Colin Wei
16 papers · 2017–2023 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (35) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
The Namer
π§
Keyword Pioneer
π
Triple Crown
π€
Dynamic Duo
(14)
β
The Questioner
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(60)
Top co-authors
Research topics
Machine Learning
(16)
Optimization & Theory Β· Machine Learning
(10)
Deep Learning
(9)
Learning Types Β· Machine Learning
(8)
Core Methods
(5)
Optimization & Theory Β· Deep Learning
(5)
Artificial Intelligence
(3)
Application Areas
(3)
Architectures
(3)
Learning Types Β· Deep Learning
(2)
Mathematics & Optimization
(1)
Bayesian & Probabilistic
(1)
Core AI
(1)
Learning Paradigms
(1)
Models
(1)
Keywords
neural network
(6)
generalization bound
(4)
sample complexity
(3)
stochastic gradient descent
(3)
representation learning
(3)
unsupervised domain adaptation
(2)
adversarial robustness
(2)
overparameterized model
(2)
contrastive learning
(2)
implicit regularization
(2)
certified robustness
(1)
data augmentation
(1)
self-supervised learning
(1)
semi-supervised learning
(1)
neural tangent kernel
(1)
entropy minimization
(1)
uniform convergence
(1)
domain adaptation
(1)
label noise
(1)
partition function
(1)
Papers
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence
ICLR 2023
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations
NeurIPS 2022
Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation
ICLR 2022
Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers
NeurIPS 2022
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss
NeurIPS 2021
Shape Matters: Understanding the Implicit Bias of the Noise Covariance
COLT 2021
Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
ICLR 2021
Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning
NeurIPS 2021
Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin
ICLR 2020
Self-training Avoids Using Spurious Features Under Domain Shift
NeurIPS 2020
The Implicit and Explicit Regularization Effects of Dropout
ICML 2020
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation
NeurIPS 2019
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
NeurIPS 2019
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel
NeurIPS 2019
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks
NeurIPS 2019
Markov Chain Truncation for Doubly-Intractable Inference
AISTATS 2017