Andrew Ilyas
Artificial Intelligence · 2017–2023
A researcher in the Science corpus: 23 papers; trusts 1,429 researchers and is trusted by 667 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 571 citations into it; #1,699 of 36,961 by trust here, #1,396 by citations
- Computer Vision and Pattern Recognition — 395 citations into it; #2,451 of 21,973 by trust here, #1,316 by citations
- Safety, Robustness & Interpretability — 290 citations into it; #120 of 2,259 by trust here, #133 by citations
- Optimization & Training — 95 citations into it; #1,329 of 2,605 by trust here, #698 by citations
- Generative Models — 92 citations into it; #509 of 1,963 by trust here, #664 by citations
- Evaluation & Benchmarks — 67 citations into it
- Signal Processing — 64 citations into it; #712 of 7,592 by trust here, #339 by citations
- Reinforcement Learning — 57 citations into it; #2,237 of 2,250 by trust here, #1,612 by citations
Whom Andrew Ilyas trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Diederik P. Kingma
- Ian J. Goodfellow
- Geoffrey E. Hinton
- Christian Szegedy
- Yoshua Bengio
- Nicholas Carlini
- Kaiming He
- Yann LeCun
- Ilya Sutskever
Who trusts Andrew Ilyas overall
- Nicholas Carlini
- Florian Tramèr
- Lukas Schott
- Tianyu Pang
- David Stutz
- Zhichao Huang
- Logan Engstrom
- Jianbo Chen
- Yinpeng Dong
- Naveed Akhtar
Papers from Andrew Ilyas's perspective
Ordered by how strongly the researchers Andrew Ilyas trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Synthesizing Robust Adversarial Examples (2017) — 1,876 citations
- Adversarial Examples Are Not Bugs, They Are Features (2019) — 2,151 citations
- How Does Batch Normalization Help Optimization? (No, It Is Not About Internal Covariate Shift) (2018) — 1,738 citations
- Black-box Adversarial Attacks with Limited Queries and Information (2018) — 1,400 citations
- Training GANs with Optimism (2017) — 593 citations
- Evaluating and Understanding the Robustness of Adversarial Logit Pairing (2018) — 145 citations
- Identifying Statistical Bias in Dataset Replication (2020) — 55 citations
- Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors (2018) — 430 citations
- The Robust Manifold Defense: Adversarial Training using Generative Models (2017) — 176 citations
- Query-Efficient Black-box Adversarial Examples (2017) — 53 citations
- Implementation Matters in Deep RL: A Case Study on PPO and TRPO (2020) — 322 citations
- Datamodels: Predicting Predictions from Training Data (2022) — 215 citations
- Computer Vision with a Single (Robust) Classifier (2019) — 36 citations
- Noise or Signal: The Role of Image Backgrounds in Object Recognition (2020) — 466 citations
- From ImageNet to Image Classification: Contextualizing Progress on Benchmarks (2020) — 151 citations
- Learning Perceptually-Aligned Representations via Adversarial Robustness (2019) — 63 citations
- Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO (2020) — 333 citations
- Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms? (2018) — 54 citations
- A Closer Look at Deep Policy Gradients (2018) — 110 citations
- Do Adversarially Robust ImageNet Models Transfer Better? (2020) — 492 citations