I am a senior lecturer at Department of Electrical Engineering at Tel Aviv University. My research focuses on Theoretical Machine Learning. I received my Ph.D from the Center for Brain Sciences (ELSC) at The Hebrew University of Jerusaelm under the supervision of Amir Globerson.

**Contact**

Tel Aviv University

Department of Electrical Engineering

EE-Labs Bulding, Room 131

__Email:__ rlivni at tauex.tau.ac.il

Spring 2020: Introduction to Computational Learning Theory With the Corona, like everyone else, lectures are given online.

**A Limitation of the PAC-Bayes Framework,**

*
R. Livni and S. Moran,
*

[pdf]

**Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study,**

*
A. Dauber, M. Feder, T. Koren and R. Livni,
*

[pdf]

**Prediction with Corrupted Expert Advice,**

*
I. Amir, I. Attias, T. Koren, R. Livni and Y. Mansour,
*

[pdf]

**Passing Tests without Memorizing: Two Models for Fooling Discriminators,**

*
O. Bousquet, R. Livni and S. Moran,
*

[pdf]

**An Algorithm for Training Polynomial Networks,**

*
R. Livni, S.Shalev-Shwartz and O. Shamir,
*

[pdf]

**An Equivalence Between Private Classification and Online Prediction,**

*
M. Bun, R. Livni and S. Moran,
*

61^{st} Symposium on Foundations of Computer Science (FOCS), 2020

[pdf]
** (Best paper award)
**

**On the Expressive Power of Kernel Methods and the Efficiency of Kernel Learning by Association Schemes,**

*
P.K Kothari and R. Livni,
*

31^{st} Conference on Algorithmic Learning Theory (ALT), 2020

[pdf]

**Graph-based Discriminators: Sample Complexity and Expressiveness,**

*
R. Livni and Y. Mansour,
*

Advances of Neural Information and Processing Systems 32 (NeurIPS), 2019

[pdf]

**On Communication Complexity of Classification Problems,**

*
D. Kane, R. Livni, S. Moran and A. Yehudayoff,
*

32^{nd} Conference on Learning Theory (COLT), 2019

[pdf],
[video]

**Private PAC Learning Implies Finite Littlestone Dimension,**

*
N. Alon, R. Livni, M. Malliaris and S. Moran,
*

51^{st} Symposium on the Theory of Computing (STOC), 2019

[pdf],
,

**Generalize Across Tasks: Efficient Algorithms for Linear Representation Learning,**

*
B. Bullins, E. Hazan, A. Kalai and R. Livni,
*

30^{th} Conference on Algorithmic Learning Theory (ALT), 2019

[pdf],

**Open Problem: Improper Learning of Mixtures of Gaussians,**

*
E. Hazan and R. Livni,
*

31^{st} Conference on Learning Theory (COLT), 2018

[pdf],

**Agnostic Learning by Refuting,**

*
P. K. Kothari, R. Livni,
*

9^{th} Innovations in Theoretical Computer Science (ITCS), 2018

[pdf]

**
Affine-Invariant Online Optimization and the Low-Rank Expert Problem
**

*
T. Koren, R. Livni
*

Advances of Neural Information and Processing Systems 30 (NIPS), 2017

[pdf]

**
Multi-Armed Bandits with Metric Movement Costs
**

*
T. Koren, R. Livni, Y. Mansour
*

Advances of Neural Information and Processing Systems 30 (NIPS), 2017

[pdf]

**
Learning Infinite--Layer Networks: Without the Kernel Trick
**

*
R. Livni, D. Carmon, A. Globerson
*

34^{th} International Conference on Machine Learning (ICML), 2017

[pdf]

**
Effective Semisupervised Learning on Manifolds
**

*
A. Globerson, R. Livni, S. Shalev-Shwartz
*

30^{th} Conference on Learning Theory (COLT), 2017

[pdf]

**
Bandits with Movement Costs and Adaptive Pricing
**

*
T. Koren, R. Livni, Y. Mansour
*

30^{th} Conference on Learning Theory (COLT), 2017

[pdf],
[video]

**
Online Pricing With Strategic and Patient Buyers,
**

*
M. Feldman, T. Koren, R. Livni, Y. Mansour, A. Zohar.
*

Advances of Neural Information and Processing Systems 29 (NIPS), 2016

[pdf],
[video]

**
Online Learning With Low Rank Experts,
**

*
E. Hazan, T. Koren, R. Livni, Y. Mansour
*

29^{th} Conference on Learning Theory (COLT), 2016

[pdf],
[video]

**
Improper Deep Kernels,**

*
U.Heinemann, R. Livni, E. Eban, G. Elidan, A. Globerson.
*

19^{th} International Conference on Artificial Intelligence and Statistics (AISTAT), 2016

[pdf]

**
Classification with Low Rank and Missing Data,
**

*
E. Hazan, R. Livni, Y. Mansour
*

32^{nd} International Conference on Machine Learning (ICML), 2015

[pdf],
[code],
[video]

**
On the Computational Efficiency of Training Neural Networks,
**

Advances in Neural Information Processing Systems 27 (NIPS), 2014

[pdf]

**
Honest Compressions and Their Application to Compression Schemes,
**

26

[pdf]

**
Vanishing Component Analysis,**

30

[pdf ] [code]

**
A Simple Geometric Interpretation of SVM using Stochastic Adversaries,
**

15

[pdf], [supplementary]

**
On Extreme Points of the Dual Ball of a Polyhedral Space,
**

*
R. Livni
*

Extracta Mathematicae.24(3):
219-241, 2009.

[pdf]