lx10077
A machine leaning learner interested in the intersection between optimization and statistics.
School of Mathematical Science, Peking UniversityPeking, China
Pinned Repositories
AveQLearning
Codes for the AISTATS 2023 paper, A Statistical Analysis of Polyak-Ruppert Averaged Q-learning.
cdiscount-image-classification
Codes for cdiscount image classification, a Kaggle competition to categorize seven million commodities into up to five thousand classes.
dqnpy
DQN and its variants in deep reinforcement learning. Now it only incorporates vallina DQN, average DQN and median DQN.
fedavgpy
On the Convergence of FedAvg on Non-IID Data
ganpy
Pytorch implementation of generative adversary networks.
lasso
Convex optimizers for LASSO, including subgradient, project gradient, proximal gradient, smooth method, lagrangian method and stochastic gradient descent variants.
LocalPower
Codes for LocalPower
lx10077.github.io
Xiang Li's personal homepage
optimpy
Home of various optimization algorithms.
rlpy
A pytorch-version implementation of RL algorithms. Now it collects TRPO, ClipPPO, A2C, GAIL and ADCV.
lx10077's Repositories
lx10077/fedavgpy
On the Convergence of FedAvg on Non-IID Data
lx10077/lasso
Convex optimizers for LASSO, including subgradient, project gradient, proximal gradient, smooth method, lagrangian method and stochastic gradient descent variants.
lx10077/dqnpy
DQN and its variants in deep reinforcement learning. Now it only incorporates vallina DQN, average DQN and median DQN.
lx10077/AveQLearning
Codes for the AISTATS 2023 paper, A Statistical Analysis of Polyak-Ruppert Averaged Q-learning.
lx10077/rlpy
A pytorch-version implementation of RL algorithms. Now it collects TRPO, ClipPPO, A2C, GAIL and ADCV.
lx10077/cdiscount-image-classification
Codes for cdiscount image classification, a Kaggle competition to categorize seven million commodities into up to five thousand classes.
lx10077/ganpy
Pytorch implementation of generative adversary networks.
lx10077/LocalPower
Codes for LocalPower
lx10077/lx10077.github.io
Xiang Li's personal homepage
lx10077/optimpy
Home of various optimization algorithms.
lx10077/privacy
Library for training machine learning models with privacy for training data
lx10077/rlkit
Collection of reinforcement learning algorithms
lx10077/WatermarkFramework
Experiment codes for the paper https://arxiv.org/abs/2404.01245