Colin Wei

Publication Activity (10 Years)

Years Active: 2016-2023
Publications (10 Years): 36

Top Topics

Fourier Analysis

Top Venues

Publications

Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. ICLR (2023)
Jeff Z. HaoChen, Colin Wei, Ananya Kumar, Tengyu Ma
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations. CoRR (2022)
Colin Wei, J. Zico Kolter
Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation. ICLR (2022)
Jeff Z. HaoChen, Colin Wei, Ananya Kumar, Tengyu Ma
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations. NeurIPS (2022)
Colin Wei, Yining Chen, Tengyu Ma
Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers. NeurIPS (2022)
Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. CoRR (2022)
Colin Wei, Yining Chen, Tengyu Ma
Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers. CoRR (2021)
Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma
Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data. ICLR (2021)
Colin Wei, Sang Michael Xie, Tengyu Ma
Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning. NeurIPS (2021)
Jeff Z. HaoChen, Colin Wei, Adrien Gaidon, Tengyu Ma
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss. NeurIPS (2021)
Colin Wei, Sang Michael Xie, Tengyu Ma
Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning. CoRR (2021)
Jeff Z. HaoChen, Colin Wei, Adrien Gaidon, Tengyu Ma
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss. CoRR (2021)
Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma
Shape Matters: Understanding the Implicit Bias of the Noise Covariance. COLT (2021)
Colin Wei, Sham M. Kakade, Tengyu Ma
The Implicit and Explicit Regularization Effects of Dropout. CoRR (2020)
Colin Wei, Tengyu Ma
Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin. ICLR (2020)
Hong Liu, Jeff Z. HaoChen, Colin Wei, Tengyu Ma
Meta-learning Transferable Representations with a Single Target Domain. CoRR (2020)
Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma
Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data. CoRR (2020)
Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma
Shape Matters: Understanding the Implicit Bias of the Noise Covariance. CoRR (2020)
Yining Chen, Colin Wei, Ananya Kumar, Tengyu Ma
Self-training Avoids Using Spurious Features Under Domain Shift. NeurIPS (2020)
Colin Wei, Sham M. Kakade, Tengyu Ma
The Implicit and Explicit Regularization Effects of Dropout. ICML (2020)
Yining Chen, Colin Wei, Ananya Kumar, Tengyu Ma
Self-training Avoids Using Spurious Features Under Domain Shift. CoRR (2020)
Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel. NeurIPS (2019)
Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Aréchiga, Tengyu Ma
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. CoRR (2019)
Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Aréchiga, Tengyu Ma
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. NeurIPS (2019)
Yuanzhi Li, Colin Wei, Tengyu Ma
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks. NeurIPS (2019)
Yuanzhi Li, Colin Wei, Tengyu Ma
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks. CoRR (2019)
Colin Wei, Tengyu Ma
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation. NeurIPS (2019)
Colin Wei, Tengyu Ma
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation. CoRR (2019)
Colin Wei, Tengyu Ma
Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin. CoRR (2019)
Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma
On the Margin Theory of Feedforward Neural Networks. CoRR (2018)
Colin Wei, Iain Murray
Markov Chain Truncation for Doubly-Intractable Inference. AISTATS (2017)
Colin Wei, Stefano Ermon
General Bounds on Satisfiability Thresholds for Random CSPs via Fourier Analysis. AAAI (2017)
Amir Roshan Zamir, Tilman Wekel, Pulkit Agrawal, Colin Wei, Jitendra Malik, Silvio Savarese
Generic 3D Representation via Pose Estimation and Matching. CoRR (2017)
Colin Wei, Stefano Ermon
General Bounds on Satisfiability Thresholds for Random CSPs via Fourier Analysis. CoRR (2017)
Colin Wei, Iain Murray
Markov Chain Truncation for Doubly-Intractable Inference. CoRR (2016)
Amir Roshan Zamir, Tilman Wekel, Pulkit Agrawal, Colin Wei, Jitendra Malik, Silvio Savarese
Generic 3D Representation via Pose Estimation and Matching. ECCV (3) (2016)