Machine Learning Seminars

Sponsored by

Title: Which Supervised Learning Method Works Best for What? An Empirical Comparison of Learning Methods and Metrics
Speaker: Rich Caruana, Microsoft Research
When: Tuesday, June 4, 2013 - 12:30
Location: CSE Gates Commons

Decision trees can be intelligible, but do they perform well enough that you should use them? Have SVMs replaced neural nets, or are neural nets still best for regression and SVMs best for classification? Boosting maximizes a margin similar to SVMs, but can boosting compete with SVMs? If it does, is it better to boost weak models or to boost stronger models? Bagging is easier than boosting - how well does it stack up against boosting? Breiman said Random Forests are better than bagging and as good as boosting. Was he right? And what about old friends like logistic regression, KNN, and naive Bayes? Should they be put out to pasture, or do they fill important niches?

In this talk we'll compare the performance of ten supervised learning methods on nine criteria: Accuracy, F-score, Lift, Precision/Recall Break-Even Point, Area under the ROC, Average Precision, Squared Error, Cross-Entropy, and Probability Calibration. The results show that no one learning method does it all, but some methods can be 'repaired' to do very well across all performance metrics. In particular, we show how to obtain good probabilities from max-margin methods such as SVMs and boosting via Platt's Method and Isotonic Regression. We also describe a meta-ensemble method that combines select models from these ten learning methods to yield even better performance than any of the individual learning methods. Although these ensembles perform extremely well, they are too complex for some real-world applications. We'll describe a model compression method that tries to fix that. Finally, if time permits, we'll discuss how the nine performance metrics relate to each other, and on which of the metrics you probably should (or shouldn't) depend.

 

Title: Reproducibility and Probabilistic Tsunami Hazard Assessment
Speaker: Randall Leveque, UW Applied Math
When: Tuesday, May 28, 2013 - 12:30
Location: CSE Gates Commons

I will discuss two somewhat independent topics. The first is the importance of reproducibility in computational research and the need for higher standards and better tools to help insure that published results can be reproduced (preferably by other researchers, but at least by the authors!). I will mention some of the tools already available to help with this.

Tsunami modeling is a motivating example since the results of numerical simulations are often used to inform public policy decisions that can have significant financial and safety implications. I will also briefly describe some of the techniques used to perform probabilistic hazard assessment and to solve the inverse problems necessary to do real-time forecasting, in hopes of identifying overlapping interests with the machine learning community.

 

Title: Local Privacy, Minimax Rates, and Learning
Speaker: John Duchi, UC Berkeley
When: Tuesday, May 21, 2013 - 12:30
Location: CSE 305

We study statistical estimation minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish sharp upper and lower bounds on the convergence rates of statistical inference procedures. As a consequence, we exhibit a precise tradeoff between the amount of privacy the data preserves and the utility, as measured by convergence rate, of any statistical estimator or learning procedure.

Joint work with Michael Jordan and Martin Wainwright.

 

Title: Recursive Deep Learning for Modeling Semantic Compositionality
Speaker: Richard Socher, Stanford
When: Tuesday, May 14, 2013 - 12:30
Location: CSE Gates Commons

Compositional and recursive structure is commonly found in different modalities, including natural language sentences and scene images. I will introduce several recursive deep learning models that, unlike standard deep learning methods can learn compositional meaning vector representations for phrases, sentences and images. These recursive neural network based models obtain state-of-the-art performance on a variety of syntactic and semantic language tasks such as parsing, paraphrase detection, relation classification and sentiment analysis.

Besides the good performance, the models capture interesting phenomena in language such as compositionality. For instance the models learn different types of high level negation and how it can change the meaning of longer phrases with many positive words. They can learn that the sentiment following a "but" usually dominates that of phrases preceding the "but." Furthermore, unlike many other machine learning approaches that rely on human designed feature sets, features are learned as part of the model.

I will focus on two recent results: Pushing the performance of the Stanford parser by 3.8% and improving its speed by 20% using syntactically untied RNNs and a recursive neural tensor network trained on a novel sentiment treebank.

 

Title: Validating Network Classifiers and Pricing Information
Speaker: Eric Bax
When: Tuesday, May 7, 2013 - 12:30
Location: CSE Gates Commons

Validating Network Classifiers: Networks are fundamental to our lives, from the network of gene interactions that shapes our bodies to the social networks that can eat up the hours of our lives. :) Collective classification uses network structure to predict node information. For example, if your friends all like jazz, are you likely to as well? Since networks grow by adding nodes based on the nodes already in the network, nodes are not drawn i.i.d. This makes trouble for most machine learning approaches to validation of classifier performance. We will discuss a method to validate network classifiers that is based on understanding how the network grows.

Pricing Information: In auctions for online advertising, data providers tell advertisers which users are the best bets for their ads. So advertisers buy a combination of information (from data providers) and advertising space (from publishers like Yahoo). How much should advertisers pay for each? Let's have a hands-on experience to find out.

 

Title: Interpretable patient-level predictive models
Speaker: Tyler McCormick, UW Sociology & Statistics
When: Tuesday, April 30, 2013 - 12:30
Location: CSE 403

This talk presents statistical methods which generate patent-level predictions that are both accurate and highly interpretable to healthcare providers and patients. In this context, an interpretable model should be able to pinpoint exactly why a particular prediction was made, and provide the reason in a clear and natural way. The talk begins by introducing the Hierarchical Association Rule Model (HARM) which sequentially predicts a patient's possible future medical conditions given the patient's current and past history of reported conditions. The core of our technique is a Bayesian hierarchical model for selecting predictive association rules (such as ``dyspepsia and epigastric pain imply heartburn") from a large set of candidate rules. We next present a model for traditional classification problems based on decision lists, which consist of a series of if...then... statements (for example, if high blood pressure, then stroke). Decision lists discretize the high-dimensional, multivariate feature space into a series of simple, readily interpretable decision statements. Our Bayesian framework, known as the Bayesian List Machine (BLM), introduces a formal relationship between sparsity and interpretability through a prior structure over lists. We compare our model with the CHADS2 score, actively used in clinical practice for estimating the risk of stroke in patients that have atrial fibrillation. Our model is as interpretable as CHADS2, but more accurate.

This is collaborative work with Cynthia Rudin, Ben Letham, and David Madigan.

 

Title: Machine learning for protein structure modeling
Speaker: David Baker, Hetunandan Kamisetty, Frank DiMaio, UW Biochemistry
When: Tuesday, March 19, 2013 - 12:30
Location: CSE 305
David will introduce protein structure modeling and describe the conformational samping and scoring problems. Hetu will describe a method to constrain this conformational space that exploits the many-to-one relationship between protein sequence and structure using graphical models. Frank will describe ongoing efforts at improving scoring by optimizing scorefunction parameters directly against experimental data.

 

Title: Graphical Event Models
Speaker: Asela Gunawardana, Microsoft Research
When: Tuesday, March 12, 2013 - 12:30
Location: CSE Gates Commons
Modeling the temporal dynamics of heterogeneous event streams is central to many real world applications. Graphical Event Models (GEMs) represent the dependencies of each type of event in a stream on past events. Learning the structure and parameters of GEMs from event stream data is valuable for understanding the dynamics of event streams, as well as for predicting their future behavior. This talk will describe specific classes of GEMs, along with computationally tractable learning algorithms and inference algorithms for them, giving empirical results on a number of real world applications. It will also touch on some recent learnability results.

 

Title: Fitting Manifolds to Probability Measures
Speaker: Hari Narayanan, UW Stats and Mathematics
When: Tuesday, February 26, 2013 - 12:30
Location: CSE 403
We are confronted with very high dimensional data sets. As a result, methods of dealing with high dimensional data have become prominent. One geometrically motivated approach for analyzing data is called manifold learning. The underlying hypothesis of this approach is that due to symmetries and constraints in the generating process, high dimensional data often lie near a low dimensional manifold. Although there are many well known algorithms based on this hypothesis, the basic question of understanding when data lies near a manifold is poorly understood. We will describe joint work with Charles Fefferman and Sanjoy Mitter on developing a provably correct algorithm to fit a nearly optimal manifold to an unknown probability distribution using i.i.d samples, and thereby test this hypothesis.

 

Title: Discovering Attributes of Objects in Images
Speaker: Ali Farhadi, UW-CSE
When: Tuesday, February 19, 2013 - 12:30
Location: CSE Gates Commons
Visual attributes have shown to be useful in several recognition tasks. The vocabulary of attributes is typically defined manually. In this talk I will show a method to discover the vocabulary of attributes by learning to project images, using learnable projections, to a binary space where categories are well separated. Category memberships are usually good proxies for visual similarity but should not be enforced as a hard constraint. Our method learns codes that maximize separability of categories unless there is strong visual evidence against it. The learned binary codes are highly discriminative; A simple linear SVMs can achieve state-of-the-art results with our short codes. In fact, our method produces state-of-the-art results on Caltech256 with only 128- dimensional bit vectors and outperforms state of the art by using longer codes. Using these codes, I will show a method to reason about conjunctions of multiple classification tasks to reason about complex queries and how to learn categories from very few training samples by borrowing examples from other categories.