353 citations
- University of TorontoCA7 papers
- University of CambridgeGB3 papers
- University of Central FloridaUS3 papers
- Amazon (Germany)DE2 papers
- Meta (Israel)IL2 papers
- OpenAI (United States)US2 papers
- University of AmsterdamNL2 papers
- University of WaterlooCA2 papers
- Aalborg UniversityDK1 paper
- AIT Austrian Institute of Technology GmbHAT1 paper
- Ames Research CenterUS1 paper
- Arizona State UniversityUS1 paper
6 papers · 1 filter
Hierarchical Verification for Adversarial Robustness
Cong Han Lim, Raquel Urtasun, Ersin Yumer
We introduce a new framework for the exact point-wise robustness verification problem that exploits the layer-wise geometric structure of deep feed-forward networks with r…
Synthetic Petri Dish: A Novel Surrogate Model for Rapid Architecture Search
Aditya Rawal, Joel Lehman, Felipe Petroski Such +2
Neural Architecture Search (NAS) explores a large space of architectural motifs -- a compute-intensive process that often involves ground-truth evaluation of each motif by instanti…
Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trials
Christian F. Perez, Felipe Petroski Such, Theofanis Karaletsos
There is broad interest in creating RL agents that can solve many (related) tasks and adapt to new tasks and environments after initial training. Model-based RL leverages learned s…
Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
Felipe Petroski Such, Aditya Rawal, Joel Lehman +2
This paper investigates the intriguing question of whether we can create learning algorithms that automatically generate training data, learning environments, and curricula in orde…
Towards Empathic Deep Q-Learning
Bart Bussmann, Jacqueline Heinerman, Joel Lehman
As reinforcement learning (RL) scales to solve increasingly complex tasks, interest continues to grow in the fields of AI safety and machine ethics. As a contribution to these fiel…
Densifying Assumed-sparse Tensors: Improving Memory Efficiency and MPI Collective Performance during Tensor Accumulation for Parallelized Training of Neural Machine Translation Models
Derya Cavdar, Valeriu Codreanu, Can Karakus +11
Neural machine translation - using neural networks to translate human language - is an area of active research exploring new neuron types and network topologies with the goal of dr…