27th Annual Conference on Learning Theory (COLT), Barcelona 2014

About

The conference strongly supports a broad definition of learning theory, including, but not limited to:

• Design and analysis of learning algorithms and their generalization ability\ • Computational complexity of learning\ • Optimization procedures for learning\ • Unsupervised, semi-supervised learning, and clustering\ • Online learning\ • Interactive learning\ • Kernel Methods\ • High dimensional and non-parametric empirical inference, including sparsity methods\ • Planning and control, including reinforcement learning\ • Learning with additional constraints: E.g. privacy, time or memory budget, communication\ • Learning in other settings: E.g. social, economic, and game-theoretic\ • Analysis of learning in related fields: natural language processing, neuroscience, bioinformatics, privacy and security, machine vision, data mining, information retrieval.

Additional information can be found at COLT 2014 home page.

Videos

Invited Speakers

50:22

Implementing the "Wisdom of the Crowd"

Yishay Mansour

Jul 15, 2014

3725 views

27th Annual Conference on Learning Theory (COLT), Barcelona 2014

About

Videos

Invited Speakers

Implementing the "Wisdom of the Crowd"

Yishay Mansour

On the Computational and Statistical Interface and "BIG DATA"

Michael I. Jordan

Unsupervised Learning; Dictionary Learning; Latent Variable Models

Uniqueness of Tensor Decompositions with Applications to Polynomial Identifiabil...

Moses Charikar

New Algorithms for Learning Incoherent and Overcomplete Dictionaries

Ankur Moitra

Belief Propagation, Robust Reconstruction and Optimal Recovery of Block Models

Joe Neeman

Concentration

An Inequality with Applications to Structured Sparsity and Multitask Dictionary ...

Andreas Maurer

Learning without Concentration

Shahar Mendelson

Localized Complexities for Transductive Learning

Ilya O. Tolstikhin

Unsupervised Learning; Dictionary Learning; Latent Variable Models II

Density-preserving quantization with application to graph downsampling

Morteza Alamgir

Mixed Regression: Minimax Optimal Rates

Constantine Caramanis

Learning Sparsely Used Overcomplete Dictionaries

Prateek Jain

Edge Label Inference in Generalized Stochastic Block Models: from Spectral Theor...

Laurent Massouile

Statistical Learning Theory

Uniqueness of ordinal embedding

Matthäus Kleindessner

On the Consistency of Output Code Based Learning Algorithms for Multiclass Learn...

Harish G. Ramaswamy

The sample complexity of agnostic learning under deterministic labels

Ruth Urner

Sample Compression for Multi-label Concept Classes

Rahim Samei

Elicitation and Identification of Properties

Ingo Steinwart

The complexity of learning halfspaces using generalized linear methods

Amit Daniely

Bayes-Optimal Scorers for Bipartite Ranking

Aditya Menon

Unsupervised Learning; Mixture Models

Learning Mixture of Discrete Distributions over Product Spaces

Prateek Jain

The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussia...

Joseph Anderson

Faster and Sample Near-Optimal Algorithms for Proper Learning Mixtures of Gaussi...

Gautam Kamath

Online Learning

Learning with Perturbations via Gaussian Smoothing

Chansoo Lee

Most Correlated Arms Identification

Sébastien Bubeck

Online Learning with Composite Loss Functions

Ofer Dekel

A Second-order Bound with Excess Losses

Pierre Gaillard

Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and N...

Francesco Orabona

Follow the Leader with Dropout Perturbations

Tim van Erven

Online Nonparametric Regression

Alexander Rakhlin

Statistical and Online Learning

Community Detection via Random and Adaptive Sampling

Se-Young Yun

Efficiency of conformalized ridge regression

Evgeny Burnaev

Logistic Regression: Tight Bounds for Stochastic and Online Optimization

Kfir Y. Levy

Learning with Partial Feedback

Finding a most biased coin with fewest flips

Karthekeyan Chandrasekaran

On the Complexity of A/B Testing

Emilie Kaufmann