Preprints/Tech Reports

Better Best of Both Worlds Bounds for Bandits with Switching Costs

I. Amir, G. Azov, T. Koren and R. Livni

Making Progress Based on False Discoveries

R. Livni

Thinking Outside the Ball: Optimal Learning with Gradient Descent for Generalized Linear Stochastic Convex Optimization

I. Amir, R. Livni and N. Srebro

Benign Underfitting of Stochastic Gradient Descent

T. Koren, R. Livni, Y. Mansour and U. Sherman

An Algorithm for Training Polynomial Networks,

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

Publications

Never Go Full Batch (in Stochastic Convex Optimization)

I. Amir, Y. Carmon, T. Koren, R. Livni

Advances of Neural Information and Processing Systems 34 (NeurIPS), 2021

Littlestone Classes are Privately Online Learnable

Noah Golowich, Roi Livni

Advances of Neural Information and Processing Systems 34 (NeurIPS), 2021

SGD Generalizes Better Than GD (And Regularization Doesn't Help),

I. Amir, T. Koren and R. Livni,

34th Conference on Learning Theory (COLT), 2021

Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games,

S. Hanneke, R. Livni and S. Moran,

Best paper runner-up

34th Conference on Learning Theory (COLT), 2021

A Limitation of the PAC-Bayes Framework,

R. Livni and S. Moran,

Advances of Neural Information and Processing Systems 33 (NeurIPS), 2020

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

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

Advances of Neural Information and Processing Systems 33 (NeurIPS), 2020

Prediction with Corrupted Expert Advice,

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

Advances of Neural Information and Processing Systems 33 (NeurIPS), 2020

Synthetic Data Generators: Sequential and Private,

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

Advances of Neural Information and Processing Systems 33 (NeurIPS), 2020

An Equivalence Between Private Classification and Online Prediction,

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

Best paper award

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

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

P.K Kothari and R. Livni,

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

Graph-based Discriminators: Sample Complexity and Expressiveness,

R. Livni and Y. Mansour,

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

On Communication Complexity of Classification Problems,

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

32nd Conference on Learning Theory (COLT), 2019

Private PAC Learning Implies Finite Littlestone Dimension,

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

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

Generalize Across Tasks: Efficient Algorithms for Linear Representation Learning,

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

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

Open Problem: Improper Learning of Mixtures of Gaussians,

E. Hazan and R. Livni,

31st Conference on Learning Theory (COLT), 2018

Agnostic Learning by Refuting,

P. K. Kothari, R. Livni,

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

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

T. Koren, R. Livni

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

Multi-Armed Bandits with Metric Movement Costs

T. Koren, R. Livni, Y. Mansour

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

Learning Infinite--Layer Networks: Without the Kernel Trick

R. Livni, D. Carmon, A. Globerson

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

Effective Semisupervised Learning on Manifolds

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

30th Conference on Learning Theory (COLT), 2017

Bandits with Movement Costs and Adaptive Pricing

T. Koren, R. Livni, Y. Mansour

30th Conference on Learning Theory (COLT), 2017

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

Online Learning With Low Rank Experts,

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

29th Conference on Learning Theory (COLT), 2016

Improper Deep Kernels,

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

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

Classification with Low Rank and Missing Data,

E. Hazan, R. Livni, Y. Mansour

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

On the Computational Efficiency of Training Neural Networks,

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

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

Honest Compressions and Their Application to Compression Schemes,

R. Livni and P. Simon

Best student paper

26th Conference on Learning Theory (COLT),2013

Vanishing Component Analysis,

R.Livni, D. Lehavi, S. Schein, H. Nachlieli, S Shalev-Shwartz and A. Globerson

Best paper award

30th International Conference on Machine Learning (ICML), 2013

A Simple Geometric Interpretation of SVM using Stochastic Adversaries,

R. Livni, K. Crammer and A. Globerson

15th International Conference on Artificial Intelligence and Statistics (AISTAT), 2012

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

R. Livni

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