The Rachel and Selim Benin School of Computer Science and Engineering

Home → Channel

Channel

The Learning Club

Time: Thursdays 10:15 - 11:30 (refreshments at 10:00)
Place: Ross 63, The Edmond J. Safra Campus. Here are maps and directions to the Ross Building.
Join or leave our distribution mailing list.
Coordinator: Dr. Amir Globerson, Elad Eban, Ohad Shamir
Past Years

Future talks

Spring 2012/2013 Semester

Metro Maps of Information

Thu, 23 May 2013, 10:00
Speaker: Dafna Shahaf , Carnegie Mellon University
Comment: When information is abundant, it becomes increasingly difficult to fit nuggets of knowledge into a single coherent picture. Complex stories spaghetti into branches, side stories, and intertwining narratives; search engines, our most popular navigational tools, are limited in their capacity to explore such complex stories. We propose a methodology for creating structured summaries of information, which we call metro maps. Just as cartographic maps have been relied upon for centuries to help us understand our surroundings, metro maps can help us understand the relationships between many pieces of information. We formalize characteristics of good maps and formulate their construction as an optimization problem. We provide efficient, scalable methods with theoretical guarantees for generating maps. User studies over real-world datasets demonstrate that our method is able to produce maps which help users acquire knowledge efficiently.

Information, Complexity and Learning

Thu, 30 May 2013, 09:00
Speaker: - ,
Comment: The workshop will be held in honor of Prof. Naftali Tishby, marking his 60th birthday, and celebrating his influential research career

TBA

Thu, 06 Jun 2013, 10:00
Speaker: Yevgeny Seldin , Queensland University of Technology and with UC Berkeley

Computable Performance Analysis of Sparse Recovery with Applications

Thu, 27 Jun 2013, 10:00
Speaker: Arye Nehorai , Washington University in St. Louis
Comment: The last decade has witnessed burgeoning developments in the reconstruction of signals based on exploiting their low-dimensional structures, particularly their sparsity, block-sparsity, and low-rankness. The reconstruction performance of these signals is heavily dependent on the structure of the operating matrix used in sensing. The quality of these matrices in the context of signal recovery is usually quantified by the restricted isometry constant and its variants. However, the restricted isometry constant and its variants are extremely difficult to compute. We present a framework for analytically computing the performance of the recovery of signals with sparsity structures. We define a family of incoherence measures to quantify the goodness of arbitrary sensing matrices. Our primary contribution is the design of efficient algorithms, based on linear programming and second order cone programming, to compute these incoherence measures. As a by-product, we implement efficient algorithms to verify sufficient conditions for exact signal recovery in the noise-free case. The utility of the proposed incoherence measures lies in their relationship to the performance of reconstruction methods. We derive closed-form expressions of bounds on the recovery errors of convex relaxation algorithms in terms of these measures. The second part of the talk applies the developed theory and algorithms to the optimal design of an OFDM radar system with multi-path components.

* indicates a special talk, not on the regular time-slot or place

Warning: DOMDocument::createElement() [domdocument.createelement]: unterminated entity reference c=0 in /a/fr-05/vol/web/www/site/utils/channelDOM.php on line 388

Warning: DOMDocument::createElement() [domdocument.createelement]: unterminated entity reference c=0 in /a/fr-05/vol/web/www/site/utils/channelDOM.php on line 388

Warning: DOMDocument::createElement() [domdocument.createelement]: unterminated entity reference c=0 in /a/fr-05/vol/web/www/site/utils/channelDOM.php on line 388

Past talks

Spring 2012/2013 Semester

projection-free online learning

Thu, 09 May 2013, 10:00
Speaker: Elad Hazan , The Technion
Comment: The computational bottleneck in applying online learning to massive data sets is usually the projection step. We present efficient on- line learning algorithms that eschew projections in favor of much more efficient linear optimization steps. Our algorithms are based on a new algorithm for general convex optimization based on the Frank-Wolfe technique, which is of independent interest. joint work with Dan Garber, Technion

Adaptive Coding of Actions and Observations

Thu, 02 May 2013, 10:00
Speaker: Pedro Ortega , The Hebrew University
Comment: The application of expected utility theory to construct adaptive agents is both computationally intractable and statistically questionable. To overcome these difficulties, agents need the ability to delay the choice of the optimal policy to a later stage when they have learned more about the environment. How should agents do this optimally? An information-theoretic answer to this question is given by the Bayesian control rule - the solution to the adaptive coding problem when there are not only observations but also actions. I will review the central ideas behind the Bayesian control rule.

Optimizing the measure of performance in structured learning

Thu, 25 Apr 2013, 10:00
Speaker: Joseph Keshet , TTI
Comment: The goal of discriminative learning is to train a system to optimize a certain desired measure of performance. In simple classification we seek a function that assigns a binary label to a single object, and tries to minimize the error rate (correct or incorrect) on unseen data. In structured prediction we are interested in the prediction a structured label, where the input is a complex object. Typically, each structured prediction task has its own measure of performance, or cost function, such as word error rate in speech recognition, the BLEU score in machine translation or the intersection-over-union score in object segmentation. Not only that those cost functions are much more involved than the binary error rate, the structured prediction itself spans an exponentially large label space. In the talk, I will present two algorithms each designed to the minimize a given cost. First, I will present a new theorem stating that a general learning update rule for linear models directly corresponds to the gradient of the desired measure of performance, and will describe its proof technique. I will present empirical results on the task of phoneme-to-speech alignment, where the goal is to minimize the special alignment cost function. Then, I will show a generalization of the theorem to training non-linear models such as HMMs, and will present empirical results on phoneme recognition task which surpass results from HMMs trained with all other training techniques. In the second part of the talk, I will describe a new algorithm which aims to minimize a regularized cost function. The algorithm is derived by directly minimizing a generalization bound for structured prediction, which gives an upper-bound on the expected cost (risk) in terms of the empirical cost. The resulting algorithm is iterative and easy to implement, and as far as we know, the only algorithm that can handle a non-separable cost functions. We will present experimental results on the task of phoneme recognition, and will show that the algorithm achieves the lowest phoneme error rate (normalized edit distance) compared to other discriminative and generative models with the same expressive power.

A Hilbert Space Embedding for Distributions. Paper by Alex Smola, Arthur Gretton, Le Song, Bernhard Schölkopf.

Thu, 18 Apr 2013, 10:00
Speaker: Yoav Wald , The Hebrew University
Comment: The authors describe a technique for comparing distributions without the need for density estimation as an intermediate step. Their approach relies on mapping distributions into a reproducing kernel Hilbert space, the paper is an overview of methods proposed over several past works, all based on this approach. In this talk I'll describe the technique and its application to a few tasks including two-sample tests and measures of independence.

Adaptive Metric Dimensionality Reduction

Sun, 07 Apr 2013, 10:00
Speaker: Aryeh Kontorovich , Ben Gurion University
Comment: We initiate the study of dimensionality reduction in general metric spaces in the context of supervised learning. Our statistical contribution consists of tight Rademacher bounds for Lipschitz functions in metric spaces that are doubling, or nearly doubling. As a by-product, we obtain a new theoretical explanation for the empirically reported improvements gained by pre-processing Euclidean data by PCA (Principal Components Analysis) prior to constructing a linear classifier. On the algorithmic front, we describe an analogue of PCA for metric spaces, namely an efficient procedure that approximates the data's intrinsic dimension, which is often much lower than the ambient dimension. Thus, our approach can exploit the dual benefits of low dimensionality: (1) more efficient proximity search algorithms, and (2) more optimistic generalization bounds. Joint work with Lee-Ad Gottlieb and Robert Krauthgamer.

Multiclass Learning Approaches: A Theoretical Comparison with Implications.

Thu, 14 Mar 2013, 10:00
Speaker: Amit Daniely , The Hebrew University
Comment: We outline a theoretical analysis and comparison of five popular multiclass classification methods: One vs. All, All Pairs, Tree-based classifiers, Error Correcting Output Codes (ECOC) with randomly generated code matrices, and Multiclass SVM. The analysis is distribution free and "hypothesis class based" (similar to the PAC/VC theory). Every method naturally defines a hypothesis class of classifiers. For each such class, we study both the approximation error (the error of the best hypothesis in the class) and the estimation error (the difference between the error of the returned classifier and the approximation error). Similar to binary classification, the estimation error is evaluated using the Graph Dimension, a generalization of theVC dimension. For the approximation error, we give two kind of result - the first shows that certain classes will always have better approximation error than other classes. The second shows that certain classes are very likely to have very large approximation error (close to 1/2). The analysis yields several conclusions of practical relevance, and reveals some phenomenons that do not happen in binary classification. Joint work with Sivan Sabato and Shai Shalev-Shwartz

D.C. Programming and DCA

Thu, 07 Mar 2013, 10:00
Speaker: Nadav Cohen , The Hebrew University
Comment: D.C. programming addresses the problem of minimizing a function f=g-h, g and h being convex. We will discuss the properties of D.C. programs and D.C. functions, including global and local optimality conditions and D.C. duality. The DCA (D.C. algorithm) is based on local optimality conditions and duality, and tackles a D.C. program with a convex analysis approach. It is a generalization of CCCP (concave-convex procedure), although historically it preceded the latter. We will discuss the merits and drawbacks of DCA, and in particular its convergence properties. Finally, we will concentrate on the class of polyhedral D.C. programs, which arise naturally in many cases, and on which DCA exhibits finite convergence.

Exact Lifted Probabilistic Inference

Thu, 28 Feb 2013, 10:00
Speaker: Udi Aspel , Ben Gurion University
Comment: Relational graphical models extend the descriptive scope of graphical models by using a first-order language. Compared with "regular" models that use propositional language, relational models are able to compactly represent large scale problems, by capturing repeated patterns and relations between domain entities. E.g., a friend of a smoker is likely to be a smoker as well. A specialized class of inference algorithms called "lifted inference" algorithms, allows inference to be applied directly on probabilistic relational models, and has proven to be vastly superior to the alternative, where a relational model is extracted into a large (and exponentially less efficient) equivalent model of propositional language. The talk will include: i. A brief introduction to Variable Elimination - an exact inference algorithm for propositional models. ii. Introduction to Relational Probabilistic Models. iii. An overview of First Order Variable Elimination - an exact inference algorithm for Relational Probabilistic Models. iv. A brief overview of our contribution. Joint work with Prof. Ronen Brafman.

Fall 2012/2013 Semester

TBA

Thu, 07 Feb 2013, 10:00
Speaker: Edo Liberty , Yahoo!

Convergence rate of coordinate descent for MAP

Thu, 24 Jan 2013, 10:00
Speaker: Ofer Meshi , The Hebrew University
Comment: Finding maximum a posteriori (MAP) assignments in graphical models is an important task in many applications. Since the problem is generally hard, linear programming (LP) relaxations are often used. Solving these relaxations efﬁciently is thus an important practical problem. In recent years, several authors have proposed message passing updates corresponding to coordinate descent in the dual LP. However, these are generally not guaranteed to converge to a global optimum. One approach to remedy this is to smooth the LP, and perform coordinate descent on the smoothed dual. However, little was known about the convergence rate of this procedure. We perform a thorough rate analysis of such schemes and derive primal and dual convergence rates. We also provide a simple dual to primal mapping that yields feasible primal solutions with a guaranteed rate of convergence. This is a joint work with Tommi Jaakkola and Amir Globerson. Presented at NIPS 2012.

On Measure Transformed Canonical Correlation Analysis

Thu, 17 Jan 2013, 10:00
Speaker: Koby Todros , University of Michigan
Comment: In this work linear canonical correlation analysis (LCCA) is generalized by applying a structured transform to the joint probability distribution of the considered pair of random vectors, i.e., a transformation of the joint probability measure defined on their joint observation space. This framework, called measure transformed canonical correlation analysis (MTCCA), applies LCCA to the data after transformation of the joint probability measure. We show that judicious choice of the transform leads to a modified canonical correlation analysis, which, in contrast to LCCA, is capable of detecting non-linear relationships between the considered pair of random vectors. Unlike kernel canonical correlation analysis, where the transformation is applied to the random vectors, in MTCCA the transformation is applied to their joint probability distribution. This results in performance advantages and reduced implementation complexity. The proposed approach is illustrated for graphical model selection in simulated data having non-linear dependencies, and for measuring long-term associations between companies traded in the NASDAQ and NYSE stock markets.

Nonlinear Signal Processing Based on Empirical Intrinsic Geometry

Thu, 10 Jan 2013, 10:00
Speaker: Ronen Talmon , Yale University
Comment: In this talk, I will present a method for nonlinear signal processing based on empirical intrinsic geometry (EIG). This method provides a convenient framework for combining geometric and statistical analysis and incorporates concepts from information geometry. Unlike classic information geometry that assumes known probabilistic models, we empirically infer an intrinsic model of distribution estimates, while maintaining similar theoretical guarantees. The key observation is that the probability distributions of signals, rather than specific realizations, uncover relevant geometric information. The proposed modeling exhibits two important properties which demonstrate its advantage compared to common geometric algorithms. We show that our model is noise resilient and invariant under different observation and instrumental modalities. In addition, we show that it can be extended efficiently to newly acquired measurements in a sequential manner. These two properties make the proposed model especially suitable for signal processing. We revisit the Bayesian approach and incorporate statistical dynamics and empirical intrinsic geometric models into a unified nonlinear filtering framework. We then apply the proposed method to nonlinear and non-Gaussian filtering problems. In addition, we show applications to biomedical signal analysis and acoustic signal processing.

Multi-Target Radar Detection with Almost Linear Complexity

Sun, 06 Jan 2013, 14:00
Speaker: Alexander Fish , University of Wisconsin
Comment: We would like to know the distances to moving objects and their velocities. The radar system is built to fulfill this task. The radar transmits a waveform S which bounds back from the objects and the echo R is received. In practice we can work in the digital model, namely S and R are sequences of N complex numbers (e.g., N=1023). THE RADAR PROBLEM IS: Design S, and an effective method of extracting, using S and R, the distances and velocities of all targets. In many applications the current sequences S which are used are pseudo-random and the algorithm they support takes O(N²logN) arithmetic operations. In the lecture we will introduce the Heisenberg sequences, and a much faster detection algorithm called the Cross Method. It solves the Radar Problem in O(NlogN+m²) operations for m objects. This is a joint work with S. Gurevich (Math, Madison), A. Sayeed (EE, Madison), K. Scheim (General Motors, Herzeliya), O. Schwartz (EECS, Berkeley).

Causal Reasoning and Learning Systems

Thu, 03 Jan 2013, 10:00
Speaker: Elon Portugaly , Microsoft Research Cambridge / Bing Ads
Comment: In complex real world systems, machine learning is used to influence actions, rather than just provide predictions. Those actions in turn influence the environment of the system. The goal of machine learning in these systems is therefore causal rather than correlational. E.g. what would be the survival chance of patient A if we gave them drug B (causal question); what is the survival chance of the patient A knowing that they were given drug B (correlational question). By injecting noise into actions taken by the system, we can collect data that allows us to infer causality, and predict the consequences of changes to the system. Such predictions allow both humans and algorithms to select changes that improve both the short-term and long-term performance of such systems. This work provides a framework (which can be viewed as a generalization of the A/B testing framework) for counterfactual causal inference in complex systems. Parts of this framework were implemented in Microsotf’s bing search advertising system, and I will show data from this implementation.

Distributed Learning and Communication Complexity

Thu, 27 Dec 2012, 10:00
Speaker: Yonatan Kibarski , The Hebrew University
Comment: Consider a dataset distributed over several computers around the world each containing several terabytes each. We describe a learning problem that learns a hypothesis over the unified dataset and show general bounds on the amount of data transfer and specific efficient algorithms. Paper by Maria-Florina Balcan, Maria-Florina Balcan, Avrim Blum, Shai Fine, Yishay Mansour.

Robust Subspace Modeling

Thu, 20 Dec 2012, 10:00
Speaker: Gilad Lerman , University Of Minnesota
Comment: Consider a dataset of vector-valued observations that consists of a modest number of noisy inliers, which are explained well by a low-dimensional subspace, along with a large number of outliers, which have no linear structure. We describe a convex optimization problem that can reliably fit a low-dimensional model to this type of data. When the inliers are contained in a low-dimensional subspace we provide a rigorous theory that describes when this optimization can recover the subspace exactly. We present an efficient algorithm for solving this optimization problem, whose computational cost is comparable to that of the non-truncated SVD. We also show that the sample complexity of the proposed subspace recovery is of the same order as PCA subspace recovery and we consequently obtain some nontrivial robustness to noise. This presentation is based on three joint works: 1) with Teng Zhang, 2) with Michael McCoy, Joel Tropp and Teng Zhang, and 3) with Matthew Coudron.

Learning patterns in Big data from small data using core-sets

Thu, 13 Dec 2012, 10:00
Speaker: Dan Feldman , MIT
Comment: When we need to solve an optimization problem we usually use the best available algorithm/software or try to improve it. In recent years we have started exploring a different approach: instead of improving the algorithm, reduce the input data and run the existing algorithm on the reduced data to obtain the desired output much faster on a streaming input, using a manageable amount of memory, and in parallel (say, using Hadoop, cloud service, or GPUs). A core-set for a given problem is a semantic compression of its input, in the sense that a solution for the problem with the (small) coreset as input yields a provable approximate solution to the problem with the original (Big) data. In this talk I will describe how we applied this magical paradigm to obtain algorithmic achievements with performance guarantees in iDiary: a system that combines sensor networks, computer vision, differential privacy, and text mining. It turns large signals collected from smart-phones or robots sensors into textual descriptions of the trajectories. The system features a user interface similar to Google Search that allows users to type text queries on their activities (e.g., "Where did I have dinner last time I visited Paris?"") and receive textual answers based on their signals.

no talk this wee due to NIPS

Thu, 06 Dec 2012, 10:00
Speaker: -------- ,

What Cannot be Learned with Bethe Approximations

Thu, 22 Nov 2012, 10:00
Speaker: Uri Heinemann , The Hebrew University

Learning the experts for online sequence prediction

Thu, 08 Nov 2012, 10:00
Speaker: Elad Eban , The Hebrew University

Learning Halfspaces with the Zero-One Loss: Time-Accuracy Tradeoffs

Thu, 01 Nov 2012, 10:00
Speaker: Aharon Birnbaum , The Hebrew University

Learnability beyond uniform convergence

Thu, 25 Oct 2012, 10:00
Speaker: Shai Shalev-Swartz , The Hebrew University

Spring 2011/2012 Semester

Efficient Inference and Learning with Cardinality-like Potentials

Wed, 20 Jun 2012, 14:00
Speaker: Danny Tarlow , University of Toronto)
Comment: Special Talk

Structured Prediction Cascades

Thu, 14 Jun 2012, 10:15
Speaker: Aviv Peretz , The Hebrew University
Comment: Student Talk

A Spectral Algorithm for Learning Hidden Markov Models

Thu, 07 Jun 2012, 10:15
Speaker: Hillel Taub-Tabib , The Hebrew University
Comment: Student Talk

What happens when design students hear about machine learning.

Thu, 31 May 2012, 10:15
Speaker: Michael Fink , Google

Pricing Derivatives Using Regret Minimization

Thu, 24 May 2012, 10:15
Speaker: Eyal Gofer , Tel Aviv University

Log-sum-exp, convexity and covariance estimation

Thu, 17 May 2012, 10:15
Speaker: Ami Wiesel , The Hebrew University

Agnostic Active Learning

Thu, 10 May 2012, 10:15
Speaker: Noam Horev , The Hebrew University
Comment: Student Talk

Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

Thu, 03 May 2012, 10:15
Speaker: Miri Cohen , The Hebrew University
Comment: Student Talk

Norm-based Adaboost-like algorithms

Thu, 19 Apr 2012, 10:15
Speaker: Dan Gutfreund , IBM Resarch

The Isotron Algorithm: High-Dimensional Isotonic Regression

Thu, 29 Mar 2012, 10:15
Speaker: Hila Gonen , The Hebrew University
Comment: Student Talk

Globally Optimizing Graph Partitioning Problems Using Message Passing

Thu, 22 Mar 2012, 10:15
Speaker: Elad Mezuman , The Hebrew University

Bounded Planning in Passive POMDPs

Thu, 15 Mar 2012, 10:15
Speaker: Roy Fox , The Hebrew University

Fall 2011/2012 Semester

Combining One-Class Classifiers via Meta-Learning

Thu, 02 Feb 2012, 10:15
Speaker: Eitan Menahem , BGU

Learning Large Scale Music Recommendations

Thu, 26 Jan 2012, 10:15
Speaker: Noam Koenigstein , Tel Aviv University

GraphLab: Parallel Large Scale Machine Learning

Thu, 19 Jan 2012, 10:15
Speaker: Danny Bickson , Carnegie Mellon University

TBA

Wed, 18 Jan 2012, 15:00
Speaker: Greg Shakhnarovich , Toyota Technological Institute at Chicago
Comment: Note the special day

Active Learning under Margin Assumptions

Sun, 15 Jan 2012, 13:00
Speaker: Sivan Sabato , The Hebrew University
Comment: Note the special day

Decomposing Documents into Authorial Threads

Thu, 12 Jan 2012, 10:15
Speaker: Moshe Koppel , Bar-Ilan University

Cancled

Wed, 11 Jan 2012, 15:00
Speaker: Ilya Stuskever , Univ. of Toronto -> Stanford
Comment: cancled

Programming by Example: from Pipe Dreams to the Future

Wed, 04 Jan 2012, 15:00
Speaker: Adam Kalai , Microsoft Research
Comment: Note the special day

The Median Hypothesis

Thu, 22 Dec 2011, 10:15
Speaker: Ran Gilad-Bachrach , Microsoft Research

Graph-guided Importance sampling

Thu, 08 Dec 2011, 10:15
Speaker: Rina Dechter , University of California Irvine (UCI)
Comment: Joint work with Vibhav Gogate. Rina is visiting HUJI for the year.

Fast Effective Clustering for Graphs and Documents

Thu, 01 Dec 2011, 10:15
Speaker: William Cohen , Carnegie Mellon University

Architecture 101 for Machine Learning

Thu, 24 Nov 2011, 10:15
Speaker: Uri Weiser , The Technion

Learning a Classifier When the Labeling Is Known

Thu, 17 Nov 2011, 10:15
Speaker: Shalev Ben David , MIT
Comment: Second of the week

Optimization, Learning and the Universality of Mirror Descent

Wed, 16 Nov 2011, 15:00
Speaker: Nathan Srebro , Toyota Technological Institute at Chicago
Comment: Notice the special date and time!

Multiclass learnability and the ERM principle

Thu, 10 Nov 2011, 10:15
Speaker: Amit Daniely , The Hebrew University

Fast Effective Clustering for Graphs and Documents

Thu, 03 Nov 2011, 10:15
Speaker: William Cohen , Carnegie Mellon University
Comment: postponed to Dec. 1st

Domain Adaptation–Can Quantity compensate for Quality

Thu, 03 Nov 2011, 10:15
Speaker: Ruth Urner , The University of Waterloo

Spring 2010/2011 Semester

Simplified PAC-Bayesian Margin Bounds

Thu, 26 May 2011, 10:15
Speaker: Alon Gonen , The Hebrew University
Comment: Student Talk

Unsupervised Supervised Learning: Who Needs Labels Anyway?

Thu, 19 May 2011, 10:15
Speaker: Guy Lebanon , Georgia Institute of Technology

Learning rates and principled reward discounting in RL

Thu, 12 May 2011, 10:15
Speaker: Tali Tishby , The Hebrew University

Sublinear optimization for machine learning

Thu, 05 May 2011, 10:15
Speaker: Elad Hazan , Technion - Israel Institute of Technology

Wikipedia-based semantics, with application to Machine Learning and Information Retrieval

Thu, 07 Apr 2011, 10:15
Speaker: Shaul Markovitch , Technion - Israel Institute of Technology

Learning Quickly When Irrelevant Attributes Abound

Thu, 31 Mar 2011, 10:15
Speaker: Amit Beka , The Hebrew University

Tight Sample Complexity of Large-Margin Learning

Thu, 24 Mar 2011, 10:15
Speaker: Sivan Sabato , The Hebrew University

Efficient learning for structured prediction

Thu, 17 Mar 2011, 10:15
Speaker: Ofer Meshi , The Hebrew University

Efficient blue-noise sampling using multiscale MCMC sampler

Thu, 10 Mar 2011, 10:15
Speaker: Raanan Fattal , The Hebrew University

Wearable sensor activity analysis using semi-Markov models with a grammar

Thu, 24 Feb 2011, 10:15
Speaker: Gideon Dror , The Academic College of Tel-Aviv-Yaffo

Convergent Message Passing Algorithms - A Unifying View

Thu, 17 Feb 2011, 10:15
Speaker: Talya Meltzer , The Hebrew University

Fall 2010/2011 Semester

Multi-view learning of speech feature spaces

Thu, 13 Jan 2011, 10:15
Speaker: Karen Livescu , TTI, Chicago

Interplay Between Sampling and Estimation: A Unified Hilbert Space Approach

Thu, 06 Jan 2011, 10:15
Speaker: Tomer Michaeli , Technion - Institute of Technology.

Robust High-dimensional Principal Component Analysis

Thu, 30 Dec 2010, 10:15
Speaker: Shie Mannor , The Technion.

Optimal Distributed Online Prediction using Mini-Batches

Thu, 23 Dec 2010, 10:15
Speaker: Ran Gilad-Bachrach , Microsoft.

Semi-Supervised Learning - A transductive graph-based algorithm and a theoretical model

Thu, 16 Dec 2010, 10:15
Speaker: Nir Rosenfeld , HUJI
Comment: Student seminar talk

A Tale of Two Norms

Thu, 02 Dec 2010, 10:15
Speaker: Nathan Srebro , TTI, Chicago

Natural Image Denoising: Optimality and Inherent Bounds

Thu, 25 Nov 2010, 10:15
Speaker: Anat Levin , Weizmann Institute of Science

Evaluating Recommender Systems

Thu, 18 Nov 2010, 10:15
Speaker: Guy Shani , Ben Gurion University

Approximated Learning and Inference in Large Scale Graphical Models

Wed, 17 Nov 2010, 13:00
Speaker: Tamir Hazan , TTI, Chicago
Comment: Note special date and time!

General Classes of Performance Bounds for Parameter Estimation

Thu, 11 Nov 2010, 10:15
Speaker: Koby Todros , Ben Gurion University

Uncertainty Estimates, Classification and Active Learning

Thu, 04 Nov 2010, 10:15
Speaker: Boaz Nadler , Weizmann Institute of Science

Optimal Control for Complex Motor Behavior - Theoretical and Practical Developments

Thu, 28 Oct 2010, 10:15
Speaker: Yuval Tassa , The Hebrew University

Machine Learning in the Data Revolution Era

Thu, 14 Oct 2010, 10:15
Speaker: Shai Shalev-Shwartz , The Hebrew University

Spring 2009/2010 Semester

Which clustering algorithm should I use? Towards principled guidelines

Thu, 07 Oct 2010, 10:15
Speaker: Shai Ben-David , University of Waterloo

Continuous-Time Belief Propagation

Thu, 17 Jun 2010, 10:15
Speaker: Tal El-Hay , The Hebrew University

Copula Networks

Thu, 10 Jun 2010, 10:15
Speaker: Gal Elidan , The Hebrew University

The value of future-information – the missing piece in reinforcement learning

Thu, 03 Jun 2010, 10:15
Speaker: Naftali Tishby , The Hebrew University

Query by Committee

Thu, 27 May 2010, 10:15
Speaker: Adam Nitzan , The Hebrew University

Learning and Domain Adaptation

Thu, 13 May 2010, 10:15
Speaker: Yishay Mansour , Tel-Aviv University

Learning to Predict by the Methods of Temporal Differences

Thu, 06 May 2010, 10:15
Speaker: Inbal Marhaim , The Hebrew University

Learning Linear Classifiers with Confidence

Thu, 29 Apr 2010, 10:15
Speaker: Koby Crammer , The Technion

When Quantity Makes Quality: Learning with Information Constraints

Thu, 22 Apr 2010, 10:15
Speaker: Ohad Shamir , The Hebrew University

A Joint Factor-Network Model for Social Networks Evolution

Thu, 15 Apr 2010, 10:15
Speaker: Amit Gruber , University of Toronto

Locality Sensitive Hashing

Thu, 18 Mar 2010, 10:15
Speaker: Roie Kliper , The Hebrew University

Long time asymptotic in Hidden Markov Models

Thu, 11 Mar 2010, 10:15
Speaker: Pavel Chigansky , The Hebrew University

Belief Propagation and Beyond

Thu, 04 Mar 2010, 10:15
Speaker: Michael Chertkov , Los Alamos National Laboratory

Learning from Labeled and Unlabeled Data, Global vs. Multiscale Approaches.

Thu, 25 Feb 2010, 10:15
Speaker: Boaz Nadler , The Weizmann Institute

Fall 2009/2010 Semester

Combining One-Class Classifiers via Meta-Learning

Tue, 02 Feb 2010, 10:15
Speaker: Eitan Menahem , Ben-Gurion University

TBA

Tue, 02 Feb 2010, 10:15
Speaker: Eitan Menahem , Ben-Gurion University of the Negev

The Multiarmed Bandit Problem

Thu, 14 Jan 2010, 10:15
Speaker: Tomer Ezra , The Hebrew University

Combining Labeled and unlabeled examples with CO- Training

Thu, 07 Jan 2010, 10:15
Speaker: Cobi Cario , The Hebrew University

Recent Advances in Solving Combinatorial Optimization Tasks over Graphical Models

Thu, 31 Dec 2009, 10:15
Speaker: Rina Dechter , UC Irvine

A Belief-Propagation Algorithm for Constrained Linear Least-Squares Problems

Thu, 24 Dec 2009, 10:15
Speaker: Jacob Goldberger , Bar-Ilan University

No Free Lunch theorems for Domain Adaptation Learning

Thu, 17 Dec 2009, 10:15
Speaker: Shai Ben-David , University of Waterloo

From "GooGoo images" to "Big Bird" - 10 Interactive Projects Bridging Machine Learning and Design

Thu, 10 Dec 2009, 10:15
Speaker: Michael Fink , Google

The "tree-dependent components" of natural scenes are edge filters

Thu, 03 Dec 2009, 10:15
Speaker: Daniel Zoran , The Hebrew University

An LP View of the M-best MAP problem

Thu, 26 Nov 2009, 10:15
Speaker: Menachem Fromer , The Hebrew University

Learning in Real-Time and Adaptivity of Online Algorithms

Thu, 19 Nov 2009, 10:15
Speaker: Elad Hazan , IBM

Point-Based Algorithms for Solving Partially Observable Markov Decision Processes (POMDPs)

Thu, 12 Nov 2009, 10:15
Speaker: Guy Shani , Ben-Gurion University

Modeling Natural Image Statistics with Markov Random Fields

Thu, 05 Nov 2009, 10:15
Speaker: Urs Koster , University of Helsinki

Efficient Learning of Sparse Predictors

Thu, 29 Oct 2009, 10:15
Speaker: Shai Shalev-Shwartz , The Hebrew University

Reducing Label Complexity by Learning From Bags

Thu, 22 Oct 2009, 10:15
Speaker: Sivan Sabato , The Hebrew University

Spring 2008/2009 Semester

Probabilistic Models for Holistic Scene Understanding

Thu, 25 Jun 2009, 10:15
Speaker: Daphne Koller , Stanford University

Markov Logic Networks

Thu, 18 Jun 2009, 10:15
Speaker: Gil Ben-Zvi , The Hebrew University

Algorithms for Transfer Learning and Semi-Supervised Learning (A review of a paper by Ando & Zhang)

Thu, 04 Jun 2009, 10:15
Speaker: Ido Ginodi , The Hebrew University

Information theoretic model validation in clustering

Tue, 19 May 2009, 10:15
Speaker: Joachim Buhmann , ETH Zurich
Comment: (Special Date)

Mean Field Variational Approximation for Continuous-Time Bayesian Networks

Thu, 14 May 2009, 10:15
Speaker: Ido Cohn , The Hebrew University

Generalization in Learning

Thu, 07 May 2009, 10:15
Speaker: Yevgeny Seldin , The Hebrew University

Generalization in Reinforcement Learning

Thu, 23 Apr 2009, 10:15
Speaker: Peter Stone , The University of Texas at Austin

Thu, 02 Apr 2009, 10:15
Speaker: Gal Chechik , Google

Energy Minimization Methods and Graph Cuts

Thu, 26 Mar 2009, 10:15
Speaker: Danny Rosenberg , The Hebrew University

Norm-Product Belief Propagation: Primal-Dual Message-Passing Algorithms for LP-relaxations and Approximate Inference

Thu, 19 Mar 2009, 10:15
Speaker: Tamir Hazan , The Hebrew University

Postponed

Thu, 12 Mar 2009, 10:15
Speaker: Yevgeny Seldin , The Hebrew University

Fall 2008/2009 Semester

Revealing Modularity and Organization in Biological Networks Using Bi-clustering

Thu, 05 Feb 2009, 10:15
Speaker: Asaf Pe'er , The Hebrew University

Stochastic Convex Optimization

Thu, 29 Jan 2009, 10:15
Speaker: Nati Srebro , Toyota Technological Insitute - Chicago

Decomposable graphical models: covariance estimation and principal component analysis

Thu, 22 Jan 2009, 10:15
Speaker: Ami Wiesel , University of Michigan

All Learning Is Robust

Thu, 15 Jan 2009, 10:15
Speaker: Shie Mannor , The Technion

Support Vector Machines with a Reject Option

Thu, 08 Jan 2009, 10:15
Speaker: Joseph Keshet , IDIAP Research Institute

Nonlinearity, memory, and phase transitions in learning

Thu, 01 Jan 2009, 10:15
Speaker: Ilya Nemenman , Los Alamos National Laboratory

Tightening LP Relaxations for MAP using Message Passing

Thu, 18 Dec 2008, 10:15
Speaker: Talya Meltzer , The Hebrew University

Machine Learning of Evaluation (with Applications to Computer Chess)

Thu, 04 Dec 2008, 10:15
Speaker: Amir Ban , The Hebrew University

From Co-Occurrence to Correspondence

Thu, 27 Nov 2008, 10:15
Speaker: Ben Taskar , University of Pennsylvania

Learning Bounded Treewidth Bayesian Networks

Thu, 13 Nov 2008, 10:15
Speaker: Gal Elidan , The Hebrew University

Spring 2007/2008 Semester

* Pre-ICML-UAI-COLT talks - Part III

Tue, 01 Jul 2008, 10:30
Speaker: Amit Gruber, Ohad Shamir, Tamir Hazan , The Hebrew University
Comment: Note special day and time!

* Non-Parametric Modeling and Visualization of Partially Ranked Data

Mon, 30 Jun 2008, 10:15
Speaker: Guy Lebanon , Purdue University
Comment: Note special day!

* Pre-ICML-UAI-COLT talks - Part II

Sun, 29 Jun 2008, 16:15
Speaker: Yevgeny Seldin, Ohad Shamir , The Hebrew University
Comment: Note special day and time!

* Pre-ICML-UAI-COLT talks - Part I

Sun, 29 Jun 2008, 10:00
Speaker: Tal El-Hay , The Hebrew University
Comment: Note special day and time!

Active Sampling for Multiple Output Identification

Thu, 26 Jun 2008, 10:15
Speaker: Oded Margalit , IBM

Latent Topic Models for Hypertext

Thu, 19 Jun 2008, 10:15
Speaker: Amit Gruber , The Hebrew University

Towards Modeling Biological Networks Using Graphical Models with Improved Free Energy Approximations

Thu, 12 Jun 2008, 10:15
Speaker: Ariel Jaimovich , The Hebrew University

Multiple Instance Learning for CAD (Computer Aided Diagnosis)

Thu, 15 May 2008, 10:15
Speaker: Inna Stainvas , Siemens

Fall 2007/2008 Semester

On the Exchange Rate between Equivalence Constraints and Labels

Thu, 01 May 2008, 10:15
Speaker: Liat Ein-Dor , Intel

Selective-PAC learning

Thu, 17 Apr 2008, 10:15
Speaker: Yair Wiener , Technion

Robust Real Time Pattern Matching using Bayesian Sequential Hypothesis Testing

Thu, 10 Apr 2008, 10:15
Speaker: Ofir Pele , The Hebrew University

Convergent Message-Passing Algorithms for Inference over General Graphs with Convex Free Energies

Thu, 27 Mar 2008, 10:15
Speaker: Tamir Hazan , The Hebrew University

Online Prediction: The Role of Convexity and Randomization

Thu, 20 Mar 2008, 10:15
Speaker: Shai Shalev-Shwartz , TTI

Gaussian Belief Propagation for Solving Systems of Linear Equations: Theory and Application

Thu, 13 Mar 2008, 10:15
Speaker: Danny Bickson , The Hebrew University

* Does a large data-set mean more, or less, work?

Sun, 24 Feb 2008, 10:15
Speaker: Nathan Srebro , Toyota Technological Institute at Chicago
Comment: Joint learning-vision seminar (in Ross 201).

A Parallel Decomposition Solver for SVM: Distributed Dual Ascend using Fenchel Duality

Thu, 14 Feb 2008, 10:15
Speaker: Tamir Hazan , The Hebrew University

Learning in High Dimensions, Sparsity and Treelets

Thu, 24 Jan 2008, 10:15
Speaker: Boaz Nadler , Weizmann Institute of Science

* The Empirical Minimization Algorithm - Upper and Lower Bounds

Wed, 23 Jan 2008, 10:30
Speaker: Shahar Mendelson , ANU, Technion
Comment: Joint learning-theory seminar (in Ross 201).

Measure Concentration of Strongly Mixing Processes with Applications

Thu, 17 Jan 2008, 10:15
Speaker: Aryeh (Leonid) Kontorovich , Weizmann Institute of Science

On LASSO type estimators

Thu, 10 Jan 2008, 10:15
Speaker: Yaacov Ritov , The Hebrew University

Robust Inference in Bayesian Networks, with Application to Gene Expression Time-Series Data

Thu, 03 Jan 2008, 10:15
Speaker: Omer Berkman , Tel-Aviv University