default search action
Roger B. Grosse
Roger Baker Grosse
Person information
- affiliation: University of Toronto, Department of Computer Science, ON, Canada
- affiliation (PhD 2014): Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [c66]Jin Peng Zhou, Yuhuai Wu, Qiyang Li, Roger Baker Grosse:
REFACTOR: Learning to Extract Theorems from Proofs. ICLR 2024 - [c65]Nathan H. Ng, Roger Baker Grosse, Marzyeh Ghassemi:
Measuring Stochastic Data Complexity with Boltzmann Influence Functions. ICML 2024 - [c64]Stephen Zhao, Rob Brekelmans, Alireza Makhzani, Roger Baker Grosse:
Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo. ICML 2024 - [i67]Jin Peng Zhou, Yuhuai Wu, Qiyang Li, Roger B. Grosse:
REFACTOR: Learning to Extract Theorems from Proofs. CoRR abs/2402.17032 (2024) - [i66]Stephen Zhao, Rob Brekelmans, Alireza Makhzani, Roger B. Grosse:
Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo. CoRR abs/2404.17546 (2024) - [i65]Sang Keun Choe, Hwijeen Ahn, Juhan Bae, Kewen Zhao, Minsoo Kang, Youngseog Chung, Adithya Pratapa, Willie Neiswanger, Emma Strubell, Teruko Mitamura, Jeff G. Schneider, Eduard H. Hovy, Roger B. Grosse, Eric P. Xing:
What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions. CoRR abs/2405.13954 (2024) - [i64]Nathan Ng, Roger B. Grosse, Marzyeh Ghassemi:
Measuring Stochastic Data Complexity with Boltzmann Influence Functions. CoRR abs/2406.02745 (2024) - [i63]Johannes Treutlein, Dami Choi, Jan Betley, Cem Anil, Samuel Marks, Roger Baker Grosse, Owain Evans:
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data. CoRR abs/2406.14546 (2024) - 2023
- [c63]Juhan Bae, Michael R. Zhang, Michael Ruan, Eric Wang, So Hasegawa, Jimmy Ba, Roger Baker Grosse:
Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve. ICLR 2023 - [c62]Nikita Dhawan, Sicong Huang, Juhan Bae, Roger Baker Grosse:
Efficient Parametric Approximations of Neural Network Function Space Distance. ICML 2023: 7795-7812 - [c61]Caspar Oesterheld, Johannes Treutlein, Roger B. Grosse, Vincent Conitzer, Jakob N. Foerster:
Similarity-based cooperative equilibrium. NeurIPS 2023 - [i62]Nikita Dhawan, Sicong Huang, Juhan Bae, Roger B. Grosse:
Efficient Parametric Approximations of Neural Network Function Space Distance. CoRR abs/2302.03519 (2023) - [i61]Rob Brekelmans, Sicong Huang, Marzyeh Ghassemi, Greg Ver Steeg, Roger B. Grosse, Alireza Makhzani:
Improving Mutual Information Estimation with Annealed and Energy-Based Bounds. CoRR abs/2303.06992 (2023) - [i60]Roger B. Grosse, Juhan Bae, Cem Anil, Nelson Elhage, Alex Tamkin, Amirhossein Tajdini, Benoit Steiner, Dustin Li, Esin Durmus, Ethan Perez, Evan Hubinger, Kamile Lukosiute, Karina Nguyen, Nicholas Joseph, Sam McCandlish, Jared Kaplan, Samuel R. Bowman:
Studying Large Language Model Generalization with Influence Functions. CoRR abs/2308.03296 (2023) - 2022
- [c60]Guodong Zhang, Yuanhao Wang, Laurent Lessard, Roger B. Grosse:
Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization. AISTATS 2022: 7659-7679 - [c59]Rob Brekelmans, Sicong Huang, Marzyeh Ghassemi, Greg Ver Steeg, Roger Baker Grosse, Alireza Makhzani:
Improving Mutual Information Estimation with Annealed and Energy-Based Bounds. ICLR 2022 - [c58]Paul Vicol, Jonathan P. Lorraine, Fabian Pedregosa, David Duvenaud, Roger B. Grosse:
On Implicit Bias in Overparameterized Bilevel Optimization. ICML 2022: 22234-22259 - [c57]Cem Anil, Ashwini Pokle, Kaiqu Liang, Johannes Treutlein, Yuhuai Wu, Shaojie Bai, J. Zico Kolter, Roger B. Grosse:
Path Independent Equilibrium Models Can Better Exploit Test-Time Computation. NeurIPS 2022 - [c56]Juhan Bae, Nathan Ng, Alston Lo, Marzyeh Ghassemi, Roger B. Grosse:
If Influence Functions are the Answer, Then What is the Question? NeurIPS 2022 - [c55]Juhan Bae, Paul Vicol, Jeff Z. HaoChen, Roger B. Grosse:
Amortized Proximal Optimization. NeurIPS 2022 - [c54]Stephen Zhao, Chris Lu, Roger B. Grosse, Jakob N. Foerster:
Proximal Learning With Opponent-Learning Awareness. NeurIPS 2022 - [i59]Juhan Bae, Paul Vicol, Jeff Z. HaoChen, Roger B. Grosse:
Amortized Proximal Optimization. CoRR abs/2203.00089 (2022) - [i58]Juhan Bae, Nathan Ng, Alston Lo, Marzyeh Ghassemi, Roger B. Grosse:
If Influence Functions are the Answer, Then What is the Question? CoRR abs/2209.05364 (2022) - [i57]Stephen Zhao, Chris Lu, Roger Baker Grosse, Jakob Nicolaus Foerster:
Proximal Learning With Opponent-Learning Awareness. CoRR abs/2210.10125 (2022) - [i56]Cem Anil, Ashwini Pokle, Kaiqu Liang, Johannes Treutlein, Yuhuai Wu, Shaojie Bai, Zico Kolter, Roger B. Grosse:
Path Independent Equilibrium Models Can Better Exploit Test-Time Computation. CoRR abs/2211.09961 (2022) - [i55]Caspar Oesterheld, Johannes Treutlein, Roger B. Grosse, Vincent Conitzer, Jakob N. Foerster:
Similarity-based Cooperation. CoRR abs/2211.14468 (2022) - [i54]Juhan Bae, Michael R. Zhang, Michael Ruan, Eric Wang, So Hasegawa, Jimmy Ba, Roger B. Grosse:
Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve. CoRR abs/2212.03905 (2022) - [i53]Paul Vicol, Jonathan Lorraine, Fabian Pedregosa, David Duvenaud, Roger B. Grosse:
On Implicit Bias in Overparameterized Bilevel Optimization. CoRR abs/2212.14032 (2022) - 2021
- [j2]Guodong Zhang, Xuchan Bao, Laurent Lessard, Roger B. Grosse:
A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints. J. Mach. Learn. Res. 22: 103:1-103:39 (2021) - [c53]Pashootan Vaezipoor, Gil Lederman, Yuhuai Wu, Chris J. Maddison, Roger B. Grosse, Sanjit A. Seshia, Fahiem Bacchus:
Learning Branching Heuristics for Propositional Model Counting. AAAI 2021: 12427-12435 - [c52]Jens Behrmann, Paul Vicol, Kuan-Chieh Wang, Roger B. Grosse, Jörn-Henrik Jacobsen:
Understanding and Mitigating Exploding Inverses in Invertible Neural Networks. AISTATS 2021: 1792-1800 - [c51]Chaoqi Wang, Shengyang Sun, Roger B. Grosse:
Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations? AISTATS 2021: 2476-2484 - [c50]Shun-ichi Amari, Jimmy Ba, Roger Baker Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu:
When does preconditioning help or hurt generalization? ICLR 2021 - [c49]Yuhuai Wu, Albert Q. Jiang, Jimmy Ba, Roger Baker Grosse:
INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving. ICLR 2021 - [c48]James Lucas, Juhan Bae, Michael R. Zhang, Stanislav Fort, Richard S. Zemel, Roger B. Grosse:
On Monotonic Linear Interpolation of Neural Network Parameters. ICML 2021: 7168-7179 - [c47]Shengyang Sun, Jiaxin Shi, Andrew Gordon Wilson, Roger B. Grosse:
Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition. ICML 2021: 9955-9965 - [c46]Yuhuai Wu, Markus N. Rabe, Wenda Li, Jimmy Ba, Roger B. Grosse, Christian Szegedy:
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning. ICML 2021: 11251-11262 - [c45]Guodong Zhang, Kyle Hsu, Jianing Li, Chelsea Finn, Roger B. Grosse:
Differentiable Annealed Importance Sampling and the Perils of Gradient Noise. NeurIPS 2021: 19398-19410 - [i52]Yuhuai Wu, Markus N. Rabe, Wenda Li, Jimmy Ba, Roger B. Grosse, Christian Szegedy:
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning. CoRR abs/2101.06223 (2021) - [i51]Guodong Zhang, Yuanhao Wang, Laurent Lessard, Roger B. Grosse:
Don't Fix What ain't Broke: Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization. CoRR abs/2102.09468 (2021) - [i50]James Lucas, Juhan Bae, Michael R. Zhang, Stanislav Fort, Richard S. Zemel, Roger B. Grosse:
Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes. CoRR abs/2104.11044 (2021) - [i49]Shengyang Sun, Jiaxin Shi, Andrew Gordon Wilson, Roger B. Grosse:
Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition. CoRR abs/2106.05992 (2021) - [i48]Guodong Zhang, Kyle Hsu, Jianing Li, Chelsea Finn, Roger B. Grosse:
Differentiable Annealed Importance Sampling and the Perils of Gradient Noise. CoRR abs/2107.10211 (2021) - [i47]Cem Anil, Guodong Zhang, Yuhuai Wu, Roger B. Grosse:
Learning to Give Checkable Answers with Prover-Verifier Games. CoRR abs/2108.12099 (2021) - 2020
- [c44]Chaoqi Wang, Guodong Zhang, Roger B. Grosse:
Picking Winning Tickets Before Training by Preserving Gradient Flow. ICLR 2020 - [c43]Sicong Huang, Alireza Makhzani, Yanshuai Cao, Roger B. Grosse:
Evaluating Lossy Compression Rates of Deep Generative Models. ICML 2020: 4444-4454 - [c42]Juhan Bae, Roger B. Grosse:
Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians. NeurIPS 2020 - [c41]Xuchan Bao, James Lucas, Sushant Sachdeva, Roger B. Grosse:
Regularized linear autoencoders recover the principal components, eventually. NeurIPS 2020 - [i46]Chaoqi Wang, Guodong Zhang, Roger Baker Grosse:
Picking Winning Tickets Before Training by Preserving Gradient Flow. CoRR abs/2002.07376 (2020) - [i45]Jens Behrmann, Paul Vicol, Kuan-Chieh Wang, Roger B. Grosse, Jörn-Henrik Jacobsen:
Understanding and mitigating exploding inverses in invertible neural networks. CoRR abs/2006.09347 (2020) - [i44]Shun-ichi Amari, Jimmy Ba, Roger B. Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu:
When Does Preconditioning Help or Hurt Generalization? CoRR abs/2006.10732 (2020) - [i43]Yuhuai Wu, Albert Q. Jiang, Jimmy Ba, Roger B. Grosse:
INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving. CoRR abs/2007.02924 (2020) - [i42]Pashootan Vaezipoor, Gil Lederman, Yuhuai Wu, Chris J. Maddison, Roger B. Grosse, Edward A. Lee, Sanjit A. Seshia, Fahiem Bacchus:
Learning Branching Heuristics for Propositional Model Counting. CoRR abs/2007.03204 (2020) - [i41]Yuhuai Wu, Honghua Dong, Roger B. Grosse, Jimmy Ba:
The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning. CoRR abs/2007.04212 (2020) - [i40]Xuchan Bao, James Lucas, Sushant Sachdeva, Roger B. Grosse:
Regularized linear autoencoders recover the principal components, eventually. CoRR abs/2007.06731 (2020) - [i39]Sicong Huang, Alireza Makhzani, Yanshuai Cao, Roger B. Grosse:
Evaluating Lossy Compression Rates of Deep Generative Models. CoRR abs/2008.06653 (2020) - [i38]Guodong Zhang, Xuchan Bao, Laurent Lessard, Roger B. Grosse:
A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints. CoRR abs/2009.11359 (2020) - [i37]Juhan Bae, Roger B. Grosse:
Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians. CoRR abs/2010.13514 (2020) - [i36]Chaoqi Wang, Shengyang Sun, Roger B. Grosse:
Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations? CoRR abs/2011.03178 (2020)
2010 – 2019
- 2019
- [c40]Sicong Huang, Qiyang Li, Cem Anil, Xuchan Bao, Sageev Oore, Roger B. Grosse:
TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer. ICLR (Poster) 2019 - [c39]James Lucas, Shengyang Sun, Richard S. Zemel, Roger B. Grosse:
Aggregated Momentum: Stability Through Passive Damping. ICLR (Poster) 2019 - [c38]James Lucas, George Tucker, Roger B. Grosse, Mohammad Norouzi:
Understanding Posterior Collapse in Generative Latent Variable Models. DGS@ICLR 2019 - [c37]Matthew MacKay, Paul Vicol, Jonathan Lorraine, David Duvenaud, Roger B. Grosse:
Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions. ICLR (Poster) 2019 - [c36]Shengyang Sun, Guodong Zhang, Jiaxin Shi, Roger B. Grosse:
Functional variational Bayesian Neural Networks. ICLR (Poster) 2019 - [c35]Guodong Zhang, Chaoqi Wang, Bowen Xu, Roger B. Grosse:
Three Mechanisms of Weight Decay Regularization. ICLR (Poster) 2019 - [c34]Cem Anil, James Lucas, Roger B. Grosse:
Sorting Out Lipschitz Function Approximation. ICML 2019: 291-301 - [c33]Chaoqi Wang, Roger B. Grosse, Sanja Fidler, Guodong Zhang:
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis. ICML 2019: 6566-6575 - [c32]Guodong Zhang, James Martens, Roger B. Grosse:
Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks. NeurIPS 2019: 8080-8091 - [c31]Guodong Zhang, Lala Li, Zachary Nado, James Martens, Sushant Sachdeva, George E. Dahl, Christopher J. Shallue, Roger B. Grosse:
Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model. NeurIPS 2019: 8194-8205 - [c30]James Lucas, George Tucker, Roger B. Grosse, Mohammad Norouzi:
Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse. NeurIPS 2019: 9403-9413 - [c29]Qiyang Li, Saminul Haque, Cem Anil, James Lucas, Roger B. Grosse, Jörn-Henrik Jacobsen:
Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks. NeurIPS 2019: 15364-15376 - [i35]Matthew MacKay, Paul Vicol, Jonathan Lorraine, David Duvenaud, Roger B. Grosse:
Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions. CoRR abs/1903.03088 (2019) - [i34]Shengyang Sun, Guodong Zhang, Jiaxin Shi, Roger B. Grosse:
Functional Variational Bayesian Neural Networks. CoRR abs/1903.05779 (2019) - [i33]Chaoqi Wang, Roger B. Grosse, Sanja Fidler, Guodong Zhang:
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis. CoRR abs/1905.05934 (2019) - [i32]Guodong Zhang, James Martens, Roger B. Grosse:
Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks. CoRR abs/1905.10961 (2019) - [i31]Guodong Zhang, Lala Li, Zachary Nado, James Martens, Sushant Sachdeva, George E. Dahl, Christopher J. Shallue, Roger B. Grosse:
Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model. CoRR abs/1907.04164 (2019) - [i30]Qiyang Li, Saminul Haque, Cem Anil, James Lucas, Roger B. Grosse, Jörn-Henrik Jacobsen:
Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks. CoRR abs/1911.00937 (2019) - [i29]James Lucas, George Tucker, Roger B. Grosse, Mohammad Norouzi:
Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse. CoRR abs/1911.02469 (2019) - 2018
- [c28]Tian Qi Chen, Xuechen Li, Roger B. Grosse, David Duvenaud:
Isolating Sources of Disentanglement in Variational Autoencoders. ICLR (Workshop) 2018 - [c27]Zachary Nado, Jasper Snoek, Roger B. Grosse, David Duvenaud, Bowen Xu, James Martens:
Stochastic Gradient Langevin dynamics that Exploit Neural Network Structure. ICLR (Workshop) 2018 - [c26]Yeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran, Roger B. Grosse:
Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches. ICLR (Poster) 2018 - [c25]Yuhuai Wu, Mengye Ren, Renjie Liao, Roger B. Grosse:
Understanding Short-Horizon Bias in Stochastic Meta-Optimization. ICLR (Poster) 2018 - [c24]Shengyang Sun, Guodong Zhang, Chaoqi Wang, Wenyuan Zeng, Jiaman Li, Roger B. Grosse:
Differentiable Compositional Kernel Learning for Gaussian Processes. ICML 2018: 4835-4844 - [c23]Kuan-Chieh Wang, Paul Vicol, James Lucas, Li Gu, Roger B. Grosse, Richard S. Zemel:
Adversarial Distillation of Bayesian Neural Network Posteriors. ICML 2018: 5177-5186 - [c22]Guodong Zhang, Shengyang Sun, David Duvenaud, Roger B. Grosse:
Noisy Natural Gradient as Variational Inference. ICML 2018: 5847-5856 - [c21]Tian Qi Chen, Xuechen Li, Roger B. Grosse, David Duvenaud:
Isolating Sources of Disentanglement in Variational Autoencoders. NeurIPS 2018: 2615-2625 - [c20]Matthew MacKay, Paul Vicol, Jimmy Ba, Roger B. Grosse:
Reversible Recurrent Neural Networks. NeurIPS 2018: 9043-9054 - [i28]Tian Qi Chen, Xuechen Li, Roger B. Grosse, David Duvenaud:
Isolating Sources of Disentanglement in Variational Autoencoders. CoRR abs/1802.04942 (2018) - [i27]Yuhuai Wu, Mengye Ren, Renjie Liao, Roger B. Grosse:
Understanding Short-Horizon Bias in Stochastic Meta-Optimization. CoRR abs/1803.02021 (2018) - [i26]Yeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran, Roger B. Grosse:
Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches. CoRR abs/1803.04386 (2018) - [i25]James Lucas, Richard S. Zemel, Roger B. Grosse:
Aggregated Momentum: Stability Through Passive Damping. CoRR abs/1804.00325 (2018) - [i24]Shengyang Sun, Guodong Zhang, Chaoqi Wang, Wenyuan Zeng, Jiaman Li, Roger B. Grosse:
Differentiable Compositional Kernel Learning for Gaussian Processes. CoRR abs/1806.04326 (2018) - [i23]Kuan-Chieh Wang, Paul Vicol, James Lucas, Li Gu, Roger B. Grosse, Richard S. Zemel:
Adversarial Distillation of Bayesian Neural Network Posteriors. CoRR abs/1806.10317 (2018) - [i22]Kevin Luk, Roger B. Grosse:
A Coordinate-Free Construction of Scalable Natural Gradient. CoRR abs/1808.10340 (2018) - [i21]Matthew MacKay, Paul Vicol, Jimmy Ba, Roger B. Grosse:
Reversible Recurrent Neural Networks. CoRR abs/1810.10999 (2018) - [i20]Guodong Zhang, Chaoqi Wang, Bowen Xu, Roger B. Grosse:
Three Mechanisms of Weight Decay Regularization. CoRR abs/1810.12281 (2018) - [i19]Cem Anil, James Lucas, Roger B. Grosse:
Sorting out Lipschitz function approximation. CoRR abs/1811.05381 (2018) - [i18]Sicong Huang, Qiyang Li, Cem Anil, Xuchan Bao, Sageev Oore, Roger B. Grosse:
TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer. CoRR abs/1811.09620 (2018) - [i17]Juhan Bae, Guodong Zhang, Roger B. Grosse:
Eigenvalue Corrected Noisy Natural Gradient. CoRR abs/1811.12565 (2018) - 2017
- [c19]Jacob R. Gardner, Chuan Guo, Kilian Q. Weinberger, Roman Garnett, Roger B. Grosse:
Discovering and Exploiting Additive Structure for Bayesian Optimization. AISTATS 2017: 1311-1319 - [c18]Jimmy Ba, Roger B. Grosse, James Martens:
Distributed Second-Order Optimization using Kronecker-Factored Approximations. ICLR (Poster) 2017 - [c17]Yuhuai Wu, Yuri Burda, Ruslan Salakhutdinov, Roger B. Grosse:
On the Quantitative Analysis of Decoder-Based Generative Models. ICLR (Poster) 2017 - [c16]Aidan N. Gomez, Mengye Ren, Raquel Urtasun, Roger B. Grosse:
The Reversible Residual Network: Backpropagation Without Storing Activations. NIPS 2017: 2214-2224 - [c15]Yuhuai Wu, Elman Mansimov, Roger B. Grosse, Shun Liao, Jimmy Ba:
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation. NIPS 2017: 5279-5288 - [i16]Aidan N. Gomez, Mengye Ren, Raquel Urtasun, Roger B. Grosse:
The Reversible Residual Network: Backpropagation Without Storing Activations. CoRR abs/1707.04585 (2017) - [i15]Yuhuai Wu, Elman Mansimov, Shun Liao, Roger B. Grosse, Jimmy Ba:
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation. CoRR abs/1708.05144 (2017) - [i14]Guodong Zhang, Shengyang Sun, David Duvenaud, Roger B. Grosse:
Noisy Natural Gradient as Variational Inference. CoRR abs/1712.02390 (2017) - 2016
- [c14]Roger B. Grosse, James Martens:
A Kronecker-factored approximate Fisher matrix for convolution layers. ICML 2016: 573-582 - [c13]Roger B. Grosse, Siddharth Ancha, Daniel M. Roy:
Measuring the reliability of MCMC inference with bidirectional Monte Carlo. NIPS 2016: 2451-2459 - [c12]Yuri Burda, Roger B. Grosse, Ruslan Salakhutdinov:
Importance Weighted Autoencoders. ICLR (Poster) 2016 - [i13]Roger B. Grosse, James Martens:
A Kronecker-factored approximate Fisher matrix for convolution layers. CoRR abs/1602.01407 (2016) - [i12]Roger B. Grosse, Siddharth Ancha, Daniel M. Roy:
Measuring the reliability of MCMC inference with bidirectional Monte Carlo. CoRR abs/1606.02275 (2016) - [i11]Yuhuai Wu, Yuri Burda, Ruslan Salakhutdinov, Roger B. Grosse:
On the Quantitative Analysis of Decoder-Based Generative Models. CoRR abs/1611.04273 (2016) - 2015
- [c11]Yuri Burda, Roger B. Grosse, Ruslan Salakhutdinov:
Accurate and conservative estimates of MRF log-likelihood using reverse annealing. AISTATS 2015 - [c10]Roger B. Grosse, Ruslan Salakhutdinov:
Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix. ICML 2015: 2304-2313 - [c9]James Martens, Roger B. Grosse:
Optimizing Neural Networks with Kronecker-factored Approximate Curvature. ICML 2015: 2408-2417 - [c8]Jimmy Ba, Ruslan Salakhutdinov, Roger B. Grosse, Brendan J. Frey:
Learning Wake-Sleep Recurrent Attention Models. NIPS 2015: 2593-2601 - [i10]James Martens, Roger B. Grosse:
Optimizing Neural Networks with Kronecker-factored Approximate Curvature. CoRR abs/1503.05671 (2015) - [i9]Beate Franke, Jean-François Plante, Ribana Roscher, Annie Lee, Cathal Smyth, Armin Hatefi, Fuqi Chen, Einat Gil, Alexander G. Schwing, Alessandro Selvitella, Michael M. Hoffman, Roger B. Grosse, Dieter Hendricks, Nancy Reid:
Statistical Inference, Learning and Models in Big Data. CoRR abs/1509.02900 (2015) - [i8]Jimmy Ba, Roger B. Grosse, Ruslan Salakhutdinov, Brendan J. Frey:
Learning Wake-Sleep Recurrent Attention Models. CoRR abs/1509.06812 (2015) - [i7]Roger B. Grosse, Zoubin Ghahramani, Ryan P. Adams:
Sandwiching the marginal likelihood using bidirectional Monte Carlo. CoRR abs/1511.02543 (2015) - 2014
- [b1]Roger Baker Grosse:
Model selection in compositional spaces. Massachusetts Institute of Technology, Cambridge, MA, USA, 2014 - [c7]James Robert Lloyd, David Duvenaud, Roger B. Grosse, Joshua B. Tenenbaum, Zoubin Ghahramani:
Automatic Construction and Natural-Language Description of Nonparametric Regression Models. AAAI 2014: 1242-1250 - [i6]James Robert Lloyd, David Duvenaud, Roger B. Grosse, Joshua B. Tenenbaum, Zoubin Ghahramani:
Automatic Construction and Natural-Language Description of Nonparametric Regression Models. CoRR abs/1402.4304 (2014) - [i5]Roger B. Grosse, David Kristjanson Duvenaud:
Testing MCMC code. CoRR abs/1412.5218 (2014) - [i4]Yuri Burda, Roger B. Grosse, Ruslan Salakhutdinov:
Accurate and Conservative Estimates of MRF Log-likelihood using Reverse Annealing. CoRR abs/1412.8566 (2014) - 2013
- [c6]