Greg Yang

18 papers · 2019–2025 · 3 conferences · across top CS/AI conferences

Achievements

+8 more ↓

🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (3) 🐝 Cross-Pollinator (14)

🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🏆 Keyword Champion (2) 🔥 Unstoppable (7) 💎 Century Club (18) ⚡ Prolific Year (5) 📈 Trend Setter 🗃️ Keyword Collector (59)

Conferences

NIPS (8) ICLR (5) ICML (5)

Top co-authors

Hadi Salman (5) Etai Littwin (3) Pengchuan Zhang (3) Soufiane Hayou (2) Ashish Kapoor (2) Ilya Razenshteyn (2) Jerry Li (2) Huan Zhang (2) Jascha Sohl-dickstein (2) Jeffrey Pennington (2)

Keywords

neural tangent kernel (4) randomized smoothing (3) neural network (3) adversarial robustness (3) neural network optimization (2) feature learning (2) representation learning (2) infinite width (2) certified robustness (2) gaussian process (2) infinite-width limit (2) gradient descent (2) model debugging (1) function space (1) neural network theory (1) transfer learning (1) deep learning (1) covariance structure (1) adversarial training (1) linear programming (1)

Papers

Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$ Parametrization ICML 2025 Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks ICLR 2024 Adaptive Optimization in the $\infty$-Width Limit ICLR 2023 Width and Depth Limits Commute in Residual Networks ICML 2023 Non-Gaussian Tensor Programs NIPS 2022 3DB: A Framework for Debugging Computer Vision Models NIPS 2022 High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation NIPS 2022 Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features ICLR 2022 Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks ICML 2021 Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics ICML 2021 On Infinite-Width Hypernetworks NIPS 2020 Denoised Smoothing: A Provable Defense for Pretrained Classifiers NIPS 2020 Randomized Smoothing of All Shapes and Sizes ICML 2020 Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes ICLR 2019 Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers NIPS 2019 Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes NIPS 2019 A Mean Field Theory of Batch Normalization ICLR 2019 A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks NIPS 2019