SOCAL MACHINE LEARNING SYMPOSIUM
UNIVERSITY OF SOUTHERN CALIFORNIA (USC)
OCTOBER 6, 2017
The Southern California Machine Learning Symposium brings together students and faculty to promote machine learning in the southern California region. The workshop serves as a forum for researchers from a variety of fields working on machine learning to share and discuss their latest findings.
Topics to be covered at the SoCal ML symposium include but are not limited to:
- Machine learning with graphs, social networks, and structured data.
- Active learning, reinforcement learning, crowdsourcing.
- Learning with images and natural language.
- Learning with high-dimensional data.
- Neural networks, deep learning, and graphical models.
- Learning dynamic and streaming data.
- Applications to interesting new domains.
- Addressing each of these issues at scale.
- New, open, or unsolved problems in machine learning theory or applications.
The majority of workshop will be focused on student and postdoc contributions, in the form of contributed talks and posters.
7:30am-8:20am: Check-in; Breakfast; poster setup
8:20am - 8:30am: Opening Remarks
8:30am - 9:15am: Machine Learning @ Amazon by Daniel Marcu (Amazon)
9:25am - 10:10am: Diverse Particle Selection for High-Dimensional Inference in Graphical Models by Erik Sudderth (UCI)
10:10am - 10:40am: Coffee break; Setup and view Poster
10:45am - 11:30am: New Frontiers in Imitation Learning by Yisong Yue (Caltech)
11:40am - 12:10pm: Contributed Talk by Alessandro Achille ( UCLA)
12:15pm - 12:45pm: Contributed Talk by Eric Nalisnick (UCI)
12:45pm - 1:45pm: Lunch
1:00pm - 1:45pm: Randomized Iterative Methods and Complexity for Markov Decision Process by Mengdi Wang (Princeton)
1:45pm - 2:30pm: Face Processing as a Case Study of Complex Information Processing in Humans by Angela Yu ( UCSD)
2:40pm - 3:25pm: Coordinate Descent Methods by Wotao Yin (UCLA)
3:25pm- 4:45pm: Coffee break , Poster session
4:45pm - 5:30pm: Keynote Talk by Joseph Lim (USC)
5:40pm - 6:25pm: Keynote Talk by Jia Deng (University of Michigan)
6:25pm - 6:30pm: Closing Remarks
- Modeling the Peripheral Bias in Scene Recognition. Garrison Cottrell and Panqu Wang.
- Distribution-Free, Size Adaptive Submatrix Detection with Acceleration. Yuchao Liu and Jiaqi Guo.
- Reinforcement Learning for Knowledge Graph Reasoning. Wenhan Xiong, Thien Hoang and William Wang.
- Analyzing the Robustness of Nearest Neighbors to Adversarial Examples. Yizhen Wang, Somesh Jha and Kamalika Chaudhuri.
- Recurrent Scene Parsing with Perspective Understanding in the Loop. Shu Kong and Charless Fowlkes.
- Boosting Variational Inference with Latent Particles. Eric Nalisnick and Padhraic Smyth.
- Natural image restoration via the hierarchical Dirichlet process. Geng Ji, Michael Hughes and Erik Sudderth.
- Approximation and Convergence Properties of Generative Adversarial Learning. Shuang Liu, Olivier Bousquet and Kamalika Chaudhuri.
- The Amortized Bootstrap. Eric Nalisnick and Padhraic Smyth.
- Emergence of Invariance and Disentangling in Deep Representations. Alessandro Achille and Stefano Soatto.
- Incremental Kernel Spectral Regression with Fixed-size Memory. Irma Ravkic and Fabien Scalzo.
- Bayesian Disease Progression Modeling of Alzheimer's Disease. Arya Pourzanjani, Benjamin Bales, Michael Harrington and Linda Petzold.
- Patient-Specific Pose Estimation in a Clinical Environment. Kenny Chen, Paolo Gabriel, Abdulwahab Alasfour, Werner Doyle, Orrin Devinsky, Daniel Friedman, Thomas Thesen and Vikash Gilja.
- Estimation of the covariance structure of heavy-tailed distributions. Stanislav Minsker and Xiaohan Wei.
- Active Learning from Imperfect Labelers. Songbai Yan, Kamalika Chaudhuri and Tara Javidi.
- Prediction of Sparse User-Item Consumption Rates with Zero-Inflated Poisson Regression. Moshe Lichman and Padhraic Smyth.
- Pufferfish Privacy Mechanisms for Correlated Data. Shuang Song, Yizhen Wang and Kamalika Chaudhuri.
- Contextual Dependence of Human Face Processing: A Bayesian Statistical Account. Chaitanya Ryali and Angela Yu.
- Convolutional Neural Networks for Electron Neutrino and Electron Energy Reconstruction in the NOvA Detectors. Lingge Li, Lars Hertel, Pierre Baldi and Jianming Bian.
- Estimating Feature Gradients with Convolutional Neural Networks for Longitudinal Data and Discrete Targets. Alex Parret.
- Statistical Modeling of the Social Perception of Faces. Chaitanya K. Ryali, Jinyan Guan, Girish Bathala, Yihan Zhang and Angela J. Yu.
- MuMIE: Multi-Modal Information Extraction. Robert Logan and Sameer Singh.
- Short-range quantitative precipitation forecasting using Deep Learning approaches. Ata Akbari Asanjan, Tiantian Yang, Xiaogang Gao, Kuolin Hsu and Soroosh Sorooshian.
- Noisy Diameter-Based Active Learning. Christopher Tosh.
- Context Embedding Networks. Kun Ho Kim, Oisin Mac Aodha and Pietro Perona.
- Neural variational message passing. Sharad Vikram.
- Rényi Differential Privacy Mechanisms for Posterior Sampling. Joseph Geumlek, Shuang Song and Kamalika Chaudhuri.
- Online Learning and Control using Sparse Local Gaussian Processes for Teleoperation. Brian Wilcox and Michael Yip.
- Deep Model-Based Reinforcement Learning with Structured Latent Representations. Sharad Vikram.
- DECADE: A Deep Metric Learning Model for Multivariate Time Series. Zhengping Che, Xinran He, Ke Xu and Yan Liu.
- Federated Multi-task Learning. Virginia Smith, Chao-Kai Chiang, Maziar Sanjabi and Ameet Talwalkar.
- Leveraging Context To Improve Machine Learning Classifications Of Marine Zooplankton. Jeffrey Ellen.
- Long Range Rover Navigation with Imitation Learning and Value Iteration Networks. Max Pflueger and Ali-Akbar Agha-Mohammadi.
- Using a Cognitive Model to Combine Probability Estimates. Irina Danileiko and Michael Lee.
- TreeWeight: local learning with tree-based ensembles. Denali Molitor, Ameet Talwalkar, Adam Bloniarz, Brooke Wenig and Christopher Wu.
- Fast Multiple Testing Correction via Data-Parallel Permutation Testing in GWAS. Nolan Donoghue, Ameet Talwalkar and Sriram Sankararaman.
- Variable Importance using Decision Trees. Arash A. Amini, Ameet Talwalkar, Seyed Jalil Kazemitabar and Adam Bloniarz.
- User Performance Predictions in Cognitive Training. Sanjana Sandeep, Christian Shelton and Aaron Seitz.
- Compact Factorization of Matrices Using Generalized Round-Rank. Pouya Pezeshkpour, Carlos Guestrin and Sameer Singh.
- Generating Natural Adversarial Examples. Zhengli Zhao, Dheeru Dua and Sameer Singh.
- DeepLung: 3D Deep Convolutional Networks for Fully Automatic Lung CT Cancer Diagnosis. Wentao Zhu, Chaochun Liu, Wei Fan and Xiaohui Xie.
- Parle: parallelizing stochastic gradient descent. Pratik Chaudhari, Carlo Baldassi, Riccardo Zecchina, Stefano Soatto and Ameet Talwalkar.
- Proximal-Proximal-Gradient Method. Ernest Ryu and Wotao Yin.
- Merging Neural Networks. Mike Izbicki and Christian Shelton.
- Deep Residual Networks with Bottom-up Attention. Tommaso Furlanello, Anima Anandkumar and Laurent Itti.
- Sampling over Search Trees Using Abstractions. Rina Dechter, Filjor Broka, Kalev Kask and Alexander Ihler.
- Medical Time Series to Concepts. Sanjay Purushotham, Bo Jiang, Zhengping Che and Yan Liu.
- A Deep Structured Learning Approach for Image Segmentation. Seyed Sajjadi and Alexandre Cunha.
- On the Behavior of the Expectation-Maximization Algorithm for Mixture Models. Babak Barazandeh and Meisam Razaviyayn.
- More Iterations per Second, Same Quality -- Why Asynchronous Algorithms may Drastically Outperform Traditional Ones. Robert Hannah and Wotao Yin.
- Example-Based Explanations using Graph Convolutional Neural Networks. Rushil Anirudh, Jayaraman J. Thiagarajan, Rahul Sridhar and Peer-Timo Bremer.
- Learning Deep Models: Critical Points and Local Openness. Maher Nouiehed, Meisam Razaviyayn and Jong-Shi Pang.
- Neural Coding of Facial Features Underlying Social Perception of Faces. Jingya Huang, Jianling Liu, Dalin Guo, Chaitanya K. Ryali, Jinyan Guan and Angela J. Yu.
- Hashing de Novo Long-Reads for Transcriptome Recovery with Binary Neural Networks. S. Karen Khatamifard, Meisam Razaviyayn and Ulya R. Karpuzcu.
- Human Learning and Decision-making in the Multi-Armed Bandit Task. Dalin Guo and Angela J. Yu.
- Parallelizing Hyperband for Large-Scale Tuning. Lisha Li, Kevin Jamieson, Afshin Rostamizadeh and Ameet Talwalkar.
- Self-Imitation Learning for Solving Mixed Integer Linear Programming Problems. Jialin Song, Ravi Kiran, Albert Zhao, Masahiro Ono and Yisong Yue.
- MCMC Methods for Tractable Inference on Medical Time Series in PCIMs. Jacob Fauber
CALL FOR PAPERS
We invite contributions in the form of extended abstracts, which will be lightly reviewed prior to selection for inclusion in the workshop. Contributions that are selected for inclusion will be presented during a poster session, with some contributions being selected for oral presentation. We invite submissions of 1 to 2-pages in NIPS format.
Contributions should be submitted by August 31 on the workshop's easychair page .
Directions to USC: Click here
Public Transportation: Click here
Public Parking: Parking on campus is currently $12. Metered parking is available in the Parking Center for $1.00 per hour. Four- and two-hour metered parking is available on streets near USC. More information here.
Hotel Accommodations: The Radisson Hotel is located adjacent to the main campus and is within easy walking distance to the venue. To contact Radisson Hotel: click here. For other nearby hotels: click here.
Abstract Submission Deadline: August 31, 2017, 11:59 PM PST
Notification: September 10, 2017, 11:59 PM PST
Registration Deadline: October 1, 2017, 11:59 PM PST
Workshop: October 6, 2017
Please send questions and enquiries to -> socalml-organizers at googlegroups dot com