples.

The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement

1 code implementation ECCV 2020 William Peebles, John Peebles, Jun-Yan Zhu, Alexei Efros, Antonio Torralba

In this paper, we propose the Hessian Penalty, a simple regularization term that encourages the Hessian of a generative model with respect to its input to be diagonal.

Disentanglement

Towards Testing Monotonicity of Distributions Over General Posets

no code implementations6 Jul 2019 Maryam Aliakbarpour, Themis Gouleakis, John Peebles, Ronitt Rubinfeld, Anak Yodpinyanee

We then build on these lower bounds to give $\Omega(n/\log{n})$ lower bounds for testing monotonicity over a matching poset of size $n$ and significantly improved lower bounds over the hypercube poset.

Testing Identity of Multidimensional Histograms

no code implementations10 Apr 2018 Ilias Diakonikolas, Daniel M. Kane, John Peebles

We give the first identity tester for this problem with {\em sub-learning} sample complexity in any fixed dimension and a nearly-matching sample complexity lower bound.

Two-sample testing

On the limitations of first order approximation in GAN dynamics

no code implementations ICLR 2018 Jerry Li, Aleksander Madry, John Peebles, Ludwig Schmidt

This suggests that such usage of the first order approximation of the discriminator, which is a de-facto standard in all the existing GAN dynamics, might be one of the factors that makes GAN training so challenging in practice.

Optimal Identity Testing with High Probability

no code implementations9 Aug 2017 Ilias Diakonikolas, Themis Gouleakis, John Peebles, Eric Price

Our new upper and lower bounds show that the optimal sample complexity of identity testing is \[ \Theta\left( \frac{1}{\epsilon^2}\left(\sqrt{n \log(1/\delta)} + \log(1/\delta) \right)\right) \] for any $n, \varepsilon$, and $\delta$.

On the Limitations of First-Order Approximation in GAN Dynamics

no code implementations ICML 2018 Jerry Li, Aleksander Madry, John Peebles, Ludwig Schmidt

While Generative Adversarial Networks (GANs) have demonstrated promising performance on multiple vision tasks, their learning dynamics are not yet well understood, both in theory and in practice.

Collision-based Testers are Optimal for Uniformity and Closeness

no code implementations11 Nov 2016 Ilias Diakonikolas, Themis Gouleakis, John Peebles, Eric Price

We study the fundamental problems of (i) uniformity testing of a discrete distribution, and (ii) closeness testing between two discrete distributions with bounded $\ell_2$-norm.

Cannot find the paper you are looking for? You can Submit a new open access paper.