UCLA Artificial General Intelligence Lab

SPIN. The official implementation of Self-Play Fine-Tuning (SPIN)

SPPO. The official implementation of Self-Play Preference Optimization (SPPO)

Rephrase-and-Respond. Official repo of Respond-and-Respond: data, code, and evaluation

RayS. RayS: A Ray Searching Method for Hard-label Adversarial Attack (KDD2020)

NeuralUCB. Python

Padam. Partially Adaptive Momentum Estimation method in the paper "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks" (accepted by IJCAI 2020)

MoE. Towards Understanding the Mixture-of-Experts Layer in Deep Learning

PDE. Official repo of Progressive Data Expansion: data, code and evaluation

COPS. The official implementation of Cross-Task Experience Sharing (COPS)

ucla-covid19-forecasts. Python

Frank-Wolfe-AdvML. A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks (AAAI'20)

NeuralTS. Python

svrg-lowrank. fast nonconvex stochastic variance reduced gradient for low-rank matrix estimation

nonconvex-RPCA. fast nonconvex algorithm for robust PCA

GFA-RFE. Uncertainty-Aware Reward-Free Exploration with General Function Approximation

CS269-Winter2019.

CW-OFUL. Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

Benign-Overfitting-CNN. Benign Overfitting in Two-layer Convolutional Neural Networks

nonconvex-IMC. fast nonconvex algorithm for inductive matrix completion

CS260-Fall2022.

PhyGCN. Python

Benign_ReLU_CNN. Python

VACDB. Variance-aware Contextual Dueling Bandits

FedLinUCB. A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

CS260-Fall18. Machine Learning

CS161-Winter2020. Fundamentals of Artificial Intelligence

pretrain-finetune-SGD. The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

FLASH. Fast Local minimA finding with third-order SmootHness (FLASH)

CS260-Spring2020. Machine Learning

CP-time-series-clustering. High-dimensional Time Series Clustering via Cross-Predictability

LDP-UCRL-VTR. Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes

nonconvex-CGGM. fast nonconvex algorithm for covariate-adjusted precision matrix estimation/conditional Gaussian graphical model estimation

SSL_Pseudo_Labeler. Python

nonconvex-LVGGM. fast nonconvex algorithm for latent variable Gaussian graphical models

DNDM. Python