{"id":278247,"date":"2016-08-25T10:38:16","date_gmt":"2016-08-25T17:38:16","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-event&#038;p=278247"},"modified":"2020-01-20T13:05:09","modified_gmt":"2020-01-20T21:05:09","slug":"new-england-machine-learning-day-2015","status":"publish","type":"msr-event","link":"https:\/\/www.microsoft.com\/en-us\/research\/event\/new-england-machine-learning-day-2015\/","title":{"rendered":"New England Machine Learning Day 2015"},"content":{"rendered":"<p><strong>Venue: <\/strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/lab\/microsoft-research-new-england\/\" target=\"_blank\" rel=\"noopener noreferrer\">Microsoft Research New England<\/a><br \/>\nHorace Mann Conference Room<br \/>\nFirst Floor Conference Center<br \/>\nOne Memorial Drive<br \/>\nCambridge, MA\u00a002142<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The fourth annual New England Machine Learning Day will be Monday, May 18, 2015, at Microsoft Research New England, One Memorial Drive, Cambridge, MA 02142. The event will bring together local academics and researchers in machine learning and its applications.<\/p>\n","protected":false},"featured_media":381722,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_startdate":"2015-05-18","msr_enddate":"2015-05-18","msr_location":"Cambridge, MA, USA","msr_expirationdate":"","msr_event_recording_link":"","msr_event_link":"","msr_event_link_redirect":false,"msr_event_time":"9:00 AM","msr_hide_region":false,"msr_private_event":true,"footnotes":""},"research-area":[13556],"msr-region":[197900],"msr-event-type":[197944],"msr-video-type":[],"msr-locale":[268875],"msr-program-audience":[],"msr-post-option":[],"msr-impact-theme":[],"class_list":["post-278247","msr-event","type-msr-event","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-region-north-america","msr-event-type-hosted-by-microsoft","msr-locale-en_us"],"msr_about":"<strong>Venue: <\/strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/lab\/microsoft-research-new-england\/\" target=\"_blank\" rel=\"noopener noreferrer\">Microsoft Research New England<\/a>\r\nHorace Mann Conference Room\r\nFirst Floor Conference Center\r\nOne Memorial Drive\r\nCambridge, MA\u00a002142","tab-content":[{"id":0,"name":"About","content":"The fourth annual New England Machine Learning Day will be Monday, May 18, 2015, at Microsoft Research New England, One Memorial Drive, Cambridge, MA 02142. The event will bring together local academics and researchers in machine learning and its applications. There will be a lively poster session during lunch. See the agenda tab for the list of presentations.\r\n<h2>Related events<\/h2>\r\n<ul>\r\n        <li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/event\/new-england-machine-learning-day-2020\/\">NEML 2020<\/a><\/li>\r\n \t<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/event\/new-england-machine-learning-day-2019\/\">NEML 2019<\/a><\/li>\r\n \t<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/event\/new-england-machine-learning-day-2018\/\">NEML 2018<\/a><\/li>\r\n \t<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/event\/new-england-machine-learning-day-2017\/\">NEML 2017<\/a><\/li>\r\n \t<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/event\/new-england-machine-learning-day-2016\/\">NEML 2016<\/a><\/li>\r\n \t<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/event\/new-england-machine-learning-day-2015\/\">NEML 2015<\/a><\/li>\r\n \t<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/event\/new-england-machine-learning-day-2014\/\">NEML 2014<\/a><\/li>\r\n \t<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/event\/new-england-machine-learning-day-2013\/\">NEML 2013<\/a><\/li>\r\n \t<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/event\/new-england-machine-learning-day-2012\/\">NEML 2012<\/a><\/li>\r\n<\/ul>"},{"id":1,"name":"Agenda","content":"9:50 - 10:00\r\nOpening remarks\r\n\r\n10:00 - 10:30, Tamara Broderick, MIT\r\n<em>Statistical and computational trade-offs from Bayesian approaches to unsupervised learning<\/em>\r\n\r\nThe flexibility, modularity, and coherent uncertainty estimates provided by Bayesian posterior inference have made this approach indispensable in a variety of domains. Since posteriors for many problems of interest cannot be calculated exactly, much work has focused on delivering accurate posterior approximations---though the computational cost of these approximations can sometimes be prohibitive, particularly in a modern, large-data context. Focusing on unsupervised learning problems, we illustrate in a series of vignettes how we can trade off some typical Bayesian desiderata for computational gains and vice versa. On one end of the spectrum, we sacrifice learning uncertainty to deliver fast, flexible methods for point estimates. In particular, we consider taking limits of Bayesian posteriors to obtain novel K-means-like objective functions as well as scalable, distributed algorithms. On the other end, we consider mean-field variational Bayes (MFVB), a popular and fast posterior approximation method that is known to provide poor estimates of parameter covariance. We develop an augmentation to MFVB that delivers accurate estimates of posterior uncertainty for model parameters.\r\n\r\n10:35 - 11:05, David Jensen, University of Massachusetts Amherst\r\n<em>Why ML Needs Causality<\/em>\r\n\r\nMachine learning has risen to extraordinary success and prominence primarily by representing and reasoning about statistical associations. Apparently, we can perform a great many useful tasks without having to concern ourselves with representing and reasoning about causality. In this talk, I will explain the key differences between associational and causal models and describe some of the recent technical developments in causal inference. I will explain why many existing machine learning tasks are really causal reasoning in disguise, why an increasing number of machine learning tasks will explicitly require causal models, and why researchers and practitioners who understand causal reasoning will succeed where others fail.\r\n\r\n11:10 - 11:40, Tim Kraska, Brown\r\n<em>Tupleware: Redefining Modern Analytics<\/em>\r\n\r\nThere is a fundamental discrepancy between the targeted and actual users of current analytics frameworks. Most systems are designed for the data and infrastructure of the Googles and Facebooks of the world\u2014petabytes of data distributed across large cloud deployments consisting of thousands of cheap commodity machines. Yet, the vast majority of companies operate or rent clusters in the range of a few dozen nodes and analyze relatively small data sets of up to a few terabytes. Targeting these users fundamentally changes the way we should build analytics systems.In this talk, Tim will present Tupleware, a new system developed at Brown University specifically aimed at the challenges faced by the typical user. The main difference of Tupleware to other frameworks is, that it automatically compiles complex machine learning workflows into highly efficient distributed programs instead of interpreting the workflows at run-time. Our initial experiments show, that Tupleware is 30x \u2013 300x faster than Spark and up to 6000x faster than Hadoop for common machine learning algorithms.\r\n\r\n11:40 - 1:45\r\nLunch and posters\r\n\r\n1:45 - 2:15, Suvrit Sra, MIT\r\n<em>Geometric optimization in machine learning<\/em>\r\n\r\n2:20 - 2:50, Jennifer Listgarten, Microsoft Research\r\n<em>Genome and Epigenome-Wide Association Studies<\/em>\r\n\r\nUnderstanding the genetic underpinnings of disease is important for screening, treatment, drug development, and basic biological insight. Genome-wide associations, wherein individual or sets of genetic markers are systematically scanned for association with disease are one window into disease processes. Naively, these associations can be found by use of a simple statistical test. However, a wide variety of confounders lie hidden in the data, leading to both spurious associations and missed associations if not properly addressed. These confounding factors include population structure, family relatedness, cell type heterogeneity, and environmental confounders. I will discuss the state-of-the art statistical approaches based on linear mixed models for conducting these analyses, in which the confounders are automatically deduced, and then corrected for, by the data and model.\r\n\r\n2:50 - 3:20\r\nCoffee break\r\n\r\n3:20 - 3:50, Krzysztof Gajos, Harvard\r\n<em>Interactive Intelligent Systems<\/em>\r\n\r\n3:55 - 4:25, Jennifer Dy, Northeastern\r\n<em>Learning in Complex Data<\/em>\r\n\r\nMachine learning as a field has become more and more important due to the ubiquity of data collection in various disciplines. Coupled with this data collection is the hope that new discoveries or knowledge can be learned from data. My research spans both fundamental research in machine learning and the application of those methods to biomedical imaging, health, science and engineering. Multi-disciplinary research is instrumental to the growth of the various areas involved. Real problems provide rich sources of complex data that challenges the state of the art in machine learning; at the same time, machine learning algorithms provide additional resources to scientists in making non-trivial contributions to their field of research. In this talk, I present two examples of innovation in machine learning motivated by challenges from complex medical domains.Chronic Obstructive Pulmonary Disease (COPD) is a lung disease characterized by airflow limitation due to noxious particles or gases (e.g., cigarette smoke). COPD is known to be a heterogeneous disease with genetic factors predisposing individuals to varying levels of disease severity as a function of exposure. An improved understanding of this heterogeneity should lead to better stratification of patients for prognosis and personalized treatments. However, standard clustering algorithms are limited because they do not take into account the interplay of the different features. We introduce a transformative way of looking at subtyping\/clustering by recasting it in terms of discovering associations of individuals to disease trajectories (i.e., grouping individuals based on their similarity in how their health changes as a response to environmental and\/or disease causing variables). This led us to the development of a nonparametric Bayesian model of mixture of disease trajectories.\r\n\r\nSkin cancer is one of the most common types of cancer. Standard clinical screening and diagnosis is performed using dermoscopy and visual examination. When an abnormal lesion is suspected, biopsy is carried out which is invasive, painful and leaves a scar. Our goal is to develop novel machine learning and image analysis algorithms that aid physicians in the early detection of skin cancer from 3D reflectance confocal microscopy images in vivo without resorting to biopsy. A key feature of interest is the dermal-epidermal junction which separates the dermis and epidermis layers of the skin. However, automated segmentation is challenging due to poor image contrast and high variability of objects in biology and medicine. This led us to the design of a novel generative probabilistic latent shape spatial Poisson process model that can take into account the uncertainty in number of objects, location, shape, and appearance. We develop a Gibbs sampler that addresses the variation in model order and nonconjugacy that arise in this setting.\r\n\r\n4:30 - 5:00, Ankur Moitra, MIT\r\n<em>Beyond Matrix Completion<\/em>\r\n\r\nHere we study some of the statistical and algorithmic problems that arise in recommendation systems. We will be interested in what happens when we move beyond the matrix setting, to work with higher order objects --- namely, tensors. To what extent does inference over more complex objects yield better predictions, but at the expense of the running time? We will explore the computational vs. statistical tradeoffs for some basic problems about recovering approximately low rank tensors from few observations, and will show that our algorithms are nearly optimal among all polynomial time algorithms, under natural complexity-theoretic assumptions.\r\n\r\nThis is based on joint work with Boaz Barak."},{"id":2,"name":"Posters","content":"<table class=\"teal-stripe tWiz tableBorder borderRows borderColumns\" cellpadding=\"5\">\r\n<tbody>\r\n<tr class=\"teal-stripeTableHeaderRow\">\r\n<td class=\"teal-stripeTableHeaderEvenCol\"><strong>\r\nPoster Title\u00a0<\/strong><\/td>\r\n<td class=\"teal-stripeTableHeaderOddCol\"><strong>Presenting Author\/\r\nComplete List of Authors<\/strong><\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Supersparse Linear Integer Models for Optimized Medical Scoring Systems<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Berk Ustun, MIT\/Berk Ustun, Cynthia Rudin<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">A Robotic Grasping System With Bandit-Based Adaptation\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">John Oberlin, Brown University\/John Oberlin, Stefanie Tellex<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Reliable and scalable variational inference for the hierarchical Dirichlet process\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Michael C. Hughes, Brown University\/Michael C. Hughes, Dae Il Kim, Erik B. Sudderth<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Learning Propositional Functions in Large State Spaces for Planning and Reinforcement Learning\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">David Hershkowitz, Brown University, Computer Science Department (undergrad)\/D. Ellis Hershkowitz, James MacGlashan, Stefanie Tellex<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Optimization as Estimation with Gaussian Process Bandits<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Zi Wang, CSAIL, MIT\/Zi Wang, Stefanie Jegelka, Leslie Pack Kaelbling, Tom\u00e1s Lozano-P\u00e9rez\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Estimating the Partition Function by Discriminance Sampling\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Qiang Liu, MIT\/Qiang Liu, Jian Peng, Alexander Ihler, John Fisher<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Preserving Modes and Messages via Diverse Particle Selection<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Jason L. Pacheco, Brown\/Jason L. Pacheco, Silvia Zuffi, Michael J. Black, Erik B. Sudderth\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Data Mining Methods for Analyzing and Modeling Spatiotemporal Data\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Dawei Wang, UMass Boston\/Dawei Wang, Wei Ding, Kui Yu<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Bayesian Or?s of And?s for Interpretable Classification, with Application to Context-Aware Recommender Systems<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Tong Wang, MIT\/Tong Wang, Cynthia Rudin, Finale Doshi-Velez, Yimin Liu, Erica Klampfl, Perry MacNeille\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Cheap Bandits<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Manjesh Hanawal, BU\/Manjesh K Hanawal, Venkatesh Saligrama\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Modeling and Prediction of Diabetes-Related Hospitalizations Using Electronic Health Records\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Tingting Xu, BU\/Theodora S. Brisimi, Tingting Xu, Ioannis Ch. Paschalidis\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Adding Expert Knowledge in Sparse Learning of High Dimensional Diffusion Data in Traumatic Brain Injury\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Matineh Shaker, Northeastern\/Matineh Shaker, Deniz Erdogmus, Jennifer Dy, Sylvain Bouix<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Machine Learning and Dynamic Programming Algorithms for Motion Planning and Control\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Oktay Arslan, Georgia Tech\/Oktay Arslan, Panagiotis Tsiotras<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Vector-Valued Property Elicitation\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Rafael Frongillo, Harvard\/Rafael Frongillo, Ian Kash<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Gradient-based Hyperparameter Optimization through Reversible Learning\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">David Duvenaud, Harvard\/Dougal Maclaurin, David Duvenaud, Ryan P. Adams<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Learning Heterogeneous Progression Patterns of Alzheimer's Disease with Clustered Hidden Markov Model\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Chenhui Hu, Harvard\/Chenhui Hu, Xiaoxiao Li, Finale Doshi-Velez, Xue Hua, Paul Thompson, Georges Fakhri, Quanzheng Li<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Exploring Collections with Interactive Spatial Organization\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Kenneth C. Arnold, Harvard\/Kenneth C. Arnold, Krzysztof Z. Gajos<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">ChordRipple: More Creative Chord Recommendations with chord2vec\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Anna Huang, Harvard\/Cheng-Zhi Anna Huang, David Duvenaud, Krzysztof Z. Gajos<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Stability and optimality in stochastic gradient descent\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Dustin Tran, Harvard\/Dustin Tran, Panos Toulis, Edoardo M. Airoldi<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Multi-Level Dirichlet Priors for Modelling Topical Variations across Textual Regions<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Kriste Krstovski, Harvard-Smithsonian Center for Astrophysics\/Kriste Krstovski, David A. Smith, Michael J. Kurtz\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Scalable Bayesian Nonparametric Policy Learning in Dec-POMDPs<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Miao Liu, MIT LIDS\/Miao Liu, Chris Amato, Jonathan P. How\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Measuring semantics assumptions\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Andrea Censi, MIT\/Andrea Censi<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">SQUARE: A Benchmark for Consensus Algorithms in Crowdsourcing\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Matt Lease, University of Texas at Austin\/Matthew Lease, Aashish Sheshadri<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">A Nearly-Linear Time Framework for Graph-Structured Sparsity<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Chinmay Hegde, MIT\/Chinmay Hegde, Piotr Indyk, Ludwig Schmidt\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Sample-Optimal Density Estimation in Nearly-Linear Time<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Jerry Li, MIT\/Jayadev Acharya, Ilias Diakonikolas, Jerry Li, Ludwig Schmidt\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">A Nearly Optimal and Agnostic Algorithm for Properly Learning a Mixture of k Gaussians, for any Constant k\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Ludwig Schmidt, MIT\/Jerry Li, Ludwig Schmidt<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Nonparametric Bayesian Inference of Strategy in Infinitely Repeated Games<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Max Kleiman-Weiner, MIT\/Max Kleiman-Weiner, Penghui Zhou, Joshua B. Tenenbaum\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Perturbation Training for Human-Robot Teams\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Ramya Ramakrishnan, MIT\/Ramya Ramakrishnan, Chongjie Zhang, Julie A. Shah<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Fixed-point algorithms for learning Determinantal Point Processes\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Zelda Mariet, MIT\/Zelda Mariet, Suvrit Sra\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Object-based World Modeling with Dependent Dirichlet Process Mixtures\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Lawson Wong, MIT CSAIL\/Lawson L.S. Wong, Thanard Kurutach, Leslie Pack Kaelbling,\u00a0Tom\u00e1s Lozano-P\u00e9rez<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Handwritten Tamil Character Recognition using a Convolutional Neural Network\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Misha Sra, MIT Media lab\/Prashanth Vijayaraghavan, Misha Sra<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Computing Sparse\/Low-rank\/Structured Optimization Solutions using an Extension of the Frank-Wolfe Method, with Application to Matrix Completion\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Paul Grigas, MIT Operations Research Center\/Robert M. Freund, Paul Grigas, Rahul Mazumder<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">A Sparse Combined Regression-Classification Formulation for Learning a Physiological Alternative to Clinical Post-Traumatic Stress Disorder Scores\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Sarah Brown, Northeastern University\/Sarah Brown, Rami Mangoubi, Andrea Webb, Jennifer Dy<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">RSVP Keyboard A Brain Computer Interface for AAC Technology\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Paula Gonzalez, Northeastern University\/U. Orhan, M. Moghadamfalahi, P. Gonzalez-Navarro, B. Girvent, A. Ahani, M. Haghighi, B. Peters, A. Mooney, A. Fowler, K. Gorman, S. Bedrick, B. Oken, M. Akcakaya, M. Fried-Oken, D. Erdogmus\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Personality Prediction in Heterogeneous Social Networks with Incomplete Attributes\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Yuan Zhong, Northeastern University\/Yuan Zhong, Yizhou Sun, Wen Zhong, Rui Dong, Yupeng Gu<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Clustering and Ranking in Heterogeneous Information Networks via Gamma-Poisson Model\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Junxiang Chen, Northeastern University\/Junxiang Chen, Wei Dai, Yizhou Sun, Jennifer Dy<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Efficient exploration of large molecular spaces with artificial neural networks\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Edward Pyzer-Knapp, Harvard\/Jos\u201a Miguel Hern ndez-Lobato, Edward Pyzer-Knapp, Ryan Adams, Al n Aspuru-Guzik\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Sparse Variational Inference for Generalized Gaussian Process Models<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Rishit Seth, Tufts University\/Rishit Sheth, Bernie Wang, Roni Khardon<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Method of Moments Learning for Left to Right Hidden Markov Models\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Cem S\u0081bakan, UIUC CS department\/Cem Subakan, Johannes Traa, Paris Smaragdis, Daniel Hsu<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Concurrent and Incremental Transfer Learning in a Network of Reinforcement Learning Agents<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Dan Garant, University of Massachusetts-Amherst\/Dan Garant, Bruno Castro da Silva, Victor Lesser, Chongjie Zhang<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Alternative approaches to discovering causality with additive noise models\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Kaleigh Clary, University of Massachusetts-Amherst\/ Kaleigh Clary, David Jensen\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Cancer Subtype Discovery Using Machine Learning<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Henry Lo, University of Massachusetts-Boston\/Henry Lo, Melissa Cruz, Dawei Wang, Wei Ding, Marieke Kuijjer, Heather Selby, John Quackenbush<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Inferring Polyadic Events With Poisson Tensor Factorization\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Aaron Schein, University of Massachusetts-Amherst\/Aaron Schein, John Paisley, David M. Blei, Hanna M. Wallach\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Towards understanding the Boundary Forest Algorithm<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Charles Mathy, Disney Research\/Jose Bento, Charles Mathy, Dan Schmidt<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Predictive Entropy Search for Bayesian Optimization with Unknown Constraints\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Michael Gelbart, Harvard\/Jos\u201a Miguel Hern ndez-Lobato, Michael Gelbart, Matt Hoffman, Ryan Adams, Zoubin Ghahramani\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Model Selection by Linear Programming\r\n\r\n&nbsp;<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Tolga Bolukbasi, BU\/Joseph Wang, Tolga Bolukbasi, Kirill Trapeznikov, Venkatesh Saligrama\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableEvenRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Bag of Words Approach to Activity Classification<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Kevin Amaral, Northeastern\/Kevin M. Amaral, Wei Ding, Scott E. Crouter, Ping Chen\r\n\r\n&nbsp;<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">NeurOS and NeuroBlocks:\u00ff A Neural\/Cognitive Operating System and Building Blocks<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Lee Scheffler, Cognitivity\/Lee Scheffler<\/td>\r\n<\/tr>\r\n<tr class=\"teal-stripeTableOddRow\">\r\n<td class=\"teal-stripeTableEvenCol\">Feature-Budgeted Random Forest<\/td>\r\n<td class=\"teal-stripeTableOddCol\">Feng Nan, Boston University\/Feng Nan, Joseph Wang, Venkatesh Saligrama<\/td>\r\n<\/tr>\r\n<\/tbody>\r\n<\/table>\r\n&nbsp;\r\n\r\nFor any questions, please contact us <a href=\"mailto:jewalker%40microsoft.com?subject=NEML 2015\">here<\/a>."},{"id":3,"name":"Committee","content":"Carla Brodley, Northeastern\r\nFinale Doshi-Velez, Harvard\r\nStefanie Jegelka, MIT\r\n<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/adum\/\" target=\"_blank\" rel=\"noopener noreferrer\">Adam Tauman Kalai<\/a>, Microsoft Research\r\n\r\nThe steering committee that selects the organizers of ML Day each year consists of Ryan Adams, Sham Kakade, Adam\u00a0Tauman Kalai, and Joshua Tenenbaum."}],"msr_startdate":"2015-05-18","msr_enddate":"2015-05-18","msr_event_time":"9:00 AM","msr_location":"Cambridge, MA, USA","msr_event_link":"","msr_event_recording_link":"","msr_startdate_formatted":"May 18, 2015","msr_register_text":"Watch now","msr_cta_link":"","msr_cta_text":"","msr_cta_bi_name":"","featured_image_thumbnail":"<img width=\"960\" height=\"360\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2017\/03\/MSR-MachineLearningDay-Hero_1920x720-v1.jpg\" class=\"img-object-cover\" alt=\"Portrait on green background, header for New England Machine Learning Day event page\" decoding=\"async\" loading=\"lazy\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2017\/03\/MSR-MachineLearningDay-Hero_1920x720-v1.jpg 1920w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2017\/03\/MSR-MachineLearningDay-Hero_1920x720-v1-300x113.jpg 300w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2017\/03\/MSR-MachineLearningDay-Hero_1920x720-v1-768x288.jpg 768w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2017\/03\/MSR-MachineLearningDay-Hero_1920x720-v1-1024x384.jpg 1024w\" sizes=\"(max-width: 960px) 100vw, 960px\" \/>","event_excerpt":"The fourth annual New England Machine Learning Day will be Monday, May 18, 2015, at Microsoft Research New England, One Memorial Drive, Cambridge, MA 02142. The event will bring together local academics and researchers in machine learning and its applications.","msr_research_lab":[199563],"related-researchers":[],"msr_impact_theme":[],"related-academic-programs":[],"related-groups":[],"related-projects":[],"related-opportunities":[],"related-publications":[],"related-videos":[],"related-posts":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/278247"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-event"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/278247\/revisions"}],"predecessor-version":[{"id":565533,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/278247\/revisions\/565533"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/381722"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=278247"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=278247"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=278247"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=278247"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=278247"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=278247"},{"taxonomy":"msr-program-audience","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-program-audience?post=278247"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=278247"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=278247"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}