Search Results for author: Alon Gonen

Found 14 papers, 1 papers with code

Towards a Combinatorial Characterization of Bounded-Memory Learning

no code implementations NeurIPS 2020 Alon Gonen, Shachar Lovett, Michal Moshkovitz

We propose a candidate solution for the case of realizable strong learning under a known distribution, based on the SQ dimension of neighboring distributions.

online learning

Towards a combinatorial characterization of bounded memory learning

no code implementations8 Feb 2020 Alon Gonen, Shachar Lovett, Michal Moshkovitz

In this paper we aim to develop combinatorial dimensions that characterize bounded memory learning.

online learning

Boosting Simple Learners

1 code implementation31 Jan 2020 Noga Alon, Alon Gonen, Elad Hazan, Shay Moran

(ii) Expressivity: Which tasks can be learned by boosting weak hypotheses from a bounded VC class?

Private Learning Implies Online Learning: An Efficient Reduction

no code implementations NeurIPS 2019 Alon Gonen, Elad Hazan, Shay Moran

We study the relationship between the notions of differentially private learning and online learning in games.

online learning

Learning in Non-convex Games with an Optimization Oracle

no code implementations17 Oct 2018 Naman Agarwal, Alon Gonen, Elad Hazan

We consider online learning in an adversarial, non-convex setting under the assumption that the learner has an access to an offline optimization oracle.

online learning

Optimal Sketching Bounds for Exp-concave Stochastic Minimization

no code implementations21 May 2018 Naman Agarwal, Alon Gonen

We derive optimal statistical and computational complexity bounds for exp-concave stochastic minimization in terms of the effective dimension.

Smooth Sensitivity Based Approach for Differentially Private Principal Component Analysis

no code implementations29 Oct 2017 Ran Gilad-Bachrach, Alon Gonen

The problem of designing simpler and more efficient methods for this task has been raised as an open problem in \cite{kapralov2013differentially}.

Fast Rates for Empirical Risk Minimization of Strict Saddle Problems

no code implementations16 Jan 2017 Alon Gonen, Shai Shalev-Shwartz

We derive bounds on the sample complexity of empirical risk minimization (ERM) in the context of minimizing non-convex risks that admit the strict saddle property.

Solving Ridge Regression using Sketched Preconditioned SVRG

no code implementations7 Feb 2016 Alon Gonen, Francesco Orabona, Shai Shalev-Shwartz

We develop a novel preconditioning method for ridge regression, based on recent linear sketching methods.

Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimization

no code implementations15 Jan 2016 Alon Gonen, Shai Shalev-Shwartz

We show that the average stability notion introduced by \cite{kearns1999algorithmic, bousquet2002stability} is invariant to data preconditioning, for a wide class of generalized linear models that includes most of the known exp-concave losses.

Faster SGD Using Sketched Conditioning

no code implementations8 Jun 2015 Alon Gonen, Shai Shalev-Shwartz

We propose a novel method for speeding up stochastic optimization algorithms via sketching methods, which recently became a powerful tool for accelerating algorithms for numerical linear algebra.

Stochastic Optimization

Strongly Adaptive Online Learning

no code implementations25 Feb 2015 Amit Daniely, Alon Gonen, Shai Shalev-Shwartz

Strongly adaptive algorithms are algorithms whose performance on every time interval is close to optimal.

online learning

Subspace Learning with Partial Information

no code implementations19 Feb 2014 Alon Gonen, Dan Rosenbaum, Yonina Eldar, Shai Shalev-Shwartz

The goal of subspace learning is to find a $k$-dimensional subspace of $\mathbb{R}^d$, such that the expected squared distance between instance vectors and the subspace is as small as possible.

Efficient Active Learning of Halfspaces: an Aggressive Approach

no code implementations17 Aug 2012 Alon Gonen, Sivan Sabato, Shai Shalev-Shwartz

Our efficient aggressive active learner of half-spaces has formal approximation guarantees that hold when the pool is separable with a margin.

Active Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.