Shai Shalev-Shwartz

research

∙ 02/13/2023

SubTuning: Efficient Finetuning for Multi-Task Learning

Finetuning a pretrained model has become a standard approach for trainin...

0 Gal Kaplun, et al. ∙

research

∙ 05/01/2022

MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning

Huge language models (LMs) have ushered in a new era for AI, serving as ...

6 Ehud Karpas, et al. ∙

research

∙ 03/28/2022

Knowledge Distillation: Bad Models Can Be Good Role Models

Large neural networks trained in the overparameterized regime are able t...

0 Gal Kaplun, et al. ∙

research

∙ 01/31/2021

The Connection Between Approximation, Depth Separation and Learnability in Neural Networks

Several recent works have shown separation results between deep neural n...

0 Eran Malach, et al. ∙

research

∙ 10/03/2020

Computational Separation Between Convolutional and Fully-Connected Networks

Convolutional neural networks (CNN) exhibit unmatched performance in a m...

9 Eran Malach, et al. ∙

research

∙ 08/18/2020

When Hardness of Approximation Meets Hardness of Learning

A supervised learning algorithm has access to a distribution of labeled ...

11 Eran Malach, et al. ∙

research

∙ 02/03/2020

Proving the Lottery Ticket Hypothesis: Pruning is All You Need

The lottery ticket hypothesis (Frankle and Carbin, 2018), states that a ...

7 Eran Malach, et al. ∙

research

∙ 10/25/2019

Learning Boolean Circuits with Neural Networks

Training neural-networks is computationally hard. However, in practice t...

0 Eran Malach, et al. ∙

research

∙ 09/26/2019

The Implicit Bias of Depth: How Incremental Learning Drives Generalization

A leading hypothesis for the surprising generalization of neural network...

0 Daniel Gissin, et al. ∙

research

∙ 08/15/2019

SenseBERT: Driving Some Sense into BERT

Self-supervision techniques have allowed neural language models to advan...

0 Yoav Levine, et al. ∙

research

∙ 07/15/2019

Discriminative Active Learning

We propose a new batch mode active learning algorithm designed for neura...

6 Daniel Gissin, et al. ∙

research

∙ 06/12/2019

Decoupling Gating from Linearity

ReLU neural-networks have been in the focus of many recent theoretical w...

0 Jonathan Fiat, et al. ∙

research

∙ 03/08/2019

Is Deeper Better only when Shallow is Good?

Understanding the power of depth in feed-forward neural networks is an o...

0 Eran Malach, et al. ∙

research

∙ 12/09/2018

Vision Zero: on a Provable Method for Eliminating Roadway Accidents without Compromising Traffic Throughput

We propose an economical, viable, approach to eliminate almost all car a...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 03/26/2018

A Provably Correct Algorithm for Deep Learning that Actually Works

We describe a layer-by-layer algorithm for training deep convolutional n...

0 Eran Malach, et al. ∙

research

∙ 08/21/2017

On a Formal Model of Safe and Scalable Self-driving Cars

In recent years, car makers and tech companies have been racing towards ...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 03/23/2017

Failures of Gradient-Based Deep Learning

In recent years, Deep Learning has become the go-to solution for a broad...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 10/11/2016

Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving

Autonomous driving is a multi-agent setting where the host vehicle must ...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 05/24/2016

Learning a Metric Embedding for Face Recognition using the Multibatch Method

This work is motivated by the engineering task of achieving a near state...

0 Oren Tadmor, et al. ∙

research

∙ 11/13/2014

SelfieBoost: A Boosting Algorithm for Deep Learning

We describe and analyze a new boosting algorithm for deep learning calle...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 10/05/2014

On the Computational Efficiency of Training Neural Networks

It is well-known that neural networks are computationally hard to train....

0 Roi Livni, et al. ∙

research

∙ 02/19/2014

Subspace Learning with Partial Information

The goal of subspace learning is to find a k-dimensional subspace of R^d...

0 Alon Gonen, et al. ∙

research

∙ 09/10/2013

Accelerated Proximal Stochastic Dual Coordinate Ascent for Regularized Loss Minimization

We introduce a proximal version of the stochastic dual coordinate ascent...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 05/12/2013

Accelerated Mini-Batch Stochastic Dual Coordinate Ascent

Stochastic dual coordinate ascent (SDCA) is an effective technique for s...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 04/26/2013

An Algorithm for Training Polynomial Networks

We consider deep neural networks, in which the output of each node is a ...

0 Roi Livni, et al. ∙

research

∙ 12/13/2012

Learning Sparse Low-Threshold Linear Classifiers

We consider the problem of learning a non-negative linear classifier wit...

0 Sivan Sabato, et al. ∙

research

∙ 11/12/2012

Proximal Stochastic Dual Coordinate Ascent

We introduce a proximal version of dual coordinate ascent method. We dem...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 09/10/2012

Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization

Stochastic Gradient Descent (SGD) has become popular for solving large s...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 06/18/2012

Learning the Experts for Online Sequence Prediction

Online sequence prediction is the problem of predicting the next element...

0 Elad Eban, et al. ∙

research

∙ 12/07/2011

Active Learning of Halfspaces under a Margin Assumption

We derive and analyze a new, efficient, pool-based active learning algor...

0 Alon Gonen, et al. ∙

research

∙ 09/05/2011

ShareBoost: Efficient Multiclass Learning with Feature Sharing

Multiclass prediction is the problem of classifying an object into a rel...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 06/08/2011

Large-Scale Convex Minimization with a Low-Rank Constraint

We address the problem of minimizing a convex function over the space of...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 06/06/2011

Using More Data to Speed-up Training Time

In many recent applications, data is plentiful. By now, we have a rather...

0 Shai Shalev-Shwartz, et al. ∙

research

∙ 10/04/2009

Regularization Techniques for Learning with Matrices

There is growing body of learning problems for which it is natural to or...

0 Sham M. Kakade, et al. ∙

Shai Shalev-Shwartz

Featured Co-authors