CSE 6389 Advanced Topics in Machine Learning, Data Mining, and Computer Vision
Spring 2017
Dr. Heng Huang
[
Administrative Basics
|
Course Description
|
Syllabus
]
Administrative Basics
Meeting time
PH 207 | Mo 4:00PM-6:50PM
Instructor
Heng Huang | ERB 533 | Office hours: Mon and Wed 2pm-4pm
Request
CSE6363 Machine Learning; Optimization; Statistics.
Good notes
for reading
Submodular Optimization
Learning with Submodular Functions: A Convex Optimization Perspective
Practical Optimization
Online Convex Optimization
Stochastic Gradient Descent Tricks
Survey ADMM Paper
Deep Learning in Neural Networks: An Overview
Good books
for reading
Convex Optimization
Introductory Lectures on Convex Programming
Numerical Optimization
Efficient Methods in Convex Programming
Course Description
In this course, we will study the cutting-edge advanced research topics in machine learning and data mining by reading and discussing a set of research papers. The main objective of this course is to cover the underlying mathematical concepts and representative algorithms, paper reading, and implementation.
Syllabus
Week 1 (Jan. 23):
NMF lecture (Hongchang Gao)
Week 2 (Jan. 30):
SVM Optimization (Xiaoqian Wang)
Week 3 (Feb. 6):
No class. Instructor will attend AAAI conference
Week 4 (Feb. 13):
Deep Learning (De Wang)
Week 5 (Feb. 20):
Deep Learning (Kamran Ghasedi)
Week 6 (Feb. 27):
Michail Theofanidis,
Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection
Michail Theofanidis,
Deep networks for motor control functions
Week 7 (Mar. 6):
Ashwin Ramesh Babu,
Sketch Tokens: A learned Mid-level Representation or Contour and Object Detection
Zhifei Deng,
Scaling Distributed Machine Learning with the Parameter Server
Week 8 (Mar. 13):
Spring Break
Week 9 (Mar. 20):
Jianjin Deng,
Efficient Mini-batch Training for Stochastic Optimization
Qicheng Wang,
Pegasos: Primal Estimated sub-GrAdient SOlver for SVM
Week 10 (Mar. 27):
Ashwin RameshBabu
Xin Miao,
Generative Adversarial Nets
Lin Yan,
Two-Manifold Problems with Applications to Nonlinear System Identification
Week 11 (Apr. 3):
Sanika Gupta,
Online Instrumental Variable Regression with Applications to Online Linear System Identification
Zhifei Deng,
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Jianjin Deng,
Efficient Mini-batch Training for Stochastic Optimization
Week 12 (Apr. 10):
Sanika Gupta,
Deep Visual Analogy-Making
Xin Miao,
Fast and Robust Parallel SGD Matrix Factorization
Lin Yan,
Scalable Machine Learning Approaches for Neighborhood Classification Using Very High Resolution Remote Sensing Imagery
Week 13 (Apr. 17):
Jianjin Deng
Qicheng Wang,
Stochastic Optimization with Importance Sampling for Regularized Loss Minimization
Neelabh Pant,
Artificial Neural Network Travel Time Prediction Model for Buses Using Only GPS Data
Week 14 (Apr. 24):
Rodrigo Linhares,
Action-Conditional Video Prediction using Deep Networks in Atari Games
Rodrigo Linhares,
Multiview Triplet Embedding: Learning Attributes in Multiple Maps
Neelabh Pant,
Traffic Flow Prediction With Big Data: A Deep Learning Approach
Week 15 (May 1):
Shirin Shirvani,
GraphChi: Large-Scale Graph computation on Just a PC
Shirin Shirvani,
Collaborative Deep Learning for Recommender Systems
Qicheng Wang,
Pegasos: Primal Estimated sub-GrAdient SOlver for SVM
Paper List
First Category: Most papers in the first category are easier to read than papers in the second category
Computer Vision Applications
Sparse Subspace Clustering with Missing Entries
Deep Visual Analogy-Making
(Sanika Gupta)
Action-Conditional Video Prediction using Deep Networks in Atari Games
(Rodrigo Linhares)
Latent Semantic Representation Learning for Scene Classification
Clustering
Multi-view Sparse Co-clustering via Proximal Alternating Linearized Minimization
Yinyang K-Means: A Drop-In Replacement of the Classic K-Means with Consistent Speedup
Parallel Correlation Clustering on Big Graphs
Fast Distributed k-Center Clustering with Outliers on Massive Data
Clustering and Projected Clustering with Adaptive Neighbors
Differentially Private Subspace Clustering
Feature Selection
Multiview Triplet Embedding: Learning Attributes in Multiple Maps
(Rodrigo Linhares)
Longitudinal LASSO: Jointly Learning Features and Temporal Contingency for Outcome Prediction
Supervised Learning
Scalable Machine Learning Approaches for Neighborhood Classification Using Very High Resolution Remote Sensing Imagery
(Lin Yan)
Optimal Action Extraction for Random Forests and Boosted Trees
Learning with Similarity Functions on Graphs using Matchings of Geometric Embeddings
Generative Adversarial Nets
(Xin Miao)
System
Scaling Distributed Machine Learning with the Parameter Server
(Zhifei Deng)
GraphChi: Large-Scale Graph computation on Just a PC
(Shirin Shirvani)
PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs
Stochastic Optimization
Efficient Mini-batch Training for Stochastic Optimization
(Jianjin Deng)
Large-Scale Distributed Bayesian Matrix Factorization using Stochastic Gradient MCMC
Scaling Up Stochastic Dual Coordinate Ascent
SVM Optimization
Pegasos: Primal Estimated sub-GrAdient SOlver for SVM
(Qicheng Wang)
Trust Region Newton Method for Large-Scale Logistic Regression
Coordinate Descent Method for Large-scale L2-loss Linear Support Vector Machines
Artificial Intelligence
Online Instrumental Variable Regression with Applications to Online Linear System Identification
(Sanika Gupta)
A Spectral Learning Approach to Range-Only SLAM
Two-Manifold Problems with Applications to Nonlinear System Identification
(Lin Yan)
Recommender Systems
Matrix Completion with Queries
Fast and Robust Parallel SGD Matrix Factorization
(Xin Miao)
Collaborative Deep Learning for Recommender Systems
(Shirin Shirvani)
Second Category: You need better machine learning research background
Distributed Optimization
PASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate Descent
Distributed Box-Constrained Quadratic Optimization for Dual Linear SVM
Adding vs. Averaging in Distributed Primal-Dual Optimization
Distributed Learning
Communication Efficient Distributed Machine Learning with the Parameter Server
Stochastic Algorithm
Stochastic Optimization with Importance Sampling for Regularized Loss Minimization
(Qicheng Wang)
Stochastic Dual Coordinate Ascent with Adaptive Probabilities
(Zhifei Deng)
Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization
Variance Reduced Stochastic Gradient Descent with Neighbors
Beyond Convexity: Stochastic Quasi-Convex Optimization
Classification:
Stochastic Optimization with Importance Sampling for Regularized Loss Minimization
Sparse Local Embeddings for Extreme Multi-label Classification
On the Optimality of Classifier Chain for Multi-label Classification
The Coherent Loss Function for Classification
Feature Learning:
Multi-Layer Feature Reduction for Tree Structured Group Lasso via Hierarchical Projection
Statistical and Algorithmic Perspectives on Randomized Sketching for Ordinary Least-Squares
On p-norm Path Following in Multiple Kernel Learning for Non-linear Feature Selection
Submodular
Structured sparsity-inducing norms through submodular functions
Parallel Double Greedy Submodular Maximization
Third Category: If you want to select papers different to the above papers, please send me your selected papers for checking. You should select papers from top conferences or journals, which were held within past three years.