Search Results for author: Nina Narodytska

Found 32 papers, 10 papers with code

Lemur: Integrating Large Language Models in Automated Program Verification

1 code implementation7 Oct 2023 Haoze Wu, Clark Barrett, Nina Narodytska

The demonstrated code-understanding capability of LLMs raises the question of whether they can be used for automated program verification, a task that demands high-level abstract reasoning about program properties that is challenging for verification tools.

CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems

no code implementations27 Feb 2023 Sagar Patel, Sangeetha Abdu Jyothi, Nina Narodytska

We present CrystalBox, a novel, model-agnostic, posthoc explainability framework for Deep Reinforcement Learning (DRL) controllers in the large family of input-driven environments which includes computer systems.

Continuous Control Decision Making

Provably Precise, Succinct and Efficient Explanations for Decision Trees

1 code implementation19 May 2022 Yacine Izza, Alexey Ignatiev, Nina Narodytska, Martin C. Cooper, Joao Marques-Silva

The paper proposes two logic encodings for computing smallest {\delta}-relevant sets for DTs.

Scalable Verification of GNN-based Job Schedulers

1 code implementation7 Mar 2022 Haoze Wu, Clark Barrett, Mahmood Sharif, Nina Narodytska, Gagandeep Singh

Recently, Graph Neural Networks (GNNs) have been applied for scheduling jobs over clusters, achieving better performance than hand-crafted heuristics.

Scheduling

KL Divergence Estimation with Multi-group Attribution

1 code implementation28 Feb 2022 Parikshit Gopalan, Nina Narodytska, Omer Reingold, Vatsal Sharan, Udi Wieder

Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory.

Fairness

Efficient Explanations With Relevant Sets

no code implementations1 Jun 2021 Yacine Izza, Alexey Ignatiev, Nina Narodytska, Martin C. Cooper, Joao Marques-Silva

Recent work proposed $\delta$-relevant inputs (or sets) as a probabilistic explanation for the predictions made by a classifier on a given input.

Explanations for Monotonic Classifiers

no code implementations1 Jun 2021 Joao Marques-Silva, Thomas Gerspacher, Martin Cooper, Alexey Ignatiev, Nina Narodytska

This paper describes novel algorithms for the computation of one formal explanation of a (black-box) monotonic classifier.

Constraint-Driven Explanations of Black-Box ML Models

no code implementations1 Jan 2021 Aditya Aniruddha Shrotri, Nina Narodytska, Alexey Ignatiev, Joao Marques-Silva, Kuldeep S. Meel, Moshe Vardi

Modern machine learning techniques have enjoyed widespread success, but are plagued by lack of transparency in their decision making, which has led to the emergence of the field of explainable AI.

Decision Making

On Relating "Why?" and "Why Not?" Explanations

no code implementations1 Jan 2021 Alexey Ignatiev, Nina Narodytska, Nicholas Asher, Joao Marques-Silva

Explanations of Machine Learning (ML) models often address a ‘Why?’ question.

Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay

no code implementations NeurIPS 2020 Joao Marques-Silva, Thomas Gerspacher, Martin C. Cooper, Alexey Ignatiev, Nina Narodytska

In contrast, we show that the computation of one PI-explanation for an NBC can be achieved in log-linear time, and that the same result also applies to the more general class of linear classifiers.

On Relating Explanations and Adversarial Examples

1 code implementation NeurIPS 2019 Alexey Ignatiev, Nina Narodytska, Joao Marques-Silva

The importance of explanations (XP's) of machine learning (ML) model predictions and of adversarial examples (AE's) cannot be overstated, with both arguably being essential for the practical success of ML in different settings.

Automating Cluster Management with Weave

1 code implementation6 Sep 2019 Lalith Suresh, Joao Loff, Faria Kalim, Nina Narodytska, Leonid Ryzhyk, Sahan Gamage, Brian Oki, Zeeshan Lokhandwala, Mukesh Hira, Mooly Sagiv

Modern cluster management systems like Kubernetes and Openstack grapple with hard combinatorial optimization problems: load balancing, placement, scheduling, and configuration.

Distributed, Parallel, and Cluster Computing

On Validating, Repairing and Refining Heuristic ML Explanations

1 code implementation4 Jul 2019 Alexey Ignatiev, Nina Narodytska, Joao Marques-Silva

Recent years have witnessed a fast-growing interest in computing explanations for Machine Learning (ML) models predictions.

Abduction-Based Explanations for Machine Learning Models

1 code implementation26 Nov 2018 Alexey Ignatiev, Nina Narodytska, Joao Marques-Silva

The experimental results, obtained on well-known datasets, validate the scalability of the proposed approach as well as the quality of the computed solutions.

BIG-bench Machine Learning

Deep Neural Network Approximation using Tensor Sketching

no code implementations21 Oct 2017 Shiva Prasad Kasiviswanathan, Nina Narodytska, Hongxia Jin

Deep neural networks are powerful learning models that achieve state-of-the-art performance on many computer vision, speech, and language processing tasks.

Verifying Properties of Binarized Deep Neural Networks

no code implementations19 Sep 2017 Nina Narodytska, Shiva Prasad Kasiviswanathan, Leonid Ryzhyk, Mooly Sagiv, Toby Walsh

To the best of our knowledge, this is the first work on verifying properties of deep neural networks using an exact Boolean encoding of the network.

Image Classification

Simple Black-Box Adversarial Perturbations for Deep Networks

no code implementations19 Dec 2016 Nina Narodytska, Shiva Prasad Kasiviswanathan

In this work, we focus on deep convolutional neural networks and demonstrate that adversaries can easily craft adversarial examples even without any internal knowledge of the target network.

The Computational Impact of Partial Votes on Strategic Voting

no code implementations28 May 2014 Nina Narodytska, Toby Walsh

These methods modify scoring rules (like the Borda count), elimination style rules (like single transferable vote) and rules based on the tournament graph (like Copeland) respectively.

The Complexity of Integer Bound Propagation

no code implementations16 Jan 2014 Lucas Bordeaux, George Katsirelos, Nina Narodytska, Moshe Y. Vardi

An important question is therefore whether strongly-polynomial algorithms exist that compute the common bound consistent fixpoint of a set of constraints.

Breaking Symmetry with Different Orderings

no code implementations21 Jun 2013 Nina Narodytska, Toby Walsh

We can break symmetry by eliminating solutions within each symmetry class.

How Hard Is It to Control an Election by Breaking Ties?

no code implementations23 Apr 2013 Nicholas Mattei, Nina Narodytska, Toby Walsh

Indeed, we prove that it can be NP-hard to control an election by breaking ties even with a two-stage voting rule.

Three Generalizations of the FOCUS Constraint

no code implementations22 Apr 2013 Nina Narodytska, Thierry Petit, Mohamed Siala, Toby Walsh

The FOCUS constraint expresses the notion that solutions are concentrated.

Coalitional Manipulation for Schulze's Rule

no code implementations3 Apr 2013 Serge Gaspers, Thomas Kalinowski, Nina Narodytska, Toby Walsh

Schulze's rule is used in the elections of a large number of organizations including Wikimedia and Debian.

Open-Ended Question Answering

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