About

The conference is a single track meeting that includes invited talks as well as oral presentations of all refereed papers. We invited submissions of papers addressing theoretical aspects of machine learning and related topics. We strongly support 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

Active learning

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.

For more information visit the COLT 2013 website.

Videos

Invited Talks

54:32

Learning Representations: A Challenge for Learning Theory

Yann LeCun

Aug 9, 2013

20579 views

26th Annual Conference on Learning Theory (COLT), Princeton 2013

About

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

Active learning

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.

Videos

Invited Talks

Learning Representations: A Challenge for Learning Theory

Yann LeCun

Is Intractability a Barrier for Machine Learning?

Sanjeev Arora

Online Learning (I)

Online Learning with Predictable Sequences

Alexander Rakhlin

A Tale of Two Metrics: Simultaneous Bounds on Competitiveness and Regret

Siddharth Barman

Online Learning for Time Series Prediction

Elad Hazan

Competing With Strategies

Karthik Sridharan

Approachability, fast and slow

Vianney Perchet

Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families

Fares Hedayati

Online Learning (II)

Opportunistic Strategies for Generalized No-Regret Problems

Andrey Bernstein

Online Similarity Prediction of Networked Data from Known and Unknown Graphs

Mark Herbster

Prediction by random-walk perturbation

Gergely Neu

Computational Learning Theory (I)

Learning Halfspaces Under Log-Concave Densities: Polynomial Approximations and M...

Raghu Meka

Complexity Theoretic Lower Bounds for Sparse Principal Component Detection

Quentin Berthet

Computational Learning Theory (II)

Representation, Approximation and Learning of Submodular Functions Using Low-ran...

Pravesh Kothari

Algorithms and Hardness for Robust Subspace Recovery

Moritz Hardt

Polynomial Time Optimal Query Algorithms for Finding Graphs with Arbitrary Real ...

Sung-Soon Choi

Computational Learning Theory (III)

Randomized partition trees for exact nearest neighbor search

Sanjoy Dasgupta

Efficient Learning of Simplices

Luis Rademacher

Unsupervised Learning

Learning a set of directions

Wouter M. Koolen

A Tensor Spectral Approach to Learning Mixed Membership Community Models

Rong Ge

Optimal Probability Estimation with Applications to Prediction and Classificatio...

Ananda Theertha Suresh

Blind Signal Separation in the Presence of Gaussian Noise

James Voss

Sparse Adaptive Dirichlet-Multinomial-like Processes

Tor Lattimore

Dimensionality Reduction and Loss Function

Subspace Embeddings and ℓp-Regression Using Exponential Random Variables

Qin Zhang

Surrogate Regret Bounds for the Area Under the ROC Curve via Strongly Proper Los...

Shivani Agarwal

A Theoretical Analysis of NDCG Type Ranking Measures

Liwei Wang

Statistical Learning Theory (I)

Divide and Conquer Kernel Ridge Regression

Yuchen Zhang

Classification with Asymmetric Label Noise: Consistency and Maximal Denoising

Gilles Blanchard

Boosting with the Logistic Loss is Consistent