Publications

Conferences

• Giorgio Patrini, Alessandro Rozza, Aditya Menon, Richard Nock and Lizhen Qu
  Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
  CVPR 2017 (oral, acceptance rate 2.7%) [] [] [slides]

• Boris Muzellec, Richard Nock, Giorgio Patrini and Frank Nielsen
  Tsallis Regularized Optimal Transport and Ecological Inference
  AAAI 2017 [arXiv]

• Giorgio Patrini, Frank Nielsen, Richard Nock and Marcello Carioni
  Loss factorization, weakly supervised learning and label noise robustness
  ICML 2016 [supp] [arXiv] [video] [slides]

• Giorgio Patrini, Richard Nock, Stephen Hardy and Tiberio Caetano
  Fast learning from distributed datasets without entity matching
  IJCAI 2016 [arXiv]

• Richard Nock, Giorgio Patrini and Arik Friedman
  Rademacher Observations, Private Data, and Boosting
  ICML 2015 [arXiv] [video] [slides]

• Giorgio Patrini, Richard Nock, Paul Rivera and Tiberio Caetano
  (Almost) No Label No Cry
  NIPS 2014 (spotlight, acceptance rate 3.7%) [supp] []

• Nicola Gatti, Giorgio Patrini, Marco Rocco and Tuomas Sandholm
  Combining local search techniques and path following for bimatrix games
  UAI 2012

• Sofia Ceppi, Nicola Gatti, Giorgio Patrini and Marco Rocco
  Local search methods for finding a Nash equilibrium in two-player games
  IAT 2010

• Sofia Ceppi, Nicola Gatti, Giorgio Patrini and Marco Rocco
  Local search techniques for computing equilibria in two-player general-sum strategic-form games
  AAMAS 2010 (extended abstract)

Workshops, tech reports and notes

• Mentari Djatmiko, Stephen Hardy, Wilko Henecka, Hamish Ivey-Law, Maximilian Ott, Giorgio Patrini, Guillaume Smith, Brian Thorne and Dongyao Wu
  Privacy-preserving entity resolution and logistic regression on encrypted data
  ICMl 2017 workshop on Private and secure machine learning [slides]

• Giorgio Patrini, Frank Nielsen and Richard Nock
  Bridging weak supervision and privacy aware learning via sufficient statistics
  NIPS 2015 workshop on Learning and privacy with incomplete data and weak supervision

Thesis

• Giorgio Patrini
  Weakly supervised learning via statistical sufficiency
  Australian National University, 2016, PhD thesis

• Giorgio Patrini and Marco Rocco
  Local search techniques for Nash equilibrium computation with bimatrix game
  Politecnico di Milano, 2012, MSc thesis

Patents

• Richard Nock and Giorgio Patrini
  Learning from distributed data, WO 2016/127218 A1

• Richard Nock, Giorgio Patrini and Tiberio Caetano
  Learning with transformed data, WO 2016/061628 A1

Academic service

Reviewer for

• NIPS 2015, 2016, 2017
• JMLR 2016
• S+SSPR 2016
• JMLC 2016

Workshop co-organizer

• Learning and privacy with incomplete data and weak supervision.
  NIPS 2015 (primary organizer)