Search Results for author: Avinatan Hassidim

Found 27 papers, 7 papers with code

Adversarial Robustness of Streaming Algorithms through Importance Sampling

no code implementations NeurIPS 2021 Vladimir Braverman, Avinatan Hassidim, Yossi Matias, Mariano Schain, Sandeep Silwal, Samson Zhou

In this paper, we introduce adversarially robust streaming algorithms for central machine learning and algorithmic tasks, such as regression and clustering, as well as their more general counterparts, subspace embedding, low-rank approximation, and coreset construction.

Adversarial Robustness

ML-based Flood Forecasting: Advances in Scale, Accuracy and Reach

no code implementations29 Nov 2020 Sella Nevo, Gal Elidan, Avinatan Hassidim, Guy Shalev, Oren Gilon, Grey Nearing, Yossi Matias

Floods are among the most common and deadly natural disasters in the world, and flood warning systems have been shown to be effective in reducing harm.

Need versus Merit: The Large Core of College Admissions Markets

no code implementations16 Oct 2020 Péter Biró, Avinatan Hassidim, Assaf Romm, Ran I. Shorrer, Sándor Sóvágó

This paper studies the set of stable allocations in college admissions markets where students can attend the same college under different financial terms.

An Optimal Elimination Algorithm for Learning a Best Arm

no code implementations NeurIPS 2020 Avinatan Hassidim, Ron Kupfer, Yaron Singer

We consider the classic problem of $(\epsilon,\delta)$-PAC learning a best arm where the goal is to identify with confidence $1-\delta$ an arm whose mean is an $\epsilon$-approximation to that of the highest mean arm in a multi-armed bandit setting.

Learning Theory PAC learning

Adversarially Robust Streaming Algorithms via Differential Privacy

no code implementations NeurIPS 2020 Avinatan Hassidim, Haim Kaplan, Yishay Mansour, Yossi Matias, Uri Stemmer

A streaming algorithm is said to be adversarially robust if its accuracy guarantees are maintained even when the data stream is chosen maliciously, by an adaptive adversary.

Adversarial Robustness

Spectral Algorithm for Low-rank Multitask Regression

no code implementations27 Oct 2019 Yotam Gigi, Ami Wiesel, Sella Nevo, Gal Elidan, Avinatan Hassidim, Yossi Matias

In this scenario sharing a low-rank component between the tasks translates to a shared spectral reflection of the water, which is a true underlying physical model.

Image Classification

LSH Microbatches for Stochastic Gradients: Value in Rearrangement

no code implementations ICLR 2019 Eliav Buchnik, Edith Cohen, Avinatan Hassidim, Yossi Matias

We make a principled argument for the properties of our arrangements that accelerate the training and present efficient algorithms to generate microbatches that respect the marginal distribution of training examples.

Learning to Screen

no code implementations NeurIPS 2019 Alon Cohen, Avinatan Hassidim, Haim Kaplan, Yishay Mansour, Shay Moran

(ii) In the second variant it is assumed that before the process starts, the algorithm has an access to a training set of $n$ items drawn independently from the same unknown distribution (e. g.\ data of candidates from previous recruitment seasons).

ML for Flood Forecasting at Scale

no code implementations28 Jan 2019 Sella Nevo, Vova Anisimov, Gal Elidan, Ran El-Yaniv, Pete Giencke, Yotam Gigi, Avinatan Hassidim, Zach Moshe, Mor Schlesinger, Guy Shalev, Ajai Tirumali, Ami Wiesel, Oleg Zlydenko, Yossi Matias

We propose to build on these strengths and develop ML systems for timely and accurate riverine flood prediction.

Towards Global Remote Discharge Estimation: Using the Few to Estimate The Many

no code implementations3 Jan 2019 Yotam Gigi, Gal Elidan, Avinatan Hassidim, Yossi Matias, Zach Moshe, Sella Nevo, Guy Shalev, Ami Wiesel

We demonstrate the efficacy of our approach for the problem of discharge estimation using simulations.

Optimization for Approximate Submodularity

no code implementations NeurIPS 2018 Yaron Singer, Avinatan Hassidim

We consider the problem of maximizing a submodular function when given access to its approximate version.

Online Linear Quadratic Control

no code implementations ICML 2018 Alon Cohen, Avinatan Hassidim, Tomer Koren, Nevena Lazic, Yishay Mansour, Kunal Talwar

We study the problem of controlling linear time-invariant systems with known noisy dynamics and adversarially chosen quadratic losses.

online learning

Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation

5 code implementations10 Apr 2018 Ariel Ephrat, Inbar Mosseri, Oran Lang, Tali Dekel, Kevin Wilson, Avinatan Hassidim, William T. Freeman, Michael Rubinstein

Solving this task using only audio as input is extremely challenging and does not provide an association of the separated speech signals with speakers in the video.

Speech Separation

Self-Similar Epochs: Value in Arrangement

no code implementations ICLR 2019 Eliav Buchnik, Edith Cohen, Avinatan Hassidim, Yossi Matias

Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples.

MUDA: A Truthful Multi-Unit Double-Auction Mechanism

2 code implementations19 Dec 2017 Erel Segal-haLevi, Avinatan Hassidim, Yonatan Aumann

In a seminal paper, McAfee (1992) presented a truthful mechanism for double auctions, attaining asymptotically-optimal gain-from-trade without any prior information on the valuations of the traders.

Computer Science and Game Theory

Robust Guarantees of Stochastic Greedy Algorithms

no code implementations ICML 2017 Avinatan Hassidim, Yaron Singer

In this paper we analyze the robustness of stochastic variants of the greedy algorithm for submodular maximization.

Fair Allocation based on Diminishing Differences

1 code implementation22 May 2017 Erel Segal-haLevi, Haris Aziz, Avinatan Hassidim

We give a full characterization of allocations that are necessarily-proportional or possibly-proportional according to this assumption.

Computer Science and Game Theory

Submodular Optimization under Noise

no code implementations12 Jan 2016 Avinatan Hassidim, Yaron Singer

We provide initial answers, by focusing on the question of maximizing a monotone submodular function under a cardinality constraint when given access to a noisy oracle of the function.

Quantum algorithm for solving linear systems of equations

3 code implementations19 Nov 2008 Aram W. Harrow, Avinatan Hassidim, Seth Lloyd

Solving linear systems of equations is a common problem that arises both on its own and as a subroutine in more complex problems: given a matrix A and a vector b, find a vector x such that Ax=b.

Quantum Physics

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