Roger B. Grosse

发表

Sorting out Lipschitz function approximation

Cem Anil, James Lucas, Roger B. Grosse, 2018, ICML.

Noisy Natural Gradient as Variational Inference

Guodong Zhang, Roger B. Grosse, Shengyang Sun, 2017, ICML.

Adversarial Distillation of Bayesian Neural Network Posteriors pdf

Richard S. Zemel, James Lucas, Roger B. Grosse, 2018, ICML.

Isolating Sources of Disentanglement in Variational Autoencoders

Roger B. Grosse, David Duvenaud, Xuechen Li, 2018, NeurIPS.

Stochastic Gradient Langevin dynamics that Exploit Neural Network Structure

Jasper Snoek, Roger B. Grosse, David Duvenaud, 2018, ICLR.

Aggregated Momentum: Stability Through Passive Damping pdf

Richard S. Zemel, James Lucas, Roger B. Grosse, 2018, ICLR.

Learning Wake-Sleep Recurrent Attention Models

Brendan J. Frey, Ruslan Salakhutdinov, Roger B. Grosse, 2015, NIPS.

Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches pdf

Dustin Tran, Roger B. Grosse, Paul Vicol, 2018, ICLR.

Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix

Ruslan Salakhutdinov, Roger B. Grosse, R. Salakhutdinov, 2015, ICML.

Optimizing Neural Networks with Kronecker-factored Approximate Curvature

Roger B. Grosse, James Martens, James Martens, 2015, ICML.

Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

Honglak Lee, Andrew Y. Ng, Roger B. Grosse, 2009, ICML '09.

Sandwiching the marginal likelihood using bidirectional Monte Carlo pdf

Ryan P. Adams, Zoubin Ghahramani, Roger B. Grosse, 2015, ArXiv.

Reversible Recurrent Neural Networks

Roger B. Grosse, Paul Vicol, Jimmy Ba, 2018, NeurIPS.

A Kronecker-factored approximate Fisher matrix for convolution layers

Roger B. Grosse, James Martens, James Martens, 2016, ICML.

Exploiting compositionality to explore a large space of model structures

Joshua B. Tenenbaum, William T. Freeman, Ruslan Salakhutdinov, 2012, UAI.

Importance Weighted Autoencoders pdf

Ruslan Salakhutdinov, Roger B. Grosse, Yuri Burda, 2015, ICLR.

Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions pdf

Roger B. Grosse, David Duvenaud, Paul Vicol, 2019, ICLR.

Measuring the reliability of MCMC inference with bidirectional Monte Carlo

Roger B. Grosse, Daniel M. Roy, Siddharth Ancha, 2016, NIPS.

Eigenvalue Corrected Noisy Natural Gradient pdf

Guodong Zhang, Roger B. Grosse, Juhan Bae, 2018, ArXiv.

Structure Discovery in Nonparametric Regression through Compositional Kernel Search pdf

Joshua B. Tenenbaum, Zoubin Ghahramani, Roger B. Grosse, 2013, ICML.

Ground truth dataset and baseline evaluations for intrinsic image algorithms

Edward H. Adelson, William T. Freeman, Roger B. Grosse, 2009, 2009 IEEE 12th International Conference on Computer Vision.

Annealing between distributions by averaging moments

Ruslan Salakhutdinov, Roger B. Grosse, Chris J. Maddison, 2013, NIPS.

Understanding Short-Horizon Bias in Stochastic Meta-Optimization pdf

Renjie Liao, Roger B. Grosse, Mengye Ren, 2018, ICLR.

Discovering and Exploiting Additive Structure for Bayesian Optimization

Roman Garnett, Kilian Q. Weinberger, Roger B. Grosse, 2017, AISTATS.

Functional Variational Bayesian Neural Networks pdf

Guodong Zhang, Roger B. Grosse, Shengyang Sun, 2019, ICLR.

Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

Elman Mansimov, Roger B. Grosse, Jimmy Ba, 2017, NIPS.

Distributed Second-Order Optimization using Kronecker-Factored Approximations

Roger B. Grosse, Jimmy Ba, James Martens, 2016, ICLR.

TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer pdf

Cem Anil, Roger B. Grosse, Sageev Oore, 2018, ICLR.

Statistical Inference, Learning and Models in Big Data pdf

Ribana Roscher, Alexander G. Schwing, Roger B. Grosse, 2015, ArXiv.

Accurate and conservative estimates of MRF log-likelihood using reverse annealing pdf

Ruslan Salakhutdinov, Roger B. Grosse, Yuri Burda, 2014, AISTATS.

On the Quantitative Analysis of Decoder-Based Generative Models pdf

Ruslan Salakhutdinov, Roger B. Grosse, Yuhuai Wu, 2016, ICLR.

A Coordinate-Free Construction of Scalable Natural Gradient pdf

Roger B. Grosse, Kevin Luk, 2018, ArXiv.

Testing MCMC code pdf

Roger B. Grosse, David Kristjanson Duvenaud, 2014, ArXiv.

The Reversible Residual Network: Backpropagation Without Storing Activations

Raquel Urtasun, Roger B. Grosse, Mengye Ren, 2017, NIPS.

Unsupervised learning of hierarchical representations with convolutional deep belief networks

Honglak Lee, Andrew Y. Ng, Roger B. Grosse, 2011, Commun. ACM.

Automatic Construction and Natural-Language Description of Nonparametric Regression Models

Joshua B. Tenenbaum, Zoubin Ghahramani, Roger B. Grosse, 2014, AAAI.

Three Mechanisms of Weight Decay Regularization pdf

Guodong Zhang, Roger B. Grosse, Bowen Xu, 2018, ICLR.

Differentiable Compositional Kernel Learning for Gaussian Processes

Guodong Zhang, Roger B. Grosse, Shengyang Sun, 2018, ICML.

On Monotonic Linear Interpolation of Neural Network Parameters

Richard S. Zemel, Roger B. Grosse, Stanislav Fort, 2021, ICML.

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning pdf

Roger B. Grosse, Christian Szegedy, Markus N. Rabe, 2021, ICML.

Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model

Guodong Zhang, Roger B. Grosse, Sushant Sachdeva, 2019, NeurIPS.

When Does Preconditioning Help or Hurt Generalization? pdf

Taiji Suzuki, Roger B. Grosse, Ji Xu, 2020, ICLR.

Amortized Proximal Optimization

Roger B. Grosse, Jeff Z. HaoChen, Paul Vicol, 2022, NeurIPS.

SOLATING S OURCES OF D ISENTANGLEMENT IN V ARIATIONAL A UTOENCODERS

Roger B. Grosse, Xuechen Li, D. Duvenaud, 2018 .

Understanding Short-Horizon Bias in Stochastic Meta-Optimization

Roger B. Grosse, Yuhuai Wu, Mengye Ren, 2018, ICLR.

Existing approaches to enforce Lipschitz constraints fall into two categories : regularization and architectural constraints . Regularization approaches

Roger B. Grosse, Cem Anil, James Lucas, 2019 .

Implicit Regularization in Overparameterized Bilevel Optimization

Roger B. Grosse, D. Duvenaud, Paul Vicol, 2021 .

Three Mechanisms of Weight Decay Regularization

Roger B. Grosse, Guodong Zhang, Chaoqi Wang, 2018, ICLR.

Picking Winning Tickets Before Training by Preserving Gradient Flow

Roger B. Grosse, Guodong Zhang, Chaoqi Wang, 2020, ICLR.

On the Invertibility of Invertible Neural Networks

Roger B. Grosse, Jörn-Henrik Jacobsen, Paul Vicol, 2019 .

Regularized linear autoencoders recover the principal components, eventually

Roger B. Grosse, James Lucas, Sushant Sachdeva, 2020, NeurIPS.

Second-order Optimization for Deep Reinforcement Learning using Kronecker-factored Approximation

Elman Mansimov, Roger B. Grosse, Jimmy Ba, 2017, NIPS 2017.

Shift-Invariance Sparse Coding for Audio Classification

Roger B. Grosse, A. Ng, R. Raina, 2007, UAI.

A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints pdf

Guodong Zhang, Roger B. Grosse, Laurent Lessard, 2020, J. Mach. Learn. Res..

Neural Theorem Proving on Inequality Problems

Roger B. Grosse, Jimmy Ba, Yuhuai Wu, 2020 .