Kamu erişimi zorunlu olan makaleler - Daniel M. RoyDaha fazla bilgi edinin
Bir yerde sunuluyor: 43
Linear mode connectivity and the lottery ticket hypothesis
J Frankle, GK Dziugaite, D Roy, M Carbin
International Conference on Machine Learning, 3259-3269, 2020
Zorunlu olanlar: US Department of Defense, Natural Sciences and Engineering Research Council …
Bayesian models of graphs, arrays and other exchangeable random structures
P Orbanz, DM Roy
IEEE transactions on pattern analysis and machine intelligence 37 (2), 437-461, 2014
Zorunlu olanlar: UK Engineering and Physical Sciences Research Council
Mondrian forests: Efficient online random forests
B Lakshminarayanan, DM Roy, YW Teh
Advances in neural information processing systems 27, 2014
Zorunlu olanlar: European Commission
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the neural tangent kernel
S Fort, GK Dziugaite, M Paul, S Kharaghani, DM Roy, S Ganguli
Advances in Neural Information Processing Systems 33, 5850-5861, 2020
Zorunlu olanlar: US National Science Foundation, Natural Sciences and Engineering Research …
Information-theoretic generalization bounds for SGLD via data-dependent estimates
J Negrea, M Haghifam, GK Dziugaite, A Khisti, DM Roy
Advances in Neural Information Processing Systems 32, 2019
Zorunlu olanlar: Canadian Institutes of Health Research, Natural Sciences and Engineering …
Data-dependent PAC-Bayes priors via differential privacy
GK Dziugaite, DM Roy
Advances in neural information processing systems 31, 2018
Zorunlu olanlar: Natural Sciences and Engineering Research Council of Canada, UK Engineering …
Sharpened generalization bounds based on conditional mutual information and an application to noisy, iterative algorithms
M Haghifam, J Negrea, A Khisti, DM Roy, GK Dziugaite
Advances in Neural Information Processing Systems 33, 9925-9935, 2020
Zorunlu olanlar: Canadian Institutes of Health Research, Natural Sciences and Engineering …
On the role of data in PAC-Bayes bounds
GK Dziugaite, K Hsu, W Gharbieh, G Arpino, D Roy
International Conference on Artificial Intelligence and Statistics, 604-612, 2021
Zorunlu olanlar: Natural Sciences and Engineering Research Council of Canada
In search of robust measures of generalization
GK Dziugaite, A Drouin, B Neal, N Rajkumar, E Caballero, L Wang, ...
Advances in Neural Information Processing Systems 33, 11723-11733, 2020
Zorunlu olanlar: Natural Sciences and Engineering Research Council of Canada
Adaptive gradient quantization for data-parallel sgd
F Faghri, I Tabrizian, I Markov, D Alistarh, DM Roy, A Ramezani-Kebrya
Advances in neural information processing systems 33, 3174-3185, 2020
Zorunlu olanlar: Natural Sciences and Engineering Research Council of Canada, European Commission
Information-theoretic generalization bounds for stochastic gradient descent
G Neu, GK Dziugaite, M Haghifam, DM Roy
Conference on Learning Theory, 3526-3545, 2021
Zorunlu olanlar: Natural Sciences and Engineering Research Council of Canada
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
GK Dziugaite, D Roy
International Conference on Machine Learning, 1377-1386, 2018
Zorunlu olanlar: US Department of Defense, Natural Sciences and Engineering Research Council …
In defense of uniform convergence: Generalization via derandomization with an application to interpolating predictors
J Negrea, GK Dziugaite, D Roy
International Conference on Machine Learning, 7263-7272, 2020
Zorunlu olanlar: Canadian Institutes of Health Research, Natural Sciences and Engineering …
Mondrian forests for large-scale regression when uncertainty matters
B Lakshminarayanan, DM Roy, YW Teh
Artificial Intelligence and Statistics, 1478-1487, 2016
Zorunlu olanlar: UK Engineering and Physical Sciences Research Council
Sampling and estimation for (sparse) exchangeable graphs
V Veitch, DM Roy
Zorunlu olanlar: US Department of Defense
Towards a unified information-theoretic framework for generalization
M Haghifam, GK Dziugaite, S Moran, D Roy
Advances in Neural Information Processing Systems 34, 26370-26381, 2021
Zorunlu olanlar: Natural Sciences and Engineering Research Council of Canada
The future is log-gaussian: Resnets and their infinite-depth-and-width limit at initialization
M Li, M Nica, D Roy
Advances in Neural Information Processing Systems 34, 7852-7864, 2021
Zorunlu olanlar: Natural Sciences and Engineering Research Council of Canada
NUQSGD: Provably communication-efficient data-parallel SGD via nonuniform quantization
A Ramezani-Kebrya, F Faghri, I Markov, V Aksenov, D Alistarh, DM Roy
Journal of Machine Learning Research 22 (114), 1-43, 2021
Zorunlu olanlar: Natural Sciences and Engineering Research Council of Canada, European Commission
The shaped transformer: Attention models in the infinite depth-and-width limit
L Noci, C Li, M Li, B He, T Hofmann, CJ Maddison, D Roy
Advances in Neural Information Processing Systems 36, 54250-54281, 2023
Zorunlu olanlar: Natural Sciences and Engineering Research Council of Canada
The neural covariance SDE: Shaped infinite depth-and-width networks at initialization
M Li, M Nica, D Roy
Advances in Neural Information Processing Systems 35, 10795-10808, 2022
Zorunlu olanlar: Natural Sciences and Engineering Research Council of Canada
Yayıncılık ve maddi kaynak bilgileri otomatik olarak bir bilgisayar programı tarafından belirlenmektedir