Search Results for author: Hyokun Yun

Found 17 papers, 8 papers with code

Robust Multi-Task Learning with Excess Risks

1 code implementation3 Feb 2024 Yifei He, Shiji Zhou, Guojun Zhang, Hyokun Yun, Yi Xu, Belinda Zeng, Trishul Chilimbi, Han Zhao

To overcome this limitation, we propose Multi-Task Learning with Excess Risks (ExcessMTL), an excess risk-based task balancing method that updates the task weights by their distances to convergence instead.

Multi-Task Learning

Threshold-aware Learning to Generate Feasible Solutions for Mixed Integer Programs

no code implementations1 Aug 2023 Taehyun Yoon, Jinwon Choi, Hyokun Yun, Sungbin Lim

Our study investigates that a specific range of variable assignment rates (coverage) yields high-quality feasible solutions, where we suggest optimizing the coverage bridges the gap between the learning and MIP objectives.

Combinatorial Optimization

MICO: Selective Search with Mutual Information Co-training

1 code implementation COLING 2022 Zhanyu Wang, Xiao Zhang, Hyokun Yun, Choon Hui Teo, Trishul Chilimbi

In contrast to traditional exhaustive search, selective search first clusters documents into several groups before all the documents are searched exhaustively by a query, to limit the search executed within one group or only a few groups.

Retrieval

Robustness to Capitalization Errors in Named Entity Recognition

no code implementations WS 2019 Sravan Bodapati, Hyokun Yun, Yaser Al-Onaizan

Robustness to capitalization errors is a highly desirable characteristic of named entity recognizers, yet we find standard models for the task are surprisingly brittle to such noise.

Data Augmentation named-entity-recognition +2

Deep Active Learning for Named Entity Recognition

2 code implementations WS 2017 Yanyao Shen, Hyokun Yun, Zachary C. Lipton, Yakov Kronrod, Animashree Anandkumar

In this work, we demonstrate that the amount of labeled training data can be drastically reduced when deep learning is combined with active learning.

Active Learning Decoder +4

WordRank: Learning Word Embeddings via Robust Ranking

2 code implementations EMNLP 2016 Shihao Ji, Hyokun Yun, Pinar Yanardag, Shin Matsushima, S. V. N. Vishwanathan

Then, based on this insight, we propose a novel framework WordRank that efficiently estimates word representations via robust ranking, in which the attention mechanism and robustness to noise are readily achieved via the DCG-like ranking losses.

Learning Word Embeddings Word Similarity

A Scalable Asynchronous Distributed Algorithm for Topic Modeling

1 code implementation16 Dec 2014 Hsiang-Fu Yu, Cho-Jui Hsieh, Hyokun Yun, S. V. N. Vishwanathan, Inderjit S. Dhillon

Learning meaningful topic models with massive document collections which contain millions of documents and billions of tokens is challenging because of two reasons: First, one needs to deal with a large number of topics (typically in the order of thousands).

Topic Models

Ranking via Robust Binary Classification

no code implementations NeurIPS 2014 Hyokun Yun, Parameswaran Raman, S. Vishwanathan

We propose RoBiRank, a ranking algorithm that is motivated by observing a close connection between evaluation metrics for learning to rank and loss functions for robust classification.

Binary Classification Classification +3

Distributed Stochastic Optimization of the Regularized Risk

no code implementations17 Jun 2014 Shin Matsushima, Hyokun Yun, Xinhua Zhang, S. V. N. Vishwanathan

Many machine learning algorithms minimize a regularized risk, and stochastic optimization is widely used for this task.

Stochastic Optimization

Ranking via Robust Binary Classification and Parallel Parameter Estimation in Large-Scale Data

no code implementations11 Feb 2014 Hyokun Yun, Parameswaran Raman, S. V. N. Vishwanathan

We propose RoBiRank, a ranking algorithm that is motivated by observing a close connection between evaluation metrics for learning to rank and loss functions for robust classification.

Binary Classification General Classification +2

NOMAD: Non-locking, stOchastic Multi-machine algorithm for Asynchronous and Decentralized matrix completion

1 code implementation1 Dec 2013 Hyokun Yun, Hsiang-Fu Yu, Cho-Jui Hsieh, S. V. N. Vishwanathan, Inderjit Dhillon

One of the key features of NOMAD is that the ownership of a variable is asynchronously transferred between processors in a decentralized fashion.

Distributed, Parallel, and Cluster Computing

Using Logistic Regression to Analyze the Balance of a Game: The Case of StarCraft II

no code implementations4 May 2011 Hyokun Yun

In online games, usually a human user competes with others, so the fairness of the game system to all users is of great importance not to lose interests of users on the game.

Applications Multimedia

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