Lune

Profiles2020-2025

Roger B Grosse

University of Toronto and Vector Institute

Also published as Roger Grosse

15Papers
12Last author
31Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers15

  1. Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic InferenceAuthor 4 of 4NeurIPS 2025
  2. Probabilistic Inference in Language Models via Twisted Sequential Monte CarloAuthor 4 of 4ICML 2024 · 61 citations
  3. Training Data Attribution via Approximate UnrollingAuthor 4 of 4NeurIPS 2024 · 41 citations
  4. Multi-Rate VAE: Train Once, Get the Full Rate-Distortion CurveAuthor 7 of 7ICLR 2023 · 3 citations
  5. Proximal Learning With Opponent-Learning AwarenessAuthor 3 of 4NeurIPS 2022 · 31 citations
  6. Amortized Proximal OptimizationAuthor 4 of 4NeurIPS 2022 · 15 citations
  7. INT: An Inequality Benchmark for Evaluating Generalization in Theorem ProvingAuthor 4 of 4ICLR 2021 · 60 citations
  8. Differentiable Annealed Importance Sampling and the Perils of Gradient NoiseAuthor 5 of 5NeurIPS 2021 · 46 citations
  9. Learning Branching Heuristics for Propositional Model CountingAuthor 5 of 7AAAI 2021 · 14 citations
  10. On Monotonic Linear Interpolation of Neural Network ParametersAuthor 6 of 6ICML 2021 · 11 citations
  11. When does preconditioning help or hurt generalization?Author 3 of 8ICLR 2021 · 11 citations
  12. Picking Winning Tickets Before Training by Preserving Gradient FlowAuthor 3 of 3ICLR 2020 · 743 citations
  13. Regularized linear autoencoders recover the principal components, eventuallyAuthor 4 of 4NeurIPS 2020 · 40 citations
  14. Evaluating Lossy Compression Rates of Deep Generative ModelsAuthor 4 of 4ICML 2020 · 30 citations
  15. Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response JacobiansAuthor 2 of 2NeurIPS 2020 · 28 citations
Dusk over the sea between two cliffs drawn in fine vertical lines