Rob Brekelmans
Rob Brekelmans
Vector Institute
Verified email at - Homepage
Cited by
Cited by
Invariant representations without adversarial training
D Moyer, S Gao, R Brekelmans, A Galstyan, G Ver Steeg
Advances in neural information processing systems 31, 2018
Auto-encoding total correlation explanation
S Gao, R Brekelmans, G Ver Steeg, A Galstyan
The 22nd international conference on artificial intelligence and statisticsá…, 2019
P4ML: A phased performance-based pipeline planner for automated machine learning
Y Gil, KT Yao, V Ratnakar, D Garijo, G Ver Steeg, P Szekely, ...
AutoML Workshop at ICML 24, 2018
Action Matching: Learning Stochastic Dynamics from Samples
K Neklyudov, R Brekelmans, D Severo, A Makhzani
International Conference on Machine Learning 2023, 2023
q-paths: Generalizing the geometric annealing path using power means
V Masrani, R Brekelmans, T Bui, F Nielsen, A Galstyan, G Ver Steeg, ...
Uncertainty in Artificial Intelligence, 1938-1947, 2021
All in the exponential family: Bregman duality in thermodynamic variational inference
R Brekelmans, V Masrani, F Wood, GV Steeg, A Galstyan
International Conference on Machine Learning 2020, 2020
Exact rate-distortion in autoencoders via echo noise
R Brekelmans, D Moyer, A Galstyan, G Ver Steeg
Advances in neural information processing systems 32, 2019
Improving mutual information estimation with annealed and energy-based bounds
R Brekelmans, S Huang, M Ghassemi, GV Steeg, R Grosse, A Makhzani
ICLR 2022 (International Conference on Learning Representations), 2023
Model-free risk-sensitive reinforcement learning
G DelÚtang, J Grau-Moya, M Kunesch, T Genewein, R Brekelmans, ...
arXiv preprint arXiv:2111.02907, 2021
Discovery and separation of features for invariant representation learning
A Jaiswal, R Brekelmans, D Moyer, GV Steeg, W AbdAlmageed, ...
arXiv preprint arXiv:1912.00646, 2019
Your Policy Regularizer is Secretly an Adversary
R Brekelmans, T Genewein, J Grau-Moya, G DelÚtang, M Kunesch, ...
Transactions on Machine Learning Research,á…, 2022
Information-Theoretic Diffusion
X Kong, R Brekelmans, GV Steeg
International Conference on Learning Representations 2023, 2023
Likelihood ratio exponential families
R Brekelmans, F Nielsen, A Makhzani, A Galstyan, GV Steeg
NeurIPS Workshop on Information Geometry, 2020
Gaussian process bandit optimization of the thermodynamic variational objective
V Nguyen, V Masrani, R Brekelmans, M Osborne, F Wood
Advances in Neural Information Processing Systems 33, 5764-5775, 2020
Disentangled representations via synergy minimization
G Ver Steeg, R Brekelmans, H Harutyunyan, A Galstyan
2017 55th Annual Allerton Conference on Communication, Control, andá…, 2017
A computational framework for solving Wasserstein Lagrangian flows
K Neklyudov, R Brekelmans, A Tong, L Atanackovic, Q Liu, A Makhzani
arXiv preprint arXiv:2310.10649, 2023
Probabilistic inference in language models via twisted sequential monte carlo
S Zhao, R Brekelmans, A Makhzani, R Grosse
arXiv preprint arXiv:2404.17546, 2024
Variational Representations of Annealing Paths: Bregman Information under monotonic embedding
R Brekelmans, F Nielsen
Information Geometry, 1-36, 2024
On Schr÷dinger Bridge Matching and Expectation Maximization
R Brekelmans, K Neklyudov
NeurIPS 2023 Workshop Optimal Transport and Machine Learning, 2023
The system can't perform the operation now. Try again later.
Articles 1–19