SOCAL MACHINE LEARNING SYMPOSIUM
University of California, Los Angeles
03/15/2019
Introduction
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.
SCHEDULE
Morning
8:00-9:00 Registration
9:00-9:10 Welcome
9:10-9:50 Invited Talk: Learning-driven Algorithms for Discrete Optimization by Bistra Dilkina (USC)
9:50-10:00 Q&A, Discussion
10:00-10:15 Contributed Talk: Synthesized Policies for Transfer and Adaptation across Tasks and Environments by Liyu Chen
10:15-10:30 Contributed Talk: The Forest Mixture Bound by Neal Lawton
10:30-11:00 Coffee Break and poster setup
11:00-11:40 Invited talk: by Alex Smola (AWS)
11:40-11:50 Q&A, Discussion
11:50-12:05 Contributed Talk: What relations are reliably embeddable in Euclidean space? by Robi Bhattacharjee
Afternoon
12:05-2:00 Lunch and first poster session
2:00-2:40 Invited Talk: Emergence of analogy from relation learning: From computational models to the brain by Hongjing Lu (UCLA Departments of Psychology & Statistics)
2:40-2:50 Q&A, Discussion
2:50-3:05 Contributed Talk: A General Framework for Multi-fidelity Bayesian Optimization with Gaussian Processes by Jialin Song
3:05-3:20 Contributed Talk: Minimizing Regularized Cholesky Score for Learning Topological Sorts of Directed Acyclic Graphs by Qiaoling Ye
3:20-3:40 Coffee Break
3:40-4:05 Invited talk: Regulating the Age of Artificial Intelligence by Alicia Solow-Niederman (UCLA School of Law)
4:05-4:20 Q&A, Discussion
4:20-5:00 Invited Talk: Visipedia: combining data, machines and experts to distill knowledge and offer truth to the people by Pietro Perona (Caltech)
5:00-6:30 Second poster session
INVITED SPEAKERS
WiSE Gabilan Assistant Professor and Assistant Professor of Computer Science
University of Southern California (USC)
Allen E. Puckett Professor of Electrical Engineering
California Institute of Technology (Caltech)
Professor
Departments of Psychology & Statistics
University of California, Los Angeles (UCLA )
REGISTRATION
Click here (closed)
ATTENDING
Event Location: The Mong Auditorium
Address: 404 Westwood Boulevard Los Angeles, CA 90095
Visitors can access Wi-Fi the on UCLA_WEB Network.
KEY DATES
Abstract Submission Deadline: February 27 2019, 11:59 PM PST (extended)
Registration Deadline: March 11 2019, 11:59 PM PST (subject to availability)
Workshop: March 15, 2019
ACCEPTED POSTERS
- Bowen Zhang, Hexiang Hu and Fei Sha. Cross-Modal and Hierarchical Modeling of Video and Text
- Denise Rava and Jelena Bradic. Causal quantile learner: robust inference for structural equation models.
- Yuqian Zhang and Jelena Bradic. High-dimensional semi-supervised learning: in search for optimal inference of the mean
- Robi Bhattacharjee and Sanjoy Dasgupta. What relations are reliably embeddable in Euclidean space?
- Eunjeong Stella Koh and Shlomo Dubnov. Information Dynamics in Machine Generated Music
- Weijia Shi, Andy Shih, Adnan Darwiche and Arthur Choi. Compiling (Convolutional) Neural Networks into Tractable Boolean Circuits
- Ziniu Hu and Yizhou Sun. Few-Shot Representation Learning for Long-Tail Words
- Sébastien M. R. Arnold, James A. Preiss, Chen-Yu Wei and Marius Kloft. Understanding the Variance of Policy Gradient Estimators in Reinforcement Learning
- Changjun Fan and Yizhou Sun. Deep reinforcement learning for network dismantling
- Yitao Liang and Guy Van den Broeck. Learning Logistic Circuits
- Liyu Chen, Hexiang Hu, Boqing Gong and Fei Sha. Synthesized Policies for Transfer and Adaptation across Tasks and Environments
- Yanli Liu, Fei Feng, Yunbei Xu and Wotao Yin. Acceleration of Primal-dual Methods and Stochastic Variance Reduction Methods by Inexact Preconditioning
- Brian Hill, Robert Brown, Eilon Gabel, Nadav Rakocz, Maxime Cannesson, Sriram Sankararaman, Ira Hofer and Eran Halperin. An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data
- Moustafa Alzantot, Ziqi Wang and Mani Srivastava. Audio Spoofing Detection using Residual Networks
- Mu Qiao, Tony Zhang, Cristina Segalin, Sarah Sam, Pietro Perona and Markus Meister. Iterative latent strategy inference during learning with high-throughput automated mice training
- S. Jalil Kazemitabar and Arash A. Amini. Approximately Identifying the Optimal Epidemic Source in Complex Networks
- Yujia Shen, Haiying Huang, Arthur Choi and Adnan Darwiche. Compiling Testing Arithmetic Circuits
- Qiaoling Ye, Arash A. Amini and Qing Zhou. Minimizing Regularized Cholesky Score for Learning Topological Sorts of Directed Acyclic Graphs
- Amir Feghahati, Christian Shelton and Michael Pazzani. Explaining Black Box Models
- Chengkuan Hong and Christian Shelton. Convolutional Deep Exponential Families
- Safa Cicek and Stefano Soatto. Input and Weight Space Smoothing for Semi-supervised Learning
- Zeyu Li, Jyun-Yu Jiang, Yizhou Sun and Wei Wang. Personalized Question Routing via Heterogeneous Network Embedding
- Alessandro Achille, Matteo Rovere and Stefano Soatto. Critical Learning Periods in Deep Networks
- Florian Wenzel, Stephan Mandt and Marius Kloft. Scalable Feature Extraction in Confounded Data
- Dongruo Zhou and Quanquan Gu. Lower Bounds for Smooth Nonconvex Finite-Sum Optimization
- Anil Ramakrishna and Rahul Gupta. Approximating Parameters of a Distributively Trained Model using Supervised Learning
- Jingyi Xu, Zilu Zhang, Tal Friedman, Yitao Liang and Guy Van den Broeck. A Semantic Loss Function for Deep Learning with Symbolic Knowledge
- Yuan Cao and Quanquan Gu. A Generalization Theory of Gradient Descent for Learning Over-parameterized Deep ReLU Networks
- Yanchao Yang, Antonio Loquercio, Davide Scaramuzza and Stefano Soatto. Unsupervised Moving Object Detection via Contextual Information Separation
- Shay Deutsch, Stefano Soatto and Andrea Bertozzi. Zero Shot Learning with the Isoperimetric Loss
- Mehran Ghamaty and Christian Shelton. Bootstrapped ensemble model for point processes
- Pasha Khosravi, Yitao Liang, Yoojung Choi and Guy Van den Broeck. What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Features
- Yanchao Yang and Stefano Soatto. Conditional Prior Networks for Optical Flow
- Difan Zou, Yuan Cao, Dongruo Zhou and Quanquan Gu. Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks
- Yunsheng Bai, Hao Ding, Song Bian, Ting Chen, Yizhou Sun and Wei Wang. SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
- Alireza Abdoli, Amy Murillo, Alec Gerry and Eamonn Keogh. Fitbit for Chickens: Time Series Classification to Improve Poultry Welfare
- Hoang Le, Cameron Voloshin and Yisong Yue. Batch Policy Learning under Multiple Constraints
- Neal Lawton, Greg Ver Steeg and Aram Galstyan. The Forest Mixture Bound
- Mehrnoosh Mirtaheri, Sami Abu-El Haija, Fred Morstatter, Greg Ver Steeg and Aram Galstyan. Identifying and Analyzing Cryptocurrency Manipulations in Social Media
- Rob Brekelmans, Daniel Moyer, Aram Galstyan and Greg Ver Steeg. Exact Rate-Distortion in Autoencoders via Echo Noise
- Fidel Pena, Pedro Fernan, Tsang Ren and Alexandre Cunha. Instance Segmentation of Biological Cells under Weakly Supervised Conditions
- Jacob Fauber. Modeling “Presentness” of Electronic Health Record Data to Improve Patient State Estimation
- Ting Chen and Yizhou Sun. Learning to Quantize with Gradient Descent
- Sami Abu-El-Haija, Rob Brekelmans, Greg Ver Steeg, Aram Galstyan and Marius Kloft. Meta-Learning Algorithm for Backpropagating Sample Importance
- Jialin Song, Yuxin Chen and Yisong Yue. A General Framework for Multi-fidelity Bayesian Optimization with Gaussian Processes
- Deepesh Data, Linqi Song and Suhas Diggavi. Data Encoding Methods for Byzantine-Resilient Distributed Optimization
- Yujia Shen, Anchal Goyanka, Adnan Darwiche and Arthur Choi. Structured Bayesian Networks: From Inference to Learning with Routes
- Lev Tauz and Lara Dolecek. Multi-Message Gradient Coding for Communication Efficient Utilization of Non-Persistent Stragglers
- Pablo Tostado, Bruno Pedroni and Gert Cauwenberghs. Performance Trade-offs in Weight Quantization for Memory-Efficient Inference
- Bruno Umbria Pedroni, Sadique Sheik, Hesham Mostafa, Somnath Paul, Charles Augustine and Gert Cauwenberghs. Small-footprint Spiking Neural Networks for Power-efficient Keyword Spotting
- Yiqin Wang, Atharva Padhye, Tomohiro Maeda, Ramesh Raskar and Achuta Kadambi. Imaging around Corners using Physics-informed Machine Learning
- Yunhao Ba, Rui Chen, Yiqin Wang, Xuezhen Wang, Alex Gilbert, Lei Yan, Boxin Shi, and Achuta Kadambi. Polarization Based Surface Normal Recovery with Physics and Deep Learning
- Kevin Lee, Siddharth Somasundaram, Yifan You, Guangyuan Zhao and Achuta Kadambi. Plenoptic-10: Vision under high dimensional physics
- Surabhi Kalyan, Siddharth Joshi, Sadique Sheik, Bruno U. Pedroni and Gert Cauwenberghs. Unsupervised Synaptic Pruning Strategies for Restricted Boltzmann Machines
AWARDS
AWS Best Poster Awards: $1000 and $750 cloud credits
- Sébastien M. R. Arnold, James A. Preiss, Chen-Yu Wei and Marius Kloft. Understanding the Variance of Policy Gradient Estimators in Reinforcement Learning
- Yunhao Ba, Rui Chen, Yiqin Wang, Xuezhen Wang, Alex Gilbert, Lei Yan, Boxin Shi, and Achuta Kadambi. Polarization Based Surface Normal Recovery with Physics and Deep Learning
AWS Nominated Paper Award: $250 cloud credits
- Yanchao Yang and Stefano Soatto. Conditional Prior Networks for Optical Flow
- Yiqin Wang, Atharva Padhye, Tomohiro Maeda, Ramesh Raskar and Achuta Kadambi. Imaging around Corners using Physics-informed Machine Learning
- Qiaoling Ye, Arash A. Amini and Qing Zhou. Minimizing Regularized Cholesky Score for Learning Topological Sorts of Directed Acyclic Graphs
- Zeyu Li, Jyun-Yu Jiang, Yizhou Sun and Wei Wang. Personalized Question Routing via Heterogeneous Network Embedding
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. Abstracts can describe published work. We invite submissions of 1 to 2-pages in NeurIPS format.
Contributions should be submitted by February 27 on the workshop's easychair page .
POSTER INSTRUCTIONS
We recommend poster dimensions to be less than 48" X 48". All posters will be presented in both poster sessions to leave ample time for discussion.
SPONSORED BY
ORGANIZERS
Guy Van den Broeck, Assistant Professor, University of California, Los Angeles
Sriram Sankararaman, Assistant Professor, University of California, Los Angeles