Search Results for author: Rizal Fathony

Found 10 papers, 4 papers with code

Fairness for Robust Learning to Rank

no code implementations12 Dec 2021 Omid Memarrast, Ashkan Rezaei, Rizal Fathony, Brian Ziebart

While conventional ranking systems focus solely on maximizing the utility of the ranked items to users, fairness-aware ranking systems additionally try to balance the exposure for different protected attributes such as gender or race.

Fairness Learning-To-Rank

Multiplicative Filter Networks

3 code implementations ICLR 2021 Rizal Fathony, Anit Kumar Sahu, Devin Willmott, J Zico Kolter

Although deep networks are typically used to approximate functions over high dimensional inputs, recent work has increased interest in neural networks as function approximators for low-dimensional-but-complex functions, such as representing images as a function of pixel coordinates, solving differential equations, or representing signed distance fields or neural radiance fields.

AP-Perf: Incorporating Generic Performance Metrics in Differentiable Learning

4 code implementations2 Dec 2019 Rizal Fathony, J. Zico Kolter

We propose a method that enables practitioners to conveniently incorporate custom non-decomposable performance metrics into differentiable learning pipelines, notably those based upon neural network architectures.

General Classification Image Classification

Fairness for Robust Log Loss Classification

1 code implementation10 Mar 2019 Ashkan Rezaei, Rizal Fathony, Omid Memarrast, Brian Ziebart

Developing classification methods with high accuracy that also avoid unfair treatment of different groups has become increasingly important for data-driven decision making in social applications.

Classification Decision Making +2

Distributionally Robust Graphical Models

no code implementations NeurIPS 2018 Rizal Fathony, Ashkan Rezaei, Mohammad Ali Bashiri, Xinhua Zhang, Brian D. Ziebart

Our approach enjoys both the flexibility of incorporating customized loss metrics into its design as well as the statistical guarantee of Fisher consistency.

Structured Prediction

Efficient and Consistent Adversarial Bipartite Matching

no code implementations ICML 2018 Rizal Fathony, Sima Behpour, Xinhua Zhang, Brian Ziebart

Many important structured prediction problems, including learning to rank items, correspondence-based natural language processing, and multi-object tracking, can be formulated as weighted bipartite matching optimizations.

Learning-To-Rank Multi-Object Tracking +2

Kernel Robust Bias-Aware Prediction under Covariate Shift

no code implementations28 Dec 2017 Anqi Liu, Rizal Fathony, Brian D. Ziebart

Robust Bias-Aware (RBA) prediction provides the conditional label distribution that is robust to the worstcase logarithmic loss for the target distribution while matching feature expectation constraints from the source distribution.

Adversarial Surrogate Losses for Ordinal Regression

no code implementations NeurIPS 2017 Rizal Fathony, Mohammad Ali Bashiri, Brian Ziebart

Ordinal regression seeks class label predictions when the penalty incurred for mistakes increases according to an ordering over the labels.

General Classification

Adversarial Multiclass Classification: A Risk Minimization Perspective

no code implementations NeurIPS 2016 Rizal Fathony, Anqi Liu, Kaiser Asif, Brian Ziebart

Recently proposed adversarial classification methods have shown promising results for cost sensitive and multivariate losses.

Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.