← Authors

Colin Wei

16 papers · 2017–2023 · 5 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer πŸ—ΊοΈ Taxonomy Completionist (29) 🐝 Cross-Pollinator (15) πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (6) πŸ“› The Namer 🀝 Dynamic Duo (14) πŸ‘‘ Triple Crown πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (5) πŸ’Ž Century Club (16) ❓ The Questioner

Conferences

NIPS (9) ICLR (4) AISTATS (1) COLT (1) ICML (1)

Top co-authors

Tengyu Ma (14) Yining Chen (3) Jeff Z. HaoChen (3) Adrien Gaidon (2) Jason Lee (2) Ananya Kumar (2) Iain Murray (1) Yuanzhi Li (1) Sang Michael Xie (1) Kendrick Shen (1)

Keywords

neural network (4) stochastic gradient descent (3) representation learning (3) contrastive learning (2) sample complexity (2) generalization bound (2) implicit regularization (2) domain adaptation (1) transfer learning (1) neural tangent kernel (1) unsupervised domain adaptation (1) markov chain monte carlo (1) importance sampling (1) partition function (1) hidden markov model (1) data augmentation (1) spectral decomposition (1) rademacher complexity (1) gradient descent (1) label noise (1)

Papers

Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence ICLR 2023
Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation ICLR 2022
Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers NIPS 2022
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations NIPS 2022
Shape Matters: Understanding the Implicit Bias of the Noise Covariance COLT 2021
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss NIPS 2021
Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning NIPS 2021
Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data ICLR 2021
The Implicit and Explicit Regularization Effects of Dropout ICML 2020
Self-training Avoids Using Spurious Features Under Domain Shift NIPS 2020
Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin ICLR 2020
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation NIPS 2019
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks NIPS 2019
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel NIPS 2019
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss NIPS 2019
Markov Chain Truncation for Doubly-Intractable Inference AISTATS 2017