Amir Sani, PhD

My research focuses on sequential resource allocation problems in agent-based and complex systems financial market models, with specific emphasis on sampling, surrogate modeling and policy approximation. My aim is to learn a resource allocation policies in (realistic) financial market models that achieve similar performance in the real world.


I am a research associate with Rama Cont at the CFM-Imperial Institute of Quantitative Finance in the Department of Mathematics at Imperial College London and an external research fellow at the Institute of Economics at Scuola Superiore Sant'Anna Pisa.

I completed my PhD, Machine Learning for Decision Making Under Uncertainty, under the supervision of Rémi Munos and Alessandro Lazaric as part of the SequeL team at INRIA-Lille Nord Europe and previously held a research fellowship at the Centre d'Économie de la Sorbonne in Université Paris 1, Panthéon-Sorbonne, working on the EU Horizons 2020 Future and Emerging Technologies DOLFINS project.



  • June 30th, 2018, Agent-Based Model Calibration, Workshop on Economics with Heterogeneous Interacting Agents, Tokyo, Japan
  • June 19th, 2018, Agent-Based Model Calibration, Invited Session on "Validation of Agent-Based Models", Computing in Economics and Finance, Milan, Italy
  • May 31st, 2018, Agent-Based Model Calibration using Machine Learning Surrogates, CFM-Imperial ENS Workshop on Machine Learning and Quantitative Finance 2018, London, England
  • May 10th, 2018, Search-Based Calibration of Agent-Based Models using Machine Learning Surrogates, Centre for Complexity Science, Imperial College London, London, United Kingdom
  • April 25th, 2018, Online Model Calibration using Machine Learning Surrogates, Capital Fund Management, Paris, France



Workshop Papers/Posters

  • Inferring Complex Networks of Influence: Understanding Green Investment Tipping Points, with Antoine Mandel, NIPS Workshop on Inference and Learning of Hypothetical and Counterfactual Interventions in Complex Systems, 2016
  • Macroeconomic Agent Based Model Calibration using Iterated Surrogates, with Francesco Lamperti, Antoine Mandel and Andrea Roventini, NIPS Workshop on Inference and Learning of Hypothetical and Counterfactual Interventions in Complex Systems, 2016
  • Information Theoretic Bootstrapping for Dependent Time Series, with Alessandro Lazaric and Daniil Ryabko, NIPS Workshop on Modern Nonparametric Methods in Machine Learning, 2013
  • The Universal Bootstrap for Dependent Data, with Alessandro Lazaric and Daniil Ryabko, Statistical modeling, financial data analysis and applications, 2013
  • Risk Averse Multi-Arm Bandits, with Alessandro Lazaric and Rémi Munos, NIPS Workshop on Markets, Mechanism and Multi-Agent Models, 2012


  • April 2018, ISCEF Special Session, Validating Agent-Based Models
  • February 10th, 2016, Collaborative Hackathon for Macroeconomic Agent-Based Model Surrogates
  • February 9th, 2016, Macroeconomic Surrogates for Agent-Based Models Workshop
  • November 2015 through February 2016, Data Driven Economics and Complexity Seminar Series