gd-zhang
Ph.D. Student @ UofT Machine Learning Group. My Chinese name is Guodong Zhang (张国栋).
University of TorontoToronto
Pinned Repositories
ACKTR
Actor Critic using Kronecker-Factored Trust Region
Differentiable-AIS
Implementation for DAIS
Follow-the-Ridge
Minimax Optimization, Stackelberg Games, Generative Adversarial Networks
IQC-Game
Minimax Optimization, Monotone Variational Inequalities
NNG-Pytorch
noisy-K-FAC
Natural Gradient, Variational Inference
noisy-quadratic-model
Large-batch Training, Neural Network Optimization
VIME-NNG
Weight-Decay
Regularization, Neural Network Training Dynamics
Deformable-ConvNets
Deformable Convolutional Networks
gd-zhang's Repositories
gd-zhang/noisy-K-FAC
Natural Gradient, Variational Inference
gd-zhang/ACKTR
Actor Critic using Kronecker-Factored Trust Region
gd-zhang/Follow-the-Ridge
Minimax Optimization, Stackelberg Games, Generative Adversarial Networks
gd-zhang/Weight-Decay
Regularization, Neural Network Training Dynamics
gd-zhang/IQC-Game
Minimax Optimization, Monotone Variational Inequalities
gd-zhang/noisy-quadratic-model
Large-batch Training, Neural Network Optimization
gd-zhang/Differentiable-AIS
Implementation for DAIS
gd-zhang/NNG-Pytorch
gd-zhang/VIME-NNG
gd-zhang/A2C
A Clearer and Simpler Synchronous Advantage Actor Critic (A2C) Implementation in TensorFlow
gd-zhang/AdversarialVariationalBayes
This repository contains the code to reproduce the core results from the paper "Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks".
gd-zhang/backpack
BACKpropagation PACKage - A backpack for PyTorch that extends the backward pass of feedforward networks to compute quantities beyond the gradient
gd-zhang/baselines-1
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
gd-zhang/deq
[NeurIPS'19] Deep Equilibrium Models
gd-zhang/EigenDamage-Pytorch
Pytorch implementations of the paper "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis".
gd-zhang/GPflow
customized GPflow with simple tensorflow api
gd-zhang/GPflow-Slim
customized GPflow with simple Tensorflow API
gd-zhang/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
gd-zhang/jax-tutorial
A tutorial on JAX (https://github.com/google/jax/)
gd-zhang/kfac
An implementation of KFAC for TensorFlow
gd-zhang/neural-tangents
Linearizing Neural Network training.
gd-zhang/nngeometry
gd-zhang/NoisyNaturalGradient
TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC"
gd-zhang/over-parametrization
Computing various norms/measures on over-parametrized neural networks
gd-zhang/PyTorch-LBFGS
A PyTorch implementation of L-BFGS.
gd-zhang/rllab
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
gd-zhang/tensorflow-forward-ad
Forward-mode Automatic Differentiation for TensorFlow
gd-zhang/Tensorflow-Project-Template
A best practice for tensorflow project template architecture.
gd-zhang/torchdiffeq
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
gd-zhang/zhusuan
A Library for Bayesian Deep Learning, Generative Models, Based on Tensorflow