Roger B. Grosse

Affiliations:
  • University of Toronto, Department of Computer Science, ON, Canada
  • Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA (PhD 2014)


According to our database1, Roger B. Grosse authored at least 84 papers between 2007 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data.
CoRR, 2024

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions.
CoRR, 2024

Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Measuring Stochastic Data Complexity with Boltzmann Influence Functions.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

REFACTOR: Learning to Extract Theorems from Proofs.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Studying Large Language Model Generalization with Influence Functions.
CoRR, 2023

Similarity-based cooperative equilibrium.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Efficient Parametric Approximations of Neural Network Function Space Distance.
Proceedings of the International Conference on Machine Learning, 2023

Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
Similarity-based Cooperation.
CoRR, 2022

Proximal Learning With Opponent-Learning Awareness.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Amortized Proximal Optimization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

If Influence Functions are the Answer, Then What is the Question?
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Path Independent Equilibrium Models Can Better Exploit Test-Time Computation.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

On Implicit Bias in Overparameterized Bilevel Optimization.
Proceedings of the International Conference on Machine Learning, 2022

Improving Mutual Information Estimation with Annealed and Energy-Based Bounds.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021
A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints.
J. Mach. Learn. Res., 2021

Learning to Give Checkable Answers with Prover-Verifier Games.
CoRR, 2021

Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes.
CoRR, 2021

Don't Fix What ain't Broke: Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization.
CoRR, 2021

Differentiable Annealed Importance Sampling and the Perils of Gradient Noise.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning.
Proceedings of the 38th International Conference on Machine Learning, 2021

Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition.
Proceedings of the 38th International Conference on Machine Learning, 2021

On Monotonic Linear Interpolation of Neural Network Parameters.
Proceedings of the 38th International Conference on Machine Learning, 2021

INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving.
Proceedings of the 9th International Conference on Learning Representations, 2021

When does preconditioning help or hurt generalization?
Proceedings of the 9th International Conference on Learning Representations, 2021

Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Understanding and Mitigating Exploding Inverses in Invertible Neural Networks.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Learning Branching Heuristics for Propositional Model Counting.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning.
CoRR, 2020

Learning Branching Heuristics for Propositional Model Counting.
CoRR, 2020

Regularized linear autoencoders recover the principal components, eventually.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Evaluating Lossy Compression Rates of Deep Generative Models.
Proceedings of the 37th International Conference on Machine Learning, 2020

Picking Winning Tickets Before Training by Preserving Gradient Flow.
Proceedings of the 8th International Conference on Learning Representations, 2020

2019
Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks.
CoRR, 2019

Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis.
Proceedings of the 36th International Conference on Machine Learning, 2019

Sorting Out Lipschitz Function Approximation.
Proceedings of the 36th International Conference on Machine Learning, 2019

Three Mechanisms of Weight Decay Regularization.
Proceedings of the 7th International Conference on Learning Representations, 2019

Functional variational Bayesian Neural Networks.
Proceedings of the 7th International Conference on Learning Representations, 2019

Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions.
Proceedings of the 7th International Conference on Learning Representations, 2019

Understanding Posterior Collapse in Generative Latent Variable Models.
Proceedings of the Deep Generative Models for Highly Structured Data, 2019

Aggregated Momentum: Stability Through Passive Damping.
Proceedings of the 7th International Conference on Learning Representations, 2019

TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer.
Proceedings of the 7th International Conference on Learning Representations, 2019

2018
Eigenvalue Corrected Noisy Natural Gradient.
CoRR, 2018

A Coordinate-Free Construction of Scalable Natural Gradient.
CoRR, 2018

Aggregated Momentum: Stability Through Passive Damping.
CoRR, 2018

Reversible Recurrent Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Isolating Sources of Disentanglement in Variational Autoencoders.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Noisy Natural Gradient as Variational Inference.
Proceedings of the 35th International Conference on Machine Learning, 2018

Adversarial Distillation of Bayesian Neural Network Posteriors.
Proceedings of the 35th International Conference on Machine Learning, 2018

Differentiable Compositional Kernel Learning for Gaussian Processes.
Proceedings of the 35th International Conference on Machine Learning, 2018

Understanding Short-Horizon Bias in Stochastic Meta-Optimization.
Proceedings of the 6th International Conference on Learning Representations, 2018

Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches.
Proceedings of the 6th International Conference on Learning Representations, 2018

Stochastic Gradient Langevin dynamics that Exploit Neural Network Structure.
Proceedings of the 6th International Conference on Learning Representations, 2018

2017
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

The Reversible Residual Network: Backpropagation Without Storing Activations.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

On the Quantitative Analysis of Decoder-Based Generative Models.
Proceedings of the 5th International Conference on Learning Representations, 2017

Distributed Second-Order Optimization using Kronecker-Factored Approximations.
Proceedings of the 5th International Conference on Learning Representations, 2017

Discovering and Exploiting Additive Structure for Bayesian Optimization.
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016
Importance Weighted Autoencoders.
Proceedings of the 4th International Conference on Learning Representations, 2016

Measuring the reliability of MCMC inference with bidirectional Monte Carlo.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

A Kronecker-factored approximate Fisher matrix for convolution layers.
Proceedings of the 33nd International Conference on Machine Learning, 2016

2015
Sandwiching the marginal likelihood using bidirectional Monte Carlo.
CoRR, 2015

Statistical Inference, Learning and Models in Big Data.
CoRR, 2015

Learning Wake-Sleep Recurrent Attention Models.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Optimizing Neural Networks with Kronecker-factored Approximate Curvature.
Proceedings of the 32nd International Conference on Machine Learning, 2015

Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix.
Proceedings of the 32nd International Conference on Machine Learning, 2015

Accurate and conservative estimates of MRF log-likelihood using reverse annealing.
Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, 2015

2014
Model selection in compositional spaces.
PhD thesis, 2014

Testing MCMC code.
CoRR, 2014

Automatic Construction and Natural-Language Description of Nonparametric Regression Models.
Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, 2014

2013
Annealing between distributions by averaging moments.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Structure Discovery in Nonparametric Regression through Compositional Kernel Search.
Proceedings of the 30th International Conference on Machine Learning, 2013

2012
Exploiting compositionality to explore a large space of model structures.
Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence, 2012

2011
Unsupervised learning of hierarchical representations with convolutional deep belief networks.
Commun. ACM, 2011

2009
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations.
Proceedings of the 26th Annual International Conference on Machine Learning, 2009

Ground truth dataset and baseline evaluations for intrinsic image algorithms.
Proceedings of the IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27, 2009

2007
Shift-Invariance Sparse Coding for Audio Classification.
Proceedings of the UAI 2007, 2007


  Loading...