Search Results for author: Vijay Ganesh

Found 15 papers, 5 papers with code

Online Bayesian Moment Matching based SAT Solver Heuristics

no code implementations ICML 2020 Haonan Duan, Saeed Nejati, George Trimponias, Pascal Poupart, Vijay Ganesh

Our solvers out-perform the baselines by solving 12 more instances from the SAT competition 2018 application benchmark and are %40 faster on average in solving hard cryptographic instances.

A Solver + Gradient Descent Training Algorithm for Deep Neural Networks

no code implementations7 Jul 2022 Dhananjay Ashok, Vineel Nagisetty, Christopher Srinivasa, Vijay Ganesh

We present a novel hybrid algorithm for training Deep Neural Networks that combines the state-of-the-art Gradient Descent (GD) method with a Mixed Integer Linear Programming (MILP) solver, outperforming GD and variants in terms of accuracy, as well as resource and data efficiency for both regression and classification tasks.

regression

String Theories involving Regular Membership Predicates: From Practice to Theory and Back

no code implementations15 May 2021 Murphy Berzish, Joel D. Day, Vijay Ganesh, Mitja Kulczynski, Florin Manea, Federico Mora, Dirk Nowotka

Designing an algorithm for the (generally undecidable) satisfiability problem for systems of string constraints requires a thorough understanding of the structure of constraints present in the targeted cases.

A SAT-based Resolution of Lam's Problem

1 code implementation8 Dec 2020 Curtis Bright, Kevin K. H. Cheung, Brett Stevens, Ilias Kotsireas, Vijay Ganesh

In 1989, computer searches by Lam, Thiel, and Swiercz experimentally resolved Lam's problem from projective geometry$\unicode{x2014}$the long-standing problem of determining if a projective plane of order ten exists.

Logic Guided Genetic Algorithms

no code implementations21 Oct 2020 Dhananjay Ashok, Joseph Scott, Sebastian Wetzel, Maysum Panju, Vijay Ganesh

Our method, logic-guided genetic algorithm (LGGA), takes as input a set of labelled data points and auxiliary truths (ATs) (mathematical facts known a priori about the unknown function the regressor aims to learn) and outputs a specially generated and curated dataset that can be used with any SR method.

Data Augmentation Symbolic Regression

Amnesiac Machine Learning

no code implementations21 Oct 2020 Laura Graves, Vineel Nagisetty, Vijay Ganesh

In this paper, we present two efficient methods that address this question of how a model owner or data holder may delete personal data from models in such a way that they may not be vulnerable to model inversion and membership inference attacks while maintaining model efficacy.

BIG-bench Machine Learning

LGML: Logic Guided Machine Learning

no code implementations5 Jun 2020 Joseph Scott, Maysum Panju, Vijay Ganesh

We introduce Logic Guided Machine Learning (LGML), a novel approach that symbiotically combines machine learning (ML) and logic solvers with the goal of learning mathematical functions from data.

BIG-bench Machine Learning

Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks

no code implementations9 Mar 2020 Sebastian J. Wetzel, Roger G. Melko, Joseph Scott, Maysum Panju, Vijay Ganesh

It turns out that in the process of learning which datapoints belong to the same event or field configuration, these SNNs also learn the relevant symmetry invariants and conserved quantities.

xAI-GAN: Enhancing Generative Adversarial Networks via Explainable AI Systems

1 code implementation24 Feb 2020 Vineel Nagisetty, Laura Graves, Joseph Scott, Vijay Ganesh

A potential weakness in GANs is that it requires a lot of data for successful training and data collection can be an expensive process.

MPro: Combining Static and Symbolic Analysis for Scalable Testing of Smart Contract

1 code implementation1 Nov 2019 William Zhang, Sebastian Banescu, Leodardo Pasos, Steven Stewart, Vijay Ganesh

We have implemented our technique in a tool called MPro, a scalable and automated smart contract analyzer based on the existing symbolic analysis tool Mythril-Classic and the static analysis tool Slither.

Cryptography and Security

An Empirical Investigation of Randomized Defenses against Adversarial Attacks

1 code implementation12 Sep 2019 Yannik Potdevin, Dirk Nowotka, Vijay Ganesh

In this paper, we propose a scientific evaluation methodology aimed at assessing the quality, efficacy, robustness and efficiency of randomized defenses to protect DNNs against adversarial examples.

Adversarial Attack General Classification +1

SAT Solvers and Computer Algebra Systems: A Powerful Combination for Mathematics

no code implementations9 Jul 2019 Curtis Bright, Ilias Kotsireas, Vijay Ganesh

By combining the search power of SAT with the deep mathematical knowledge in CASs we can solve many problems in mathematics that no other known methods seem capable of solving.

Mathematical Proofs Mathematical Reasoning

Effective problem solving using SAT solvers

no code implementations14 Jun 2019 Curtis Bright, Jürgen Gerhard, Ilias Kotsireas, Vijay Ganesh

In this article we demonstrate how to solve a variety of problems and puzzles using the built-in SAT solver of the computer algebra system Maple.

Relating Complexity-theoretic Parameters with SAT Solver Performance

no code implementations26 Jun 2017 Edward Zulkoski, Ruben Martins, Christoph Wintersteiger, Robert Robere, Jia Liang, Krzysztof Czarnecki, Vijay Ganesh

Over the years complexity theorists have proposed many structural parameters to explain the surprising efficiency of conflict-driven clause-learning (CDCL) SAT solvers on a wide variety of large industrial Boolean instances.

SAT-based Analysis of Large Real-world Feature Models is Easy

1 code implementation17 Jun 2015 Jia Hui Liang, Vijay Ganesh, Venkatesh Raman, Krzysztof Czarnecki

We discovered that a key reason why large real-world FMs are easy-to-analyze is that the vast majority of the variables in these models are unrestricted, i. e., the models are satisfiable for both true and false assignments to such variables under the current partial assignment.

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