-
Department of Computer Science, UCLA
- http://web.cs.ucla.edu/~qgu
Highlights
- Pro
-
SPPO Public
The official implementation of Self-Play Preference Optimization (SPPO)
-
Rephrase-and-Respond Public
Official repo of Respond-and-Respond: data, code, and evaluation
-
-
GFA-RFE Public
Uncertainty-Aware Reward-Free Exploration with General Function Approximation
-
SPIN Public
The official implementation of Self-Play Fine-Tuning (SPIN)
-
-
-
MoE Public
Towards Understanding the Mixture-of-Experts Layer in Deep Learning
-
PDE Public
Official repo of Progressive Data Expansion: data, code and evaluation
-
-
Padam Public
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)
-
-
-
Benign-Overfitting-CNN Public
Benign Overfitting in Two-layer Convolutional Neural Networks
-
pretrain-finetune-SGD Public
The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift
-
multipass-SGD Public
Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime
-
LDP-UCRL-VTR Public
Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes
-
HF-UCRL-VTR Public
Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs
-
POWERS Public
Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs
Jupyter Notebook Apache License 2.0 UpdatedOct 12, 2022 -
FedLinUCB Public
A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
-
CW-OFUL Public
Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions
-
-
-
-
RayS Public
RayS: A Ray Searching Method for Hard-label Adversarial Attack (KDD2020)
-
-
-
Frank-Wolfe-AdvML Public
A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks (AAAI'20)
-
CS161-Winter2020 Public
Fundamentals of Artificial Intelligence
-