About Me

I am Rizal Fathony [full name: Rizal Zaini Ahmad Fathony], a third year PhD student at the Department of Computer Science, University of Illinois at Chicago. I work with my advisor Prof. Brian Ziebart in Statistical Machine Learning theory and applications.

Before attending PhD program at UIC, I completed Bachelor of Applied Science degree in Statistical Computation from the Institute of Statistics, Jakarta, Indonesia and Master of Science from the University of Illinois at Chicago.

Research Interest

I am generally interested in developing theoretically sound learning algorithms for various prediction tasks.

My current research is mainly in the theory of adversarial prediction --where we approximate our training data and optimize over the exact performance measure--, and also in the application of adversarial prediction for structured prediction tasks.


Adversarial prediction is an alternative approach to Empirical Risk Minimization (ERM) framework. Rather than optimizing a convex surrogate loss on training set as in ERM methods, it directly optimizes the desired performance measures and approximates training data. It results in a convex optimization over the Nash equilibrium of zero-sum games defined by the performance measures and the approximation of training data.


Some keywords related to my research interest are:
adversarial prediction, structured prediction, risk minimization, statistical learning theory, statistical consistency, kernel methods, game theory, convex and non-convex optimization, neural networks and deep learning.


Rizal Fathony, Anqi Liu, Kaiser Asif, Brian D. Ziebart. “Adversarial Multiclass Classification: A Risk Minimization Perspective”. Advances in Neural Information Processing Systems 29 (NIPS), 2016. [nips] [pdf] [poster] [code]

Abstract: Recently proposed adversarial classification methods have shown promising results for cost sensitive and multivariate losses. In contrast with empirical risk minimization (ERM) methods, which use convex surrogate losses to approximate the desired non-convex target loss function, adversarial methods minimize non-convex losses by treating the properties of the training data as being uncertain and worst case within a minimax game. Despite this difference in formulation, we recast adversarial classification under zero-one loss as an ERM method with a novel prescribed loss function. We demonstrate a number of theoretical and practical advantages over the very closely related hinge loss ERM methods. This establishes adversarial classification under the zero-one loss as a method that fills the long standing gap in multiclass hinge loss classification, simultaneously guaranteeing Fisher consistency and universal consistency, while also providing dual parameter sparsity and high accuracy predictions in practice.


NIPS Travel Award 2016

Won an International Fulbright Master of Science and Technology Scholarship Award (2012 - 2014)

Runner Up Developer at Indonesia Open Source Festival - Android Apps Competition (2010)

Nominee of Research and Development Category at Asia Pacific Information and Communication Technology Award (APICTA), Melbourne, Australia (2009)

Best Research and Development Category at Indonesia Information and Communication Technology Award, Jakarta, Indonesia (2009)

Grantee of a full scholarship and monthly stipend from the Indonesian government during undergraduate study at the Institute of Statistics, Jakarta, Indonesia (2003 - 2007)


Research AssistantDecember 2016 - present


Research Assistant at Prof. Brian Ziebart’s lab on Adversarial Prediction research.

Teaching AssistantAugust 2015 - December 2016


CS 412 Introduction to Machine Learning (Fall 2016).
CS 412 Introduction to Machine Learning (Spring 2016).
CS 491 Introduction to Machine Learning (Fall 2015).

Statistical Dissemination System Developer January 2008 - June 2012


Developed web-based statistical data dissemination and visualization systems for major surveys and censuses conducted by Central Bureau of Statistics Indonesia.

Template Design by W3layouts