Paul Rolland (2022)

Research Interests:

  • Bayesian optimization,
  • Machine Learning
  • Convex Optimization

 

Biography

I received my Bachelor degree at EPFL in Physics, and spent my third year abroad at the Imperial College of London in 2014. I then got my Master at EPFL in “Computational Sciences and Engineering”. My master project was supervised by Prof. Volkan Cevher, and I started my PhD at LIONS in 2017. I finished my PHD in September 2022.

Publications with LIONS

Predicting in Uncertain Environments: Methods for Robust Machine Learning

P. T. Y. Rolland / V. Cevher (Dir.)  

Lausanne, EPFL, 2022. 

Detailed record

Full text – View at publisher

Identifiability and Generalizability from Multiple Experts in Inverse Reinforcement Learning

P. T. Y. Rolland; L. Viano; N. Schürhoff; B. Nikolov; V. Cevher 

2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, November 28 – December 3, 2022.

Detailed record

Full text

Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models

P. T. Y. Rolland; V. Cevher; M. Kleindessner; C. Russel; B. Schölkopf et al. 

2022. 38th International Conference on Machine Learning (ICML), Baltimore, Maryland, USA, July 17-23, 2022.

Detailed record

Full text

The Effect of the Intrinsic Dimension on the Generalization of Quadratic Classifiers

F. Latorre; L. T. Dadi; P. T. Y. Rolland; V. Cevher 

2021. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia, December 6-14, 2021.

Detailed record

Full text

Robust Reinforcement Learning via Adversarial training with Langevin Dynamics

K. Parameswaran; Y-T. Huang; Y-P. Hsieh; P. T. Y. Rolland; C. Shi et al. 

2020-11-05

Detailed record

Full text

Lipschitz constant estimation for Neural Networks via sparse polynomial optimization

F. Latorre; P. T. Y. Rolland; V. Cevher 

2020-04-26. 8th International Conference on Learning Representations, Addis Ababa, ETHIOPIA, April 26-30, 2020.

Detailed record

Full text

Efficient Proximal Mapping of the 1-path-norm of Shallow Networks

F. Latorre; P. T. Y. Rolland; S. N. Hallak; V. Cevher 

2020. 37th International Conference on Machine Learning (ICML), Virtual, July 13-18, 2020.

Detailed record

Full text

Double-Loop Unadjusted Langevin Algorithm

P. Rolland; A. Eftekhari; A. Kavis; V. Cevher 

2020. 37th International Conference on Machine Learning (ICLM 2020), Virtual, July 12-18, 2020.

Detailed record

Full text

Efficient learning of smooth probability functions from Bernoulli tests with guarantees.

P. T. Y. Rolland; A. Kavis; A. Immer; A. Singla; V. Cevher 

2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.

Detailed record

Full text

Mirrored Langevin Dynamics

Y-P. Hsieh; A. Kavis; P. T. Y. Rolland; V. Cevher 

2018. Thirty-second Conference on Neural Information Processing Systems (NIPS), Montréal, p. 2878-2887.

Detailed record

Full text

Contact

email: [email protected]

EPFL people page

Access map