Empirical Inference 2013

16 papers
The 2013 edition of Empirical Inference comprised 22 papers centered on statistical learning theory and optimization. Primary research themes included continuous convex relaxations for discrete submodular optimization and the application of sequential Rademacher complexity to assess online learnability. Scholars also focused on online-to-batch conversion techniques for statistical generalization and the direct approximation of divergences between probability distributions. Theoretical advancements were prominent in areas such as PAC-Bayesian theory and the statistical analysis of Support Vector Machines (SVMs). Specific studies explored kernels, pre-images, and transductive online learning via randomized rounding. Prolific contributors during this period included Bernhard Schölkopf, Masashi Sugiyama, and Ingo Steinwart, as well as Nicolò Cesa-Bianchi and Ohad Shamir. The collective work from this year emphasized refining mathematical frameworks for the median hypothesis and improving the efficiency of transductive learning algorithms.

Top Research Directions

The 14 research directions with Empirical Inference 2013 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Continuous Relaxation of Submodular Functions16.2%
2Functional Gradient Descent for Ensemble Learning16.2%
3Generalization Guarantees via Online to Batch Conversion16.2%
4Implicit Regularization via Early Stopping16.2%
5Incorporating Structural Dependencies into Sparse Regularization16.2%
6Moving Beyond Binary Classification Frameworks16.2%
7Non-Vacuous Generalization Bounds for Deep Learning16.2%
8Robust Boosting in the Presence of Label Noise16.2%
9Scaling Kernel Methods Beyond Quadratic Complexity16.2%
10Sequential Rademacher Complexity for Online Learning16.2%
11The Empirical Validation Gap16.2%
12The Mechanics of Benign Overfitting in High Dimensions16.2%
13The Theoretical Gap in Complex Iterative Algorithms16.2%
14Unified Mathematical Frameworks for Optimization Algorithms16.2%

Download all directions as CSV

Institutions

Institutions credited by Empirical Inference 2013 papers: a paper credits every institution named in its affiliations, once. 10 institutions share 5 credited papers.

#InstitutionPapersShare
1Microsoft (United States) 240.0%
2Italian Institute of Technology 120.0%
3Massachusetts Institute of Technology 120.0%
4Princeton University 120.0%
5University at Albany, State University of New York 120.0%
6University College London 120.0%
7University of Genoa 120.0%
8University of Milan 120.0%
9École Centrale Paris 120.0%
10École Polytechnique Fédérale de Lausanne 120.0%

Download all institutions as CSV

About this data

Papers. Empirical Inference 2013 lists 16 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 5 of 16 papers (31.2%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Empirical Inference 2013”, https://lacuna.tiptreesystems.com/venue/empirical-inference/2013.

Top Authors

AuthorPapers
Bernhard Schölkopf2
David McAllester1
Dominik Janzing1
Gunnar Ratsch1
Ingo Steinwart1
Jonas Peters1
Joris M. Mooij1
Kun Zhang1
Leon Bottou1
Lorenzo Rosasco1
Marius Kloft1
Masashi Sugiyama1
Massimiliano Pontil1
Nicolò Cesa-Bianchi1
Ohad Shamir1
Ran Gilad-Bachrach1
Robert E. Schapire1
Samy Bengio1
Silvia Villa1
Tomaso Poggio1

Impactful Papers

Papers from Empirical Inference 2013 that shaped research clusters.

Influential

Papers

Title
Direct Approximation of Divergences Between Probability Distributions
Efficient Learning of Sparse Ranking Functions
Efficient Transductive Online Learning via Randomized Rounding
Empirical Inference - Festschrift in Honor of Vladimir N. Vapnik
Explaining AdaBoost
In Hindsight: Doklady Akademii Nauk SSSR, 181(4), 1968
Kernels, Pre-images and Optimization
Multi-task Learning for Computational Biology: Overview and Outlook
On Learnability, Complexity and Stability
On Sparsity Inducing Regularization Methods for Machine Learning
On the Relations and Differences Between Popper Dimension, Exclusion Dimension and VC-Dimension
PAC-Bayesian Theory
Semi-supervised Learning in Causal and Anticausal Settings
Some Remarks on the Statistical Analysis of SVMs and Related Methods
Statistical Learning Theory in Practice
The Median Hypothesis