Timezone: »
Structured prediction of tree-shaped objects is heavily studied under the name of syntactic dependency parsing. Current practice based on maximum likelihood or margin is either agnostic to or inconsistent with the evaluation loss. Risk minimization alleviates the discrepancy between training and test objectives but typically induces a non-convex problem. These approaches adopt explicit regularization to combat overfitting without probabilistic interpretation. We propose a moment-based distributionally robust optimization approach for tree structured prediction, where the worst-case expected loss over a set of distributions within bounded moment divergence from the empirical distribution is minimized. We develop efficient algorithms for arborescences and other variants of trees. We derive Fisher consistency, convergence rates and generalization bounds for our proposed method. We evaluate its empirical effectiveness on dependency parsing benchmarks.
Author Information
Yeshu Li (University of Illinois, Chicago)
Danyal Saeed (University of Illinois at Chicago)
Xinhua Zhang (University of Illinois at Chicago (UIC))
Brian Ziebart (University of Illinois at Chicago)
Kevin Gimpel
More from the Same Authors
-
2022 : Poisoning Generative Models to Promote Catastrophic Forgetting »
Siteng Kang · Xinhua Zhang -
2022 : Continual Poisoning of Generative Models to Promote Catastrophic Forgetting »
Siteng Kang · Xinhua Zhang -
2023 Poster: Distributionally Robust Skeleton Learning of Discrete Bayesian Networks »
Yeshu Li · Brian Ziebart -
2022 Panel: Panel 6B-1: Moment Distributionally Robust… & Public Wisdom Matters!… »
Yeshu Li · Karish Grover -
2022 Poster: Certifying Robust Graph Classification under Orthogonal Gromov-Wasserstein Threats »
Hongwei Jin · Zishun Yu · Xinhua Zhang -
2021 : Fairness for Robust Learning to Rank »
Omid Memarrast · Ashkan Rezaei · Rizal Fathony · Brian Ziebart -
2020 Poster: Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks »
Hongwei Jin · Zhan Shi · Venkata Jaya Shankar Ashish Peruri · Xinhua Zhang -
2020 Spotlight: Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks »
Hongwei Jin · Zhan Shi · Venkata Jaya Shankar Ashish Peruri · Xinhua Zhang -
2020 Poster: Proximal Mapping for Deep Regularization »
Mao Li · Yingyi Ma · Xinhua Zhang -
2020 Spotlight: Proximal Mapping for Deep Regularization »
Mao Li · Yingyi Ma · Xinhua Zhang -
2018 Poster: Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes »
Andrea Tirinzoni · Marek Petrik · Xiangli Chen · Brian Ziebart -
2018 Poster: Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise »
Dan Hendrycks · Mantas Mazeika · Duncan Wilson · Kevin Gimpel -
2018 Spotlight: Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes »
Andrea Tirinzoni · Marek Petrik · Xiangli Chen · Brian Ziebart -
2018 Poster: Distributionally Robust Graphical Models »
Rizal Fathony · Ashkan Rezaei · Mohammad Ali Bashiri · Xinhua Zhang · Brian Ziebart -
2017 Poster: Adversarial Surrogate Losses for Ordinal Regression »
Rizal Fathony · Mohammad Ali Bashiri · Brian Ziebart -
2016 Poster: Adversarial Multiclass Classification: A Risk Minimization Perspective »
Rizal Fathony · Anqi Liu · Kaiser Asif · Brian Ziebart -
2015 Poster: Softstar: Heuristic-Guided Probabilistic Inference »
Mathew Monfort · Brenden M Lake · Brenden Lake · Brian Ziebart · Patrick Lucey · Josh Tenenbaum -
2015 Poster: Adversarial Prediction Games for Multivariate Losses »
Hong Wang · Wei Xing · Kaiser Asif · Brian Ziebart -
2014 Workshop: Novel Trends and Applications in Reinforcement Learning »
Csaba Szepesvari · Marc Deisenroth · Sergey Levine · Pedro Ortega · Brian Ziebart · Emma Brunskill · Naftali Tishby · Gerhard Neumann · Daniel Lee · Sridhar Mahadevan · Pieter Abbeel · David Silver · Vicenç Gómez -
2014 Poster: Robust Classification Under Sample Selection Bias »
Anqi Liu · Brian Ziebart -
2014 Spotlight: Robust Classification Under Sample Selection Bias »
Anqi Liu · Brian Ziebart