wovepaper — the arXiv observatory

NewEvery arXiv paper, its researchers & institutions — mapped.

papers

Publications (20)

Multi-Instance Learning with Any Hypothesis Class

Sivan Sabato, Naftali Tishby

Multiclass learnability and the ERM principle

Amit Daniely, Sivan Sabato, Shai Ben-David +1

Efficient Active Learning of Halfspaces: an Aggressive Approach

Alon Gonen, Sivan Sabato, Shai Shalev-Shwartz

Auditing: Active Learning with Outcome-Dependent Query Costs

Sivan Sabato, Anand D. Sarwate, Nathan Srebro

Multiclass Learning Approaches: A Theoretical Comparison with Implications

Amit Daniely, Sivan Sabato, Shai Shalev Shwartz

Submodular Learning and Covering with Response-Dependent Costs

Sivan Sabato

Active Learning of Halfspaces under a Margin Assumption

Alon Gonen, Sivan Sabato, Shai Shalev-Shwartz

Nearest-Neighbor Sample Compression: Efficiency, Consistency, Infinite Dimensions

Aryeh Kontorovich, Sivan Sabato, Roi Weiss

Loss minimization and parameter estimation with heavy tails

Daniel Hsu, Sivan Sabato

Distribution-Dependent Sample Complexity of Large Margin Learning

Sivan Sabato, Nathan Srebro, Naftali Tishby

Feature Multi-Selection among Subjective Features

Sivan Sabato, Adam Kalai

Tunable Sensitivity to Large Errors in Neural Network Training

Gil Keren, Sivan Sabato, BjÃ¶rn Schuller

Temporal anomaly detection: calibrating the surprise

Eyal Gutflaish, Aryeh Kontorovich, Sivan Sabato +2

Fast Single-Class Classification and the Principle of Logit Separation

Gil Keren, Sivan Sabato, BjÃ¶rn Schuller

Tight Sample Complexity of Large-Margin Learning

Sivan Sabato, Nathan Srebro, Naftali Tishby

Active Nearest-Neighbor Learning in Metric Spaces

Aryeh Kontorovich, Sivan Sabato, Ruth Urner

Selecting with History

Tom Hess, Sivan Sabato

Interactive algorithms: from pool to stream

Sivan Sabato, Tom Hess

Active Regression by Stratification

Sivan Sabato, Remi Munos

Learning Sparse Low-Threshold Linear Classifiers

Sivan Sabato, Shai Shalev-Shwartz, Nathan Srebro +2