Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
20091.5k citationsRoger Grosse, Andrew Y. Ng et al.profile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
This map shows the geographic impact of Roger Grosse's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Roger Grosse with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Roger Grosse more than expected).
This network shows the impact of papers produced by Roger Grosse. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Roger Grosse. The network helps show where Roger Grosse may publish in the future.
Co-authorship network of co-authors of Roger Grosse
This figure shows the co-authorship network connecting the top 25 collaborators of Roger Grosse.
A scholar is included among the top collaborators of Roger Grosse based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Roger Grosse. Roger Grosse is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Wu, Yuhuai, et al.. (2021). INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving. arXiv (Cornell University).
2.
Bao, Xuchan, James Lucas, Sushant Sachdeva, & Roger Grosse. (2020). Regularized linear autoencoders recover the principal components, eventually. Neural Information Processing Systems. 33. 6971–6981.1 indexed citations
3.
Lucas, James, George Tucker, Roger Grosse, & Mohammad Norouzi. (2019). Understanding Posterior Collapse in Generative Latent Variable Models. International Conference on Learning Representations.40 indexed citations
4.
Zhang, Guodong, James Martens, & Roger Grosse. (2019). Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks. arXiv (Cornell University). 32. 8080–8091.5 indexed citations
5.
Li, Xuechen, et al.. (2018). Isolating Sources of Disentanglement in Variational Autoencoders.. International Conference on Learning Representations.15 indexed citations
6.
Nado, Zachary, et al.. (2018). STOCHASTIC GRADIENT LANGEVIN DYNAMICS THAT EXPLOIT NEURAL NETWORK STRUCTURE. International Conference on Learning Representations.4 indexed citations
7.
Wang, Kuan-Chieh, Paul Vicol, James Lucas, et al.. (2018). Adversarial Distillation of Bayesian Neural Network Posteriors. International Conference on Machine Learning. 5190–5199.3 indexed citations
8.
Sun, Shengyang, Guodong Zhang, Chaoqi Wang, et al.. (2018). Differentiable Compositional Kernel Learning for Gaussian Processes. International Conference on Machine Learning. 4828–4837.7 indexed citations
9.
Wen, Yeming, Paul Vicol, Jimmy Ba, Dustin Tran, & Roger Grosse. (2018). Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches. arXiv (Cornell University).6 indexed citations
10.
Ba, Jimmy, Roger Grosse, & James Martens. (2017). Distributed Second-Order Optimization using Kronecker-Factored Approximations. International Conference on Learning Representations.24 indexed citations
11.
Gardner, Jacob R., Chuan Guo, Kilian Q. Weinberger, Roman Garnett, & Roger Grosse. (2017). Discovering and Exploiting Additive Structure for Bayesian Optimization. International Conference on Artificial Intelligence and Statistics. 1311–1319.29 indexed citations
12.
Wu, Yuhuai, Elman Mansimov, Roger Grosse, S. Matthew Liao, & Jimmy Ba. (2017). Second-order Optimization for Deep Reinforcement Learning using Kronecker-factored Approximation. Neural Information Processing Systems. 5285–5294.3 indexed citations
13.
Gomez, Aidan N., Mengye Ren, Raquel Urtasun, & Roger Grosse. (2017). The Reversible Residual Network: Backpropagation Without Storing Activations. arXiv (Cornell University). 30. 2214–2224.66 indexed citations
14.
Wu, Yuhuai, Elman Mansimov, Roger Grosse, S. Matthew Liao, & Jimmy Ba. (2017). Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation. Neural Information Processing Systems. 30. 5279–5288.27 indexed citations
15.
Grosse, Roger, et al.. (2016). Measuring the reliability of MCMC inference with bidirectional Monte Carlo. Neural Information Processing Systems. 29. 2451–2459.4 indexed citations
16.
Burda, Yuri, Roger Grosse, & Ruslan Salakhutdinov. (2015). {Accurate and conservative estimates of MRF log-likelihood using reverse annealing}. International Conference on Artificial Intelligence and Statistics. 102–110.12 indexed citations
17.
Grosse, Roger, et al.. (2015). Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix. International Conference on Machine Learning. 2304–2313.19 indexed citations
18.
Martens, James & Roger Grosse. (2015). Optimizing Neural Networks with Kronecker-factored Approximate Curvature. International Conference on Machine Learning. 2408–2417.29 indexed citations
19.
Grosse, Roger, et al.. (2007). Shift-invariant sparse coding for audio classification. Uncertainty in Artificial Intelligence. 149–158.116 indexed citations
20.
Kiefer, Max & Roger Grosse. (1984). Why utility customers don't pay their bills.1 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.