• Negar Rostamzadeh
  • October 28, 2016

Welcome to WiML 2017! Both of our poster sessions (Mon Dec 4, 12.20pm – 2.00pm and Thursday Dec 7, 4:40 pm – 6:05 pm) are open to WiML and NIPS attendees. For printable version of this information, see our program book.

Sunday

12:00 – 14:00 – Registration Desk Opens

19:00 – 22:30 – Pre Workshop Dinner (Optional). Separate Registration Required

Monday

All events are held in Room 104, except for the poster session, which takes place in the Pacific Ballroom

9:00 – 12:00 – Registration Desk Opens

11:00 – 11:15 – Opening Remarks – Jenn Wortman Vaughan Microsoft Research. Co-Founder of WiML.

11:15 – 11:50 – Invited Talk – Tamara Broderick MIT. Bayesian machine learning: Quantifying uncertainty and robustness at scale

11:50 – 12:10 – Contributed Talk: Aishwarya Unnikrishnan, Indraprastha Institute of Information Technology Delhi. Towards Communication-Centric Multi-Agent Deep Reinforcement Learning for Guarding a Territory Game. [Abstract]

12:10 – 12:30 – Contributed Talk: Peyton Greenside, Stanford University. Graph convolutional networks can encode three-dimensional genome architecture in deep learning models for genomics. [Abstract]

12:30 – 14:00 – Lunch + Poster Session 

14:00 – 14:35 – Invited Talk – Hanna Wallach  Microsoft Research. Machine Learning for Social Science

14:35 – 14:50 – Coffee Break

14:50 – 15:50 – Research and Career Advice Roundtables

15:55 – 16:15 – Contributed Talk: Palak Agarwal, WorldQuant. Fairness Aware Recommendations. [Abstract]

16:15 – 16:35 – Contributed Talk: Victoria Krakovna, DeepMind. Reinforcement Learning with a Corrupted Reward Channel. [Abstract]

16:35 – 16:45 – Closing Remarks

Thursday

All events are held in Room 104, except for the poster session, which takes place in the Pacific Ballroom

10:00 – 14:00 – Registration Desk Opens

12:00 – 12:45 – Lunch

12:45 – 13:05 – Opening Remarks – Raia Hadsell, DeepMind

13:05 – 13:40 – Invited Talk – Joelle Pineau Head Facebook AI Research (Montreal Lab)/ Mc Gill. Improving health-care: challenges and opportunities for reinforcement learning

13:40 – 13:55 – Contributed Talk: Zhenyi Tang, University of Illinois. Harnessing Adversarial Attacks on Deep Reinforcement Learning for Improving Robustness. [Abstract]

13:55 – 14:10 – Contributed Talk: Hoda Heidari, ETH Zurich. A General Framework for Evaluating Callout Mechanisms in Repeated Auctions. [Abstract]

14:10 – 14:20 – Coffee Break

14:20 – 15:20 – Research and Career Advice Roundtable

15:20 – 15:55 – Invited Talk – Nina Mishra Amazon. Time-Critical Machine Learning

15:55 – 16:15 – Contributed Talk: Sarah Bouchat, Nothwestern University. Engaging Experts: A Dirichlet Process Approach to Divergent Elicited Priors in Social Science. [Abstract]

16:15 – 16:35 – Contributed Talk: Nesreen K Ahmed, Intel Labs. Representation Learning in Large Attributed Graphs. [Abstract]

16:35 – 16:40 – Closing Remarks 

16:40 – 18:05 – Poster Session (Coffee and Snacks Served)

[/vc_column_inner][/vc_row_inner]

Invited Talks

 

BioJenn Wortman Vaughan is a Senior Researcher at Microsoft Research, New York City. She studies algorithmic economics and machine learning, with an emphasis on prediction markets, crowdsourcing, and other human-in-the-loop systems. Jenn came to MSR in 2012 from UCLA, where she was an assistant professor in the computer science department. She completed her Ph.D. at the University of Pennsylvania in 2009, and subsequently spent a year as a Computing Innovation Fellow at Harvard. She is the recipient of Penn’s 2009 Rubinoff dissertation award for innovative applications of computer technology, a National Science Foundation CAREER award, a Presidential Early Career Award for Scientists and Engineers (PECASE), and a handful of best paper awards. In her “spare” time, Jenn is involved in a variety of efforts to provide support for women in computer science; most notably, she co-founded the Annual Workshop for Women in Machine Learning, which has been held each year since 2006.

Jenn will be giving our opening remarks on Monday.

BioRaia Hadsell is a research scientist on the Deep Learning team at DeepMind. Her fundamental research interests are in robotics, neural networks, and real-world learning systems. Her research at DeepMind focuses on a number of fundamental challenges in AGI, including continual and transfer learning, deep reinforcement learning, and neural models of navigation.

Raia will be giving our opening remarks on Thursday.

BioTamara Broderick is the ITT Career Development Assistant Professor in the Department of Electrical Engineering and Computer Science at MIT. Her work is in the areas of statistics and machine learning. Before joining MIT, she completed her PhD in Statistics at UC Berkeley in 2014 with Professor Michael I. Jordan. Her research interests are in Bayesian inference and graphical models—with an emphasis on scalable, nonparametric, and unsupervised learning. She has been awarded a Google Faculty Research Award, the ISBA Lifetime Members Junior Researcher Award, the Savage Award (for an outstanding doctoral dissertation in Bayesian theory and methods), the Evelyn Fix Memorial Medal and Citation (for the Ph.D. student on the Berkeley campus showing the greatest promise in statistical research), the Berkeley Fellowship, an NSF Graduate Research Fellowship, a Marshall Scholarship, and the Phi Beta Kappa Prize (for the graduating Princeton senior with the highest academic average).

Title: Bayesian machine learning: Quantifying uncertainty and robustness at scale

Bio: Hannah Wallach Hanna Wallach is a Senior Researcher at Microsoft Research New York City and an Adjunct Associate Professor in the College of Information and Computer Sciences  at the University of Massachusetts Amherst. She is also a member of UMass’s Computational Social Science Institute. Hanna develops machine learning methods for studying the structure, content, and dynamics of social processes. Her work is inherently interdisciplinary: she collaborates with political scientists, sociologists, and journalists to understand how organizations work by analyzing publicly available interaction data, such as email networks, document collections, press releases, meeting transcripts, and news articles. To complement this agenda, she also studies issues of fairness, accountability, and transparency as they relate to machine learning. Hanna’s research has had broad impact in machine learning, natural language processing, and computational social science. In 2014, she was named one of Glamour magazine’s “35 Women Under 35 Who Are Changing the Tech Industry”; in 2015, she was selected to the International Machine Learning Society’s Board of Trustees; in 2016, she was named co-winner of the 2016 Borg Early Career Award; and in 2017, she is serving as program co-chair for
NIPS. She is the recipient of several National Science Foundation grants, an Intelligence Advanced Research Projects Activity grant, and a grant from the Office of Juvenile Justice and Delinquency Prevention. Hanna is committed to increasing diversity and has worked for over a decade to address the under-representation of women in computing. She co-founded two projects—the first of their kind—to increase women’s involvement in free and open source software development: Debian Women and the GNOME Women’s Summer Outreach Program. She also co-founded the annual Women in Machine Learning Workshop, which is now in its twelfth year. Hanna holds a BA in computer science from the University of Cambridge, an MSc in cognitive science and machine learning from the University of Edinburgh, and a PhD in machine learning from the University of Cambridge.

Title: Machine Learning for Social Science

Abstract: In this talk, I will introduce the audience to the emerging area of computational social science, focusing on how machine learning for social science differs from machine learning in other contexts. I will then present Bayesian Poisson tensor decomposition — a general framework for uncovering latent structure from large-scale, digital archives of discrete data (such as networks and text). I will focus on one particular model for measuring latent community structure from country-to-country interaction data. Finally, I will talk briefly about the broader ethical implications of analyzing social data.

Bio: Joelle Pineau is a professor of  Computer Science at McGill University where she co-directs the Reasoning and Learning Lab. This year she has been appointed the head Facebook AI Research’s new research lab in Montreal. Dr. Pineau’s research focuses on developing new models and algorithms for planning and learning in complex partially-observable domains. She also works on applying these algorithms to complex problems in robotics, health care, games and conversational agents. She serves on the editorial board of the Journal of Artificial Intelligence Research and the Journal of Machine Learning Research and is currently President of the International Machine Learning Society. She is a Senior Fellow of the Canadian Institute for Advanced Research and in 2016 was named a member of the College of New Scholars, Artists and Scientists by the Royal Society of Canada.

Title: Improving health-care: challenges and opportunities for reinforcement learning

Abstract:  Reinforcement learning offers a powerful paradigm for automatically discovering and optimizing sequential treatments for chronic and life-threatening diseases. In particular, we will focus on how data collected in multi-stage sequential trials can be used to automatically generate treatment strategies that are tailored to patient characteristics and time-dependent outcomes. We will also examine promising methods to improve the efficiency of clinical trials through adaptation. Examples will be drawn from ongoing research projects on developing new treatment strategies for epilepsy and cancer.

BioNina Mishra is a Principal Scientist at Amazon and a visiting scholar at Stanford. She has many years of experience leading projects in industry at Amazon, Microsoft Research and HP Labs, as well as academia as Associate Professor at the University of Virginia and Acting Faculty at Stanford University. Her research interests are in data science, data mining, web search, machine learning and privacy. The projects that she pursues encompass the design and evaluation of new data mining algorithms on real, colossal-sized datasets. She has authored ~50 publications in top venues including: Web Search: WWW, WSDM, SIGIR; Machine Learning: ICML, NIPS, AAAI, COLT; Databases: VLDB, PODS; Cryptography: CRYPTO, EUROCRYPT; Theory: FOCS and SODA. Her research publications received external recognition: best paper award nomination, algorithm in Wikipedia and taught in graduate courses around the world. Also, her research has had product implications at Microsoft, specifically in the Bing search engine, and was featured in external press coverage including New Scientist, ACM TechNews, IEEE Computing Now, Search Engine Land and Microsoft Research. She’s been granted 14 patent applications with a dozen more still in the application stage. Her service to the community includes: serving on journal editorial boards Machine Learning, Journal of Privacy and Confidentiality, IEEE Transactions on Knowledge and Data Engineering and IEEE Intelligent Systems; chairing the premier machine learning conference ICML in 2003, as well as numerous program committees for web search, data mining and machine learning conferences.

Title: Time-Critical Machine Learning

Abstract: Machine learning algorithms are now being used to help people in real time.   In some situations, data is continuously streaming and discovering actionable insights in real time is crucial.  Examples include monitoring heart activity, detecting falls or alerting for changes in air, water or food quality.  We focus on one kind of insight — anomaly detection.  In other situations, we show how people rely on technology in life-critical moments.  We show how machine learning algorithms and sensors can together be used to help in urgent scenarios

[/vc_column_inner][/vc_row_inner]

Mentorship Roundtables - Monday 4th December

This year we have four categories of mentorship roundtables: Research Roundtables (Tables 1-22), Career Advice Roundtables (Tables 23-42), NIPS Paper Discussion (Tables 43-50), Company Career Tables (Tables 51-63). On Monday 4th December, these tables will take place at 2:50pm – 3:50pm

Table 1: Reinforcement learning I – Katja Hofmann, Microsoft Research

Table 2: Reinforcement learning II – Oriol Vinyals, DeepMind

Table 3: Deep learning I – Yoshua Bengio, MILA – Université de Montréal

Table 4: Deep learning II – Doina Precup, McGill University / Head DeepMind Montreal

Table 5: Bayesian methods I – Meire Fortunato, DeepMind

Table 6: Bayesian methods II –Neil Lawrence, Amazon Research Cambridge

Table 7: Graphical models – Anima Anandkumar, Amazon Web Services/ Caltech

Table 8: Statistical inference, estimation and Optimization – Irina Kukuyeva, Dia&Co

Table 9: Neuroscience – Katharina Volz, Founder OccamzRazor

Table 10: Robotics I – Bonolo Mathibela, IBM Research

Table 11: Black Box vs Open Box ML Approaches – Barbara Engelhardt, Assistant Professor, Princeton

Table 12: Natural language processing – George Dahl, Google Brain

Table 13: Biological Applications – Luisa Cutillo, University Parthenope of Naples

Table 14: Healthcare/Clinical Applications  – Marzyeh Ghassemi, MIT/Verily

Table 15: Causal Inference and Counterfactuals – Sara Magliacane, IBM Research

Table 16: Computer Vision  – Amy Zhang, Facebook AI Research

Table 17: Fairness, accountability, transparency in ML – Christian Borgs, Microsoft Research

Table 18: Social Sciences Application – Timnit Gebru, Microsoft Research

Table 19: Music Applications – Vidhya Murali, Spotify USA Inc

Table 20: Business Applications – Pallika Kanani, Oracle Labs

Table 21: Industrial Applications in AI/ Commercialising your Research – Jennifer Schumacher, 3M

Table 22: Technical AGI Safety – Victoria Krakovna, DeepMind

Table 23: Creative AI Applications (Art, Music, Design) – Luba Elliott, iambic.a

Table 24: Work-Life Balance (Industry) – Hanna Wallach, Microsoft

Table 25: Work-Life Balance (Academia) – Joelle Pineau, Head Facebook AI Research Montreal/ Professor McGill University

Table 26: Life with Kids / Work-life balance – Caitlin Smallwood

Table 27: Getting a Job (Industry)  – Beth Zeranski, Microsoft

Table 28: Getting a Job (Academic) – Yisong Yue, Caltech/ Tamara Broderick MIT

Table 29: Doing a Postdoc – Adriana Romero, Facebook AI Research

Table 30:  Choosing between Academia and Industry – Daniel Jiang, University of Pittsburgh

Table 31:  Choosing between Academia and Industry – Samy Bengio, Google Brain

Table 32: Doing Research in Industry – Natalia Neverova, Facebook AI Research; Stacey Svetlichnaya, Flickr / Yahoo Research

Table 33: Keeping up with academia while in industry – Nevena Lazic, Google

Table 34: Surviving Graduate School – Lily Hu, Salesforce Research;

Table 35: Establishing Collaborators – Moustapha Cisse, Facebook AI Research

Table 36: Scientific Communication – Chris Bishop, Lab Director Microsoft Research Cambridge

Table 37: Building your Professional Brand – Katherine Gorman, Talking Machines/Collective Next

Table 38: Founding Startups/ Building your Professional Brand – Rachel Thomas, Fast.AI/ University of San Francisco

Table 39: Founding Startups – Philippe Beaudoin, Element AI

Table 40: Early-Stage Start-ups using Machine Learning/Deep Learning – Lisha Li, Amplify Partners

Table 41: Joining Start-ups –  Lavanya Tekumalla, Amazon

Table 42:  Finding Mentors/ Networking – Lisa Amini, Director IBM Research AI

Table 43: Long-term Career Planning – Jennifer Chayes, Managing Director, Microsoft Research NE & NYC

Table 44: NIPS Paper Discussion: SVCCA: Singular Vector Canonical Correlation Analysis for Deep Understanding and Improvement   – Maithra Raghu, Google Brain and Cornell University

Table 45: NIPS Paper Discussion: Self-supervised Learning of Motion Capture – Katerina Fragkiadaki, Carnegie Mellon University

Table 46:  NIPS Paper Discussion: Linear regression without correspondence – Daniel Hsu, Columbia University

 Table 47:  NIPS Paper Discussion: A-NICE-MC: Adversarial Training for MCMC – Jiaming Song, Stanford University

Table 48:  NIPS Paper Discussion: Learning multiple visual domains with residual adapters – Sylvestre-Alvise Rebuffi, University of Oxford

 Table 49:  NIPS Paper Discussion: Efficient Use of Limited-Memory Resources to Accelerate Linear Learning – Celestine Dünner, IBM Research

 Table 50:  NIPS Paper Discussion: Variational Inference via χ Upper Bound Minimization – Adji Bousso Dieng, Columbia University

 Table 51:  NIPS Paper Discussion: Robust Hypothesis Test for Functional Effect with Gaussian Processes – Jeremiah Liu, Harvard University

Table 52:  NIPS Paper Discussion: Bayesian Dyadic Trees and Histograms for Regression  – Stéphanie van der Pas, Leiden University

 Table 52: Careers@ElementAI

Table 53: Careers@Facebook

Table 54: Careers@DeepMind

Table 55: Careers@Capital One

Table 56: Careers@Criteo

Table 57: Careers@Microsoft

Table 58: Careers@Intel

Table 59: Careers@Google

Table 60: Careers@Airbnb

Table 61: Careers@Apple

Table 62: Careers@IBM

Table 63: Careers@NVIDIA

Table 64: Careers@Pandora

 

[/vc_column_inner][/vc_row_inner]

Mentorship Roundtables - Thursday 7th December

This year we have four categories of mentorship roundtables: Research Roundtables (Tables 1-25), Career Advice Roundtables (Tables 26-43), NIPS Paper Discussion (Tables 44-57), Company Career Tables (Tables 51-63). On Thursday 7th December, these tables will take place at 2:20pm – 3:20pm

Table 1: Reinforcement learning I – Raia Hadsell, DeepMind

Table 2: Black Box vs Open Box ML Approaches – Barbara Engelhardt, Assistant Professor, Princeton

Table 3: Deep learning I – Anima Anandkumar, Amazon Web Services/ Caltech

Table 4: Deep learning II – Amy Zhang, Facebook AI Research

Table 5: Bayesian methods I – Chris Bishop, Lab Director Microsoft Research Cambridge

Table 6: Bayesian methods II – Zoubin Ghahramani, University of Cambridge

Table 7: Graphical models – David Blei, Columbia University

Table 8: Generative Models – Ian Goodfellow, Google Brain

Table 9: Technical AGI Safety – Shane Legg, Founder DeepMind

Table 10: Kernel Methods – Corinna Cortes, Head of Google Research

Table 11: Neuroscience – Katharina Volz, Founder OccamzRazor

Table 12: Robotics –

Table 13: Natural language processing – George Dahl, Google Brain

Table 14: Statistical inference and estimation – Timnit Gebru, Microsoft Research

Table 15: Biological Applications – Luisa Cutillo, University Parthenope of Naples

Table 16: Healthcare/Clinical Applications  – Marzyeh Ghassemi, MIT/Verily

Table 17: Optimization  – Irina Kukuyeva, Dia & Co

Table 18: Causal Inference and Counterfactuals – Sara Magliacane, IBM Research

Table 19: Computer Vision – Natalia Neverova, Facebook AI Research;

Table 20: Fairness, accountability, transparency in ML I – Christian Borgs, Microsoft Research

Table 21: Fairness, accountability, transparency in ML II – Nyalleng Moorosi, Council for Scientific and Industrial Research

Table 22: Learning Theory – Hoda Heidari, ETHZ

Table 23: Social Sciences Application – Lise Getoor, UC Santa Cruz

Table 24: Business Applications – Pallika Kanani, Oracle Labs

Table 25: Industrial Applications in AI/ Commercialising your Research – Jennifer Schumacher, 3M

Table 26: Work-Life Balance (Industry) – Amy Nicholson, Olivia Klose, Microsoft

Table 27: Work-Life Balance (Academia) – Neil Lawrence, Amazon Research Cambridge

Table 28: Life with Kids / Work-life balance – Caitlin Smallwood, Netflix

Table 29: Getting a Job (Industry)  – Aleatha Parker-Wood Symantec

Table 30: Getting a Job (Academic) – Yisong Yue, Caltech

Table 31: Doing a Postdoc – Aida Nematzadeh, UC Berkeley

Table 32:  Choosing between Academia and Industry – Daniel Hsu, Columbia University

Table 33:  Choosing between Academia and Industry – Adriana Romero, Facebook AI Research

Table 34: Doing Research in Industry –  Stacey  Svetlichnaya Flickr / Yahoo Research

Table 35: Keeping up with academia while in industry – Chew-Yean Yam, Microsoft

Table 36: Surviving Graduate School – Shruthi Kubatur, Nikon Research Corporation of America

Table 37: Establishing Collaborators/ Long-term Career Planning – Jennifer Chayes, Managing Director, Microsoft Research NE & NYC

Table 38: Scientific Communication – Katherine Gorman, Talking Machines/ Collective Next

Table 39: Building your Professional Brand/ Founding Startups – Rachel Thomas, Fast.AI/ University of San Francisco

Table 40: Founding Startups – Philippe Beaudoin, Element AI

Table 41: Early-Stage Start-ups using Machine Learning/Deep Learning – Lisha Li, Amplify Partners

Table 42: Joining Start-ups –  Lavanya Tekumalla, Amazon

Table 43:  Networking/ Finding Mentors – Muhammad Jamal Afridi, 3M

Table 44:  

Table 45:  NIPS Paper: A-NICE-MC: Adversarial Training for MCMC – Jiaming Song, Stanford University

Table 46:  NIPS Paper: Learning multiple visual domains with residual adapters – Sylvestre-Alvise Rebuffi, University of Oxford

Table 47:  NIPS Paper: Variational Inference via χ Upper Bound Minimization – Adji Bousso Dieng, Columbia University

Table 48: NIPS Paper: A framework for Multi-A(rmed)/B(andit) Testing with Online FDR Control – Fanny Yang, UC Berkley

Table 49: NIPS Paper: Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin – Ritambhara Singh, University of Virginia

Table 50:  NIPS Paper: Style Transfer from Non-parallel Text by Cross-Alignment – Tianxiao Shen, MIT CSAIL

Table 51:  NIPS Paper: Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model  – Devi Parikh, Georgia Tech / Facebook AI Research

Table 52:  

Table 53:  NIPS Paper: Inferring Generative Model Structure with Static Analysis – Paroma Varma, Stanford University

Table 54:  NIPS Paper: Concrete Dropout (Topic: Bayesian Deep Learning)  – Yarin Gal, University of Oxford

Table 55:  NIPS Paper: Do Deep Neural Networks Suffer from Crowding? – Anna Volokitin, ETH Zurich

Table 56

Table 57:  NIPS Paper: Deanonymization in the Bitcoin P2P Network – Giulia Fanti, Carnegie Mellon University

Table 58: Careers@ElementAI

Table 59: Careers@Facebook

Table 60: Careers@DeepMind

Table 61: Careers@Capital One

Table 62: Careers@Criteo

Table 63: Careers@Microsoft

Table 64: Careers@Intel

Table 65: Careers@Google

Table 66: Careers@Airbnb

Table 67: Careers@Apple

Table 68: Careers@IBM

Table 69: Careers@NVIDIA

Table 70: Careers@Pandora

WiML 2017 Poster Session

Monday, Dec 4, 12:20 pm to 2:00 pm and Thursday Dec 7, 4:35pm -6:00pm, open to WiML and NIPS attendees

 

350+ posters covering theory, methodology, and applications of machine learning will be presented across 2 poster sessions.

The list of posters and authors can be found in the program book 

Accepted posters (with abstracts). Abstracts listed here are for archival purposes and do not constitute proceedings for this workshop.

Poster size: Up to 48 inches tall and 60 inches wide. We recommend printing in the stand A0 size (33.11 inches by 46.81 inches). You can orient the poster in portrait or landscape as long as it fits within the specified dimensions.  

Copyright © Women in Machine Learning 2017