Colin Wei

发表

General Bounds on Satisfiability Thresholds for Random CSPs via Fourier Analysis

Colin Wei, Stefano Ermon, Colin Wei, 2017, AAAI.

Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin

Colin Wei, Tengyu Ma, Tengyu Ma, 2020, ICLR.

Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Colin Wei, Tengyu Ma, Adrien Gaidon, 2019, NeurIPS.

Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin pdf

Colin Wei, Tengyu Ma, 2019, ArXiv.

The Implicit and Explicit Regularization Effects of Dropout pdf

Colin Wei, Tengyu Ma, Sham Kakade, 2020, ICML.

On the Margin Theory of Feedforward Neural Networks pdf

Qiang Liu, Colin Wei, Tengyu Ma, 2018, ArXiv.

Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data pdf

Colin Wei, Tengyu Ma, Yining Chen, 2020, ArXiv.

Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation

Colin Wei, Tengyu Ma, Tengyu Ma, 2019, NeurIPS.

Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks

Colin Wei, Yuanzhi Li, Tengyu Ma, 2019, NeurIPS.

Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel

Colin Wei, Tengyu Ma, Qiang Liu, 2018, NeurIPS.

Markov Chain Truncation for Doubly-Intractable Inference

Colin Wei, Iain Murray, Iain Murray, 2016, AISTATS.

Meta-learning Transferable Representations with a Single Target Domain pdf

Colin Wei, Tengyu Ma, Hong Liu, 2020, ArXiv.

Generic 3D Representation via Pose Estimation and Matching

Jitendra Malik, Silvio Savarese, Colin Wei, 2016, ECCV.

Self-training Avoids Using Spurious Features Under Domain Shift pdf

Colin Wei, Tengyu Ma, Ananya Kumar, 2020, NeurIPS.

Shape Matters: Understanding the Implicit Bias of the Noise Covariance pdf

Colin Wei, Tengyu Ma, Jason D. Lee, 2020, COLT.

Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss pdf

Colin Wei, Tengyu Ma, Adrien Gaidon, 2021, ArXiv.

Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers pdf

Colin Wei, Tengyu Ma, Yining Chen, 2021, ArXiv.

Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning pdf

Colin Wei, Tengyu Ma, Sang Michael Xie, 2021, ArXiv.

Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data pdf

Colin Wei, Tengyu Ma, Kendrick Shen, 2020, ICLR.

Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin pdf

Colin Wei, Tengyu Ma, Tengyu Ma, 2019, ICLR.