Avraham Ruderman

发表

Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures pdf

Pushmeet Kohli, Csaba Szepesvári, Krishnamurthy Dvijotham, 2018, ICLR.

Neural scene representation and rendering

Koray Kavukcuoglu, Daan Wierstra, Karol Gregor, 2018, Science.

Human-level performance in 3D multiplayer games with population-based reinforcement learning

Guy Lever, Joel Z. Leibo, Demis Hassabis, 2018, Science.

Human-level performance in first-person multiplayer games with population-based deep reinforcement learning

Joel Z. Leibo, Ari S. Morcos, Neil C. Rabinowitz, 2018, ArXiv.

VALUATION : A N ADVERSARIAL APPROACH TO UNCOVER CATASTROPHIC FAILURES

Jonathan Uesato, N. Heess, T. Erez, 2019 .

Learning with Similarities on Subsets

Avraham Ruderman, 2015 .

Unsupervised Pre-Training Speeds up the Search for Good Features : An Analysis of a Simplified Model of Neural Network Learning

Avraham Ruderman, 2014 .

Learned Deformation Stability in Convolutional Neural Networks

Ari S. Morcos, Neil C. Rabinowitz, Avraham Ruderman, 2018, ArXiv.

PSI Draft Specification

Avraham Ruderman, Barry J. Drake, Mark D. Reid, 2022, ArXiv.

Uncovering Surprising Behaviors in Reinforcement Learning via Worst-case Analysis

Pushmeet Kohli, Jonathan Uesato, Richard Everett, 2018 .

Learned Deformation Stability in Convolutional Neural Networks

Ari S. Morcos, Neil C. Rabinowitz, Avraham Ruderman, 2018, ArXiv.

Tighter Variational Representations of f-Divergences via Restriction to Probability Measures pdf

Mark D. Reid, James Petterson, Dario García-García, 2012, ICML.

On the behaviour of tests based on sample spacings for moderatesamples

Avraham Ruderman, S. Penev, 2011 .

Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs

Daniel Zoran, Ari S. Morcos, Avraham Ruderman, 2018, 1804.04438.