UCLA Artificial General Intelligence Lab's repositories
Rephrase-and-Respond
Official repo of Respond-and-Respond: data, code, and evaluation
Frank-Wolfe-AdvML
A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks (AAAI'20)
svrg-lowrank
fast nonconvex stochastic variance reduced gradient for low-rank matrix estimation
CS161-Winter2020
Fundamentals of Artificial Intelligence
Benign-Overfitting-CNN
Benign Overfitting in Two-layer Convolutional Neural Networks
CS260-Spring2020
Machine Learning
HF-UCRL-VTR
Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs
LDP-UCRL-VTR
Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes
pretrain-finetune-SGD
The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift
RobustOFUL
Corruption-robust linear contextual bandits
multipass-SGD
Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime
nonconvex-lowrank
nonconvex Low-rank matrix factorization