George Deligiannidis

George Deligiannidis

Computational Statistics, Monte Carlo methods

Publications

2022

  • O. Clivio , F. Falck , B. Lehmann , G. Deligiannidis , C. Holmes , Neural score matching for high-dimensional causal inference, in International Conference on Artificial Intelligence and Statistics, 2022, 7076–7110.
  • Y. Shi , V. De Bortoli , G. Deligiannidis , A. Doucet , Conditional Simulation Using Diffusion Schr\backslash" odinger Bridges, arXiv preprint arXiv:2202.13460, 2022.
  • E. Clerico , A. Shidani , G. Deligiannidis , A. Doucet , Chained Generalisation Bounds, in COLT 2022, 2022, no. arXiv:2203.00977.
  • A. Campbell , J. Benton , V. De Bortoli , T. Rainforth , G. Deligiannidis , A. Doucet , A Continuous Time Framework for Discrete Denoising Models, arXiv preprint arXiv:2205.14987, 2022.
  • A. Shidani , G. Deligiannidis , A. Doucet , Ranking in Contextual Multi-Armed Bandits, arXiv preprint arXiv:2207.00109, 2022.
  • E. Clerico , G. Deligiannidis , B. Guedj , A. Doucet , A PAC-Bayes bound for deterministic classifiers, arXiv preprint arXiv:2209.02525, 2022.
  • F. Falck , C. Williams , D. Danks , G. Deligiannidis , C. Yau , C. Holmes , A. Doucet , M. Willetts , A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs, Advances in Neural Information Processing Systems, 2022.

2021

  • G. Deligiannidis , D. Paulin , A. Bouchard-Côté , A. Doucet , Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates, Annals of Applied Probability, vol. 31, no. 6, 2612–2662, 2021.
  • G. Deligiannidis , S. Gouëzel , Z. Kosloff , Boundary of the Range of a random walk and the F\backslash" olner property, Electronic Journal of Probability, vol. 26, 1–39, 2021.
  • G. Deligiannidis , S. Maurer , M. V. Tretyakov , Random walk algorithm for the Dirichlet problem for parabolic integro-differential equation, BIT Numerical Mathematics, vol. 61, no. 4, 1223–1269, 2021.
  • A. Corenflos , J. Thornton , G. Deligiannidis , A. Doucet , Differentiable particle filtering via entropy-regularized optimal transport, in International Conference on Machine Learning, 2021, 2100–2111.
  • A. Camuto , G. Deligiannidis , M. A. Erdogdu , M. Gurbuzbalaban , U. Simsekli , L. Zhu , Fractal structure and generalization properties of stochastic optimization algorithms, NeurIPS (Spotlight), vol. 34, 18774–18788, 2021.
  • E. Clerico , G. Deligiannidis , A. Doucet , Wide stochastic networks: Gaussian limit and PAC-Bayesian training, arXiv preprint arXiv:2106.09798, 2021.
  • G. Deligiannidis , V. De Bortoli , A. Doucet , Quantitative uniform stability of the iterative proportional fitting procedure, arXiv preprint arXiv:2108.08129, 2021.
  • E. Clerico , G. Deligiannidis , A. Doucet , Conditional Gaussian PAC-Bayes, in Accepted at AISTATS 2022, 2021, no. arXiv preprint arXiv:2110.11886.
  • E. Khribch , G. Deligiannidis , D. Paulin , On Mixing Times of Metropolized Algorithm With Optimization Step (MAO): A New Framework, arXiv preprint arXiv:2112.00565, 2021.

2020

  • S. M. Schmon , G. Deligiannidis , A. Doucet , M. K. Pitt , Large-sample asymptotics of the pseudo-marginal method, Biometrika, Jul. 2020.
  • F. Faizi , P. Buigues , G. Deligiannidis , E. Rosta , Simulated tempering with irreversible Gibbs sampling techniques, Journal of Chemical Physics, vol. 153, no. 21, 2020.
  • F. Faizi , G. Deligiannidis , E. Rosta , Efficient Irreversible Monte Carlo Samplers, Journal of Chemical Theory and Computation, vol. 16, no. 4, 2124–2138, 2020.
  • S. Schmon , A. Doucet , G. Deligiannidis , Bernoulli race particle filters, in AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics, 2020.
  • L. Middleton , G. Deligiannidis , A. Doucet , P. Jacob , Unbiased markov chain monte carlo for intractable target distributions, Electronic Journal of Statistics, vol. 14, no. 2, 2842–2891, 2020.
  • J. Heng , A. Bishop , G. Deligiannidis , A. Doucet , Controlled sequential monte carlo, Annals of Statistics, vol. 48, no. 5, 2904–2929, 2020.
  • L. Middleton , G. Deligiannidis , A. Doucet , P. Jacob , Unbiased smoothing using particle independent metropolis-hastings, in AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics, 2020.
  • S. Schmon , G. Deligiannidis , A. Doucet , M. Pitt , Large sample asymptotics of the pseudo-marginal method, Biometrika, 2020.
  • G. Deligiannidis , A. Doucet , S. Rubenthaler , Ensemble Rejection Sampling, aarXiv:2001.0988, 2020.
  • R. Cornish , A. Caterini , G. Deligiannidis , A. Doucet , Relaxing bijectivity constraints with continuously indexed normalising flows, in ICML, 2020, 2133–2143.
  • S. Hayou , E. Clerico , B. He , G. Deligiannidis , A. Doucet , J. Rousseau , Stable ResNet, AISTATS 2021, 2020.
  • U. Simsekli , O. Sener , G. Deligiannidis , M. Erdogdu , Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks, NeurIPS (Spotlight), vol. 33, 2020.

2019

  • G. Deligiannidis , A. Bouchard-Côté , A. Doucet , Exponential ergodicity of the bouncy particle sampler, Annals of Statistics, vol. 47, no. 3, 1268–1287, 2019.
  • R. Cornish , P. Vanetti , A. Bouchard-Côté , G. Deligiannidis , A. Doucet , Scalable metropolis-hastings for exact Bayesian inference with large datasets, in 36th International Conference on Machine Learning, ICML 2019, 2019, vol. 2019-June, 2398–2429.
  • S. Syed , A. Bouchard-Côté , G. Deligiannidis , A. Doucet , Non-reversible parallel tempering: a scalable highly parallel MCMC scheme, Journal of the Royal Statistical Society, Series B (to appear), 2019.
  • S. M. Schmon , G. Deligiannidis , A. Doucet , Bernoulli Race Particle Filters, AISTATS, 2019.

2018

  • G. Deligiannidis , A. Doucet , M. Pitt , The correlated pseudomarginal method, JRSSB, vol. 80, no. 5, 839–870, 2018.
  • G. Deligiannidis , A. Lee , Which ergodic averages have finite asymptotic variance?, Annals of Applied Probability, vol. 28, no. 4, 2309–2334, 2018.

2017

  • G. Deligiannidis , Z. Kosloff , Relative complexity of Random walks in Random scenery in the absence of a weak invariance principle for the local times, Annals of Probability, vol. 45, no. 4, 2505–2532, 2017.
  • P. Vanetti , A. Bouchard-Côté , G. Deligiannidis , A. Doucet , Piecewise-Deterministic Markov Chain Monte Carlo, arXiv preprint arXiv:1707.05296, 2017.

2016

  • G. Deligiannidis , S. Utev , Optimal Bounds for the Variance of Self-Intersection Local Times, International Journal of Stochastic Analysis, vol. 2016, 2016.

2015

  • A. Doucet , M. Pitt , G. Deligiannidis , R. Kohn , Efficient implementation of Markov chain Monte Carlo when using an unbiased likelihood estimator, Biometrika, vol. 102, no. 2, 295–313, 2015.
  • G. Deligiannidis , M. Peligrad , S. Utev , Asymptotic Variance of Stationary Reversible and Normal Markov Processes, Electronic Journal of Probability, vol. 20, 2015.

2013

  • G. Deligiannidis , S. Utev , Variance of partial sums of stationary sequences, Annals of Probability, vol. 41, no. 5, 3606–3616, 2013.

2011

  • G. Deligiannidis , S. Utev , Asymptotic variance of the self-intersections of stable random walks using Darboux-Wiener theory, Siberian Mathematical Journal, vol. 52, no. 4, 639–650, 2011.

2009

  • G. Deligiannidis , H. Le , S. Utev , Optimal stopping for processes with independent increments , and applications, Journal of Applied Probability, vol. 46, no. 4, 1130–1145, 2009.