429 citations · 1.2k across the 20 of their papers we have counts for
20 papers
Recovering Hidden Reward in Diffusion-Based Policies
Yanbiao Ji, Qiuchang Li, Yuting Hu +7
This paper introduces EnergyFlow, a framework that unifies generative action modeling with inverse reinforcement learning by parameterizing a scalar energy function whose gradient…
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation
Bobby He, James Martens, Guodong Zhang +4
Skip connections and normalisation layers form two standard architectural components that are ubiquitous for the training of Deep Neural Networks (DNNs), but whose precise roles ar…
Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers
Guodong Zhang, Aleksandar Botev, James Martens
Training very deep neural networks is still an extremely challenging task. The common solution is to use shortcut connections and normalization layers, which are both crucial ingre…
Learning to Give Checkable Answers with Prover-Verifier Games
Cem Anil, Guodong Zhang, Yuhuai Wu +1
Our ability to know when to trust the decisions made by machine learning systems has not kept up with the staggering improvements in their performance, limiting their applicability…
Differentiable Annealed Importance Sampling and the Perils of Gradient Noise
Guodong Zhang, Kyle Hsu, Jianing Li +2
Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation, but are not fully differentiable due to the use of Metropol…
Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization
Guodong Zhang, Yuanhao Wang, Laurent Lessard +1
Smooth minimax games often proceed by simultaneous or alternating gradient updates. Although algorithms with alternating updates are commonly used in practice, the majority of exis…
A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints
Guodong Zhang, Xuchan Bao, Laurent Lessard +1
The theory of integral quadratic constraints (IQCs) allows the certification of exponential convergence of interconnected systems containing nonlinear or uncertain elements. In thi…
On the Suboptimality of Negative Momentum for Minimax Optimization
Guodong Zhang, Yuanhao Wang
Smooth game optimization has recently attracted great interest in machine learning as it generalizes the single-objective optimization paradigm. However, game dynamics is more comp…
Picking Winning Tickets Before Training by Preserving Gradient Flow
Chaoqi Wang, Guodong Zhang, Roger Grosse
Overparameterization has been shown to benefit both the optimization and generalization of neural networks, but large networks are resource hungry at both training and test time. N…
On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach
Yuanhao Wang, Guodong Zhang, Jimmy Ba
Many tasks in modern machine learning can be formulated as finding equilibria in \emph{sequential} games. In particular, two-player zero-sum sequential games, also known as minimax…
Benchmarking Model-Based Reinforcement Learning
Tingwu Wang, Xuchan Bao, Ignasi Clavera +7
Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL h…
Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model
Guodong Zhang, Lala Li, Zachary Nado +5
Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we…
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis
Chaoqi Wang, Roger Grosse, Sanja Fidler +1
Reducing the test time resource requirements of a neural network while preserving test accuracy is crucial for running inference on resource-constrained devices. To achieve this go…
Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks
Guodong Zhang, James Martens, Roger Grosse
Natural gradient descent has proven effective at mitigating the effects of pathological curvature in neural network optimization, but little is known theoretically about its conver…
Functional Variational Bayesian Neural Networks
Shengyang Sun, Guodong Zhang, Jiaxin Shi +1
Variational Bayesian neural networks (BNNs) perform variational inference over weights, but it is difficult to specify meaningful priors and approximate posteriors in a high-dimens…
Eigenvalue Corrected Noisy Natural Gradient
Juhan Bae, Guodong Zhang, Roger Grosse
Variational Bayesian neural networks combine the flexibility of deep learning with Bayesian uncertainty estimation. However, inference procedures for flexible variational posterior…
Three Mechanisms of Weight Decay Regularization
Guodong Zhang, Chaoqi Wang, Bowen Xu +1
Weight decay is one of the standard tricks in the neural network toolbox, but the reasons for its regularization effect are poorly understood, and recent results have cast doubt on…
Differentiable Compositional Kernel Learning for Gaussian Processes
Shengyang Sun, Guodong Zhang, Chaoqi Wang +3
The generalization properties of Gaussian processes depend heavily on the choice of kernel, and this choice remains a dark art. We present the Neural Kernel Network (NKN), a flexib…
Noisy Natural Gradient as Variational Inference
Guodong Zhang, Shengyang Sun, David Duvenaud +1
Variational Bayesian neural nets combine the flexibility of deep learning with Bayesian uncertainty estimation. Unfortunately, there is a tradeoff between cheap but simple variatio…
Deformable Convolutional Networks
Jifeng Dai, Haozhi Qi, Yuwen Xiong +4
Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we intro…