---
title: "Roger Grosse · University of Toronto — author profile and papers"
description: "Roger Grosse, University of Toronto: 3 papers on Elamur Research (2020–2023), h-index 31 — affiliations, topics, co-authors and who cites…"
canonical: "https://research.elamur.ai/free/en/authors/roger-grosse/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/roger-grosse/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Roger Grosse

# Roger Grosse

Roger Grosse has 3 papers in our library, in 2020–2023, most of them on [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/); often with [Jimmy Lei Ba](https://md.research.elamur.ai/free/en/authors/jimmy-lei-ba/), [Yuhuai Wu](https://md.research.elamur.ai/free/en/authors/yuhuai-wu/), [Albert Q. Jiang](https://md.research.elamur.ai/free/en/authors/albert-q-jiang/).

3 papers in our library · 2020–2023

[OpenAlex](https://openalex.org/A5067036768) · [**h-index 31**](https://openalex.org/authors/A5067036768) · [99 works](https://openalex.org/works?filter=author.id:A5067036768) · [7,450 citations](https://openalex.org/works?filter=author.id:A5067036768&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/roger-grosse/#papers) · [🔗 Cited 964 times in our library](https://md.research.elamur.ai/free/en/authors/roger-grosse/cited-by/) · [22 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #6931](https://md.research.elamur.ai/free/en/paper-stars/page/70/#star-6931)

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Roger+Grosse) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Roger+Grosse) · [dblp](https://dblp.org/search?q=Roger+Grosse) · [ACL Anthology](https://aclanthology.org/search/?q=Roger+Grosse)

## Affiliations

[🎓**University of Toronto** Toronto · Canada 2014–2026 · 63 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-toronto/) · [🔬**Vector Institute** Toronto · Canada 2017–2025 · 27 papers](https://md.research.elamur.ai/free/en/labs/vector-institute/) · [🎓**Massachusetts Institute of Technology** Cambridge · United States 2009–2024 · 6 papers](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) · [🤝**Machine Intelligence Research Institute** Berkeley · United States 2022–2023 · 2 papers](https://ror.org/01h4ass90) · [🔬**MIT Computer Science and Artificial Intelligence Laboratory** Cambridge · United States 2011–2012 · 2 papers](https://md.research.elamur.ai/free/en/labs/mit-computer-science-and-artificial-intelligence-laboratory/) · [🎓**Stanford University** Stanford · United States 2007–2009 · 2 papers](https://md.research.elamur.ai/free/en/universities/stanford-university/)

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed.

## Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 5 The field of science this work belongs to (OpenAlex fields).[Computer Science · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computational Theory and Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/)

🧭 Topics 3 Research subjects and languages the work is about.[Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning · 2 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Evaluation & benchmarks · 1 work](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/)

## Works by year

### 2020s

[**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/roger-grosse/year/2023/) · [**2021** 1 paper](https://md.research.elamur.ai/free/en/authors/roger-grosse/year/2021/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/authors/roger-grosse/year/2020/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Studying Large Language Model Generalization with Influence Functions](https://md.research.elamur.ai/free/en/papers/grosse-2023-studying-large-language-model-generalization/)** *(2023 · 105 citations)* Knowing which training examples drive a given behavior in a large language model could help researchers anticipate and reduce its risks.
2. **[INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving](https://md.research.elamur.ai/free/en/papers/wu-2020-int-inequality-benchmark-evaluating-generalization/)** *(2020 · 41 citations)* Learning-based theorem provers struggle with two issues: formal proof corpora are small, and useful target theorems often differ substantially from those seen in training.
3. **[LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning](https://md.research.elamur.ai/free/en/papers/wu-2021-lime-learning-inductive-bias-primitives/)** *(2021 · 39 citations)* The paper asks whether the inductive bias needed for mathematical reasoning can be taught to a generic transformer through data rather than through specialized architectures.

## All works

25 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. **[Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations ↗](https://doi.org/10.1145/1553374.1553453) International Conference on Machine Learning · no summary yet**Honglak Lee et al.*2009 · 2,412 citations*
2. **[Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation ↗](https://arxiv.org/abs/1708.05144) arXiv (Cornell University) · no summary yet**Yuhuai Wu et al.*2017 · 450 citations*
3. **[Importance Weighted Autoencoders ↗](https://arxiv.org/abs/1509.00519) arXiv (Cornell University) · no summary yet**Yuri Burda, Roger Grosse, Ruslan Salakhutdinov*2015 · 316 citations*
4. **[Toy Models of Superposition ↗](https://arxiv.org/abs/2209.10652) arXiv:2209.10652 · no summary yet**Nelson Elhage et al.*2022 · 277 citations*
5. **[Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches ↗](https://arxiv.org/abs/1803.04386) arXiv:1803.04386 · no summary yet**Yeming Wen et al.*2018 · 189 citations*
6. [**Studying Large Language Model Generalization with Influence Functions arXiv:2308.03296**Roger Grosse, Juhan Bae, Cem Anil, et al.*2023 · 105 citations*](https://md.research.elamur.ai/free/en/papers/grosse-2023-studying-large-language-model-generalization/)
7. **[Distributed Second-Order Optimization using Kronecker-Factored Approximations ↗](https://openalex.org/W2750933313) International Conference on Learning Representations · no summary yet**Jimmy Lei Ba, Roger Grosse, James Martens*2017 · 73 citations*
8. **[Accurate and Conservative Estimates of MRF Log-likelihood using Reverse Annealing ↗](https://arxiv.org/abs/1412.8566) arXiv (Cornell University) · no summary yet**Yuri Burda, Roger Grosse, Ruslan Salakhutdinov*2014 · 43 citations*
9. [**INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving arXiv:2007.02924**Yuhuai Wu, Albert Qiaochu Jiang, Jimmy Ba, et al.*2020 · 41 citations*](https://md.research.elamur.ai/free/en/papers/wu-2020-int-inequality-benchmark-evaluating-generalization/)
10. **[On the Quantitative Analysis of Decoder-Based Generative Models ↗](https://arxiv.org/abs/1611.04273) arXiv (Cornell University) · no summary yet**Yuhuai Wu et al.*2016 · 41 citations*
11. [**LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning arXiv:2101.06223**Yuhuai Wu, Markus Rabe, Wenda Li, et al.*2021 · 39 citations*](https://md.research.elamur.ai/free/en/papers/wu-2021-lime-learning-inductive-bias-primitives/)
12. **[Exploiting compositionality to explore a large space of model structures ↗](https://arxiv.org/abs/1210.4856) arXiv (Cornell University) · no summary yet**Roger Grosse et al.*2012 · 33 citations*
13. **[Reversible Recurrent Neural Networks ↗](https://arxiv.org/abs/1810.10999) arXiv (Cornell University) · no summary yet**Matthew Mackay et al.*2018 · 30 citations*
14. **[Adversarial Distillation of Bayesian Neural Network Posteriors ↗](https://arxiv.org/abs/1806.10317) arXiv (Cornell University) · no summary yet**Kuan-Chieh Wang et al.*2018 · 29 citations*
15. **[Learning Wake-Sleep Recurrent Attention Models ↗](https://arxiv.org/abs/1509.06812) arXiv (Cornell University) · no summary yet**Jimmy Lei Ba et al.*2015 · 29 citations*
16. **[The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning ↗](https://arxiv.org/abs/2007.04212) arXiv (Cornell University) · no summary yet**Yuhuai Wu et al.*2020 · 27 citations*
17. **[Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes ↗](https://arxiv.org/abs/2104.11044) arXiv (Cornell University) · no summary yet**James Lucas et al.*2021 · 13 citations*
18. **[When Does Preconditioning Help or Hurt Generalization? ↗](https://arxiv.org/abs/2006.10732) arXiv (Cornell University) · no summary yet**Шун-ичи Амари et al.*2020 · 11 citations*
19. **[Aggregated Momentum: Stability Through Passive Damping ↗](https://arxiv.org/abs/1804.00325) arXiv (Cornell University) · no summary yet**James Lucas et al.*2018 · 10 citations*
20. **[Sabotage Evaluations for Frontier Models ↗](https://arxiv.org/abs/2410.21514) arXiv (Cornell University) · no summary yet**Joe Benton et al.*2024 · 7 citations*
21. **[Second-order Optimization for Deep Reinforcement Learning using Kronecker-factored Approximation ↗](https://openalex.org/W2753431380) neural information processing systems · no summary yet**Yuhuai Wu et al.*2017 · 7 citations*
22. **[Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve ↗](https://arxiv.org/abs/2212.03905) arXiv (Cornell University) · no summary yet**Juhan Bae et al.*2022 · 4 citations*
23. **[Forecasting Rare Language Model Behaviors ↗](https://arxiv.org/abs/2502.16797) arXiv (Cornell University) · no summary yet**Erik Jones et al.*2025 · 3 citations*
24. **[On Monotonic Linear Interpolation of Neural Network Parameters ↗](https://openalex.org/W3172058676) International Conference on Machine Learning · no summary yet**James Lucas et al.*2021 · 1 citation*
25. **[Accurate and Conservative Estimates of MRF Log-likelihood using Reverse Annealing. arXiv:1412.8566 ↗](https://openalex.org/W7100459168) no summary yet**Yuri Burda, Roger Grosse, Ruslan Salakhutdinov*2014*

## Co-authors here

12 of 15 co-authors with a page, the most papers together first.

- [Jimmy Lei Ba](https://md.research.elamur.ai/free/en/authors/jimmy-lei-ba/) ×2
- [Yuhuai Wu](https://md.research.elamur.ai/free/en/authors/yuhuai-wu/) ×2
- [Albert Q. Jiang](https://md.research.elamur.ai/free/en/authors/albert-q-jiang/)
- [Alex Tamkin](https://md.research.elamur.ai/free/en/authors/alex-tamkin/)
- [Benoit Steiner](https://md.research.elamur.ai/free/en/authors/benoit-steiner/)
- [Cem Anil](https://md.research.elamur.ai/free/en/authors/cem-anil/)
- [Christian Szegedy](https://md.research.elamur.ai/free/en/authors/christian-szegedy/)
- [Dustin Li](https://md.research.elamur.ai/free/en/authors/dustin-li/)
- [Esin Durmus](https://md.research.elamur.ai/free/en/authors/esin-durmus/)
- [Ethan Perez](https://md.research.elamur.ai/free/en/authors/ethan-perez/)
- [Evan Hubinger](https://md.research.elamur.ai/free/en/authors/evan-hubinger/)
- [Kamile Lukošiute](https://md.research.elamur.ai/free/en/authors/kamile-luko-vsiute/)

## Venues

Where their works here were published, the most works first, with the editions of those that have a page.

- International Conference on Machine Learning ×2
- International Conference on Learning Representations
- neural information processing systems

## Cited by

Papers of our library cite their works 964 times (of the 149,439 papers whose bibliographies we read); [254 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/roger-grosse/cited-by/).

Updated 3 November 2026