Search Results for author: Ran Gilad-Bachrach

Found 18 papers, 10 papers with code

Tighter Bounds on the Information Bottleneck with Application to Deep Learning

1 code implementation12 Feb 2024 Nir Weingarten, Zohar Yakhini, Moshe Butman, Ran Gilad-Bachrach

These advancements strengthen the case for the IB and its variational approximations as a data modeling framework, and provide a simple method to significantly enhance the adversarial robustness of classifier DNNs.

Adversarial Robustness

Graph Neural Networks Use Graphs When They Shouldn't

1 code implementation8 Sep 2023 Maya Bechler-Speicher, Ido Amos, Ran Gilad-Bachrach, Amir Globerson

We analyze the implicit bias of gradient-descent learning of GNNs and prove that when the ground truth function does not use the graphs, GNNs are not guaranteed to learn a solution that ignores the graph, even with infinite data.

Graph Classification

The Case Against Explainability

no code implementations20 May 2023 Hofit Wasserman Rozen, Niva Elkin-Koren, Ran Gilad-Bachrach

Accordingly, this study carries some important policy ramifications, as it calls upon regulators and Machine Learning practitioners to reconsider the widespread pursuit of end-user Explainability and a right to explanation of AI systems.

TREE-G: Decision Trees Contesting Graph Neural Networks

1 code implementation6 Jul 2022 Maya Bechler-Speicher, Amir Globerson, Ran Gilad-Bachrach

When dealing with tabular data, models based on decision trees are a popular choice due to their high accuracy on these data types, their ease of application, and explainability properties.

 Ranked #1 on Graph Classification on HIV dataset (Accuracy metric)

Graph Classification Graph Learning +2

Inherent Inconsistencies of Feature Importance

no code implementations16 Jun 2022 Nimrod Harel, Uri Obolski, Ran Gilad-Bachrach

The rapid advancement and widespread adoption of machine learning-driven technologies have underscored the practical and ethical need for creating interpretable artificial intelligence systems.

Feature Importance

A Last Switch Dependent Analysis of Satiation and Seasonality in Bandits

1 code implementation22 Oct 2021 Pierre Laforgue, Giulia Clerici, Nicolò Cesa-Bianchi, Ran Gilad-Bachrach

Motivated by the fact that humans like some level of unpredictability or novelty, and might therefore get quickly bored when interacting with a stationary policy, we introduce a novel non-stationary bandit problem, where the expected reward of an arm is fully determined by the time elapsed since the arm last took part in a switch of actions.

Trees with Attention for Set Prediction Tasks

1 code implementation International Conference on Machine Learning 2021 Roy Hirsch, Ran Gilad-Bachrach

However, most machine learning algorithms are not designed to handle set structures and are limited to processing records of fixed size.

BIG-bench Machine Learning Interpretable Machine Learning

Robust Model Compression Using Deep Hypotheses

1 code implementation13 Mar 2021 Omri Armstrong, Ran Gilad-Bachrach

This leads to our Compact Robust Estimated Median Belief Optimization (CREMBO) algorithm for robust model compression.

Binary Classification Knowledge Distillation +1

Marginal Contribution Feature Importance -- an Axiomatic Approach for The Natural Case

1 code implementation15 Oct 2020 Amnon Catav, Boyang Fu, Jason Ernst, Sriram Sankararaman, Ran Gilad-Bachrach

While it is common to make the distinction between local scores that focus on individual predictions and global scores that look at the contribution of a feature to the model, another important division distinguishes model scenarios, in which the goal is to understand predictions of a given model from natural scenarios, in which the goal is to understand a phenomenon such as a disease.

Feature Importance

Algorithmic Copywriting: Automated Generation of Health-Related Advertisements to Improve their Performance

no code implementations27 Oct 2019 Brit Youngmann, Ran Gilad-Bachrach, Danny Karmon, Elad Yom-Tov

The marginal contribution of the generator model was, on average, 28\% lower than that of human-authored ads, while the translator model received, on average, 32\% more clicks than human-authored ads.


E-Gotsky: Sequencing Content using the Zone of Proximal Development

no code implementations28 Apr 2019 Oded Vainas, Ori Bar-Ilan, Yossi Ben-David, Ran Gilad-Bachrach, Galit Lukin, Meitar Ronen, Roi Shillo, Daniel Sitton

Vygotsky's notions of Zone of Proximal Development and Dynamic Assessment emphasize the importance of personalized learning that adapts to the needs and abilities of the learners and enables more efficient learning.

Human-Computer Interaction Computers and Society

Low Latency Privacy Preserving Inference

1 code implementation ICLR 2019 Alon Brutzkus, Oren Elisha, Ran Gilad-Bachrach

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity.

Privacy Preserving Transfer Learning

Turning Lemons into Peaches using Secure Computation

no code implementations4 Oct 2018 Stav Buchsbaum, Ran Gilad-Bachrach, Yehuda Lindell

However, we argue that in many of these situations, the problem is not the missing information but the computational challenge of obtaining it.

Computer Science and Game Theory Cryptography and Security

Modeling and Simultaneously Removing Bias via Adversarial Neural Networks

no code implementations18 Apr 2018 John Moore, Joel Pfeiffer, Kai Wei, Rishabh Iyer, Denis Charles, Ran Gilad-Bachrach, Levi Boyles, Eren Manavoglu

In real world systems, the predictions of deployed Machine Learned models affect the training data available to build subsequent models.


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}.

DART: Dropouts meet Multiple Additive Regression Trees

1 code implementation7 May 2015 K. V. Rashmi, Ran Gilad-Bachrach

Multiple Additive Regression Trees (MART), an ensemble model of boosted regression trees, is known to deliver high prediction accuracy for diverse tasks, and it is widely used in practice.


Crypto-Nets: Neural Networks over Encrypted Data

1 code implementation18 Dec 2014 Pengtao Xie, Misha Bilenko, Tom Finley, Ran Gilad-Bachrach, Kristin Lauter, Michael Naehrig

To achieve the privacy requirements, we use homomorphic encryption in the following protocol: the data owner encrypts the data and sends the ciphertexts to the third party to obtain a prediction from a trained model.

Using Multiple Samples to Learn Mixture Models

no code implementations NeurIPS 2013 Jason D. Lee, Ran Gilad-Bachrach, Rich Caruana

In the mixture models problem it is assumed that there are $K$ distributions $\theta_{1},\ldots,\theta_{K}$ and one gets to observe a sample from a mixture of these distributions with unknown coefficients.

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