research
∙
05/18/2023
Lightweight Online Learning for Sets of Related Problems in Automated Reasoning
We present Self-Driven Strategy Learning (sdsl), a lightweight online le...
share
research
∙
03/23/2023
Soy: An Efficient MILP Solver for Piecewise-Affine Systems
Piecewise-affine (PWA) systems are widely used for modeling and control ...
research
∙
03/03/2023
Convex Bounds on the Softmax Function with Applications to Robustness Verification
The softmax function is a ubiquitous component at the output of neural n...
research
∙
12/02/2022
VeriX: Towards Verified Explainability of Deep Neural Networks
We present VeriX, a first step towards verified explainability of machin...
research
∙
09/04/2022
Proof-Stitch: Proof Combination for Divide and Conquer SAT Solvers
With the increasing availability of parallel computing power, there is a...
research
∙
08/16/2022
On Optimizing Back-Substitution Methods for Neural Network Verification
With the increasing application of deep learning in mission-critical sys...
research
∙
03/19/2022
Efficient Neural Network Analysis with Sum-of-Infeasibilities
Inspired by sum-of-infeasibilities methods in convex optimization, we pr...
research
∙
03/07/2022
Scalable Verification of GNN-based Job Schedulers
Recently, Graph Neural Networks (GNNs) have been applied for scheduling ...
research
∙
03/02/2021
DeepCert: Verification of Contextually Relevant Robustness for Neural Network Image Classifiers
We introduce DeepCert, a tool-supported method for verifying the robustn...
research
∙
11/05/2020
An SMT-Based Approach for Verifying Binarized Neural Networks
Deep learning has emerged as an effective approach for creating modern s...
research
∙
10/07/2020
Global Optimization of Objective Functions Represented by ReLU Networks
Neural networks (NN) learn complex non-convex functions, making them des...
research
∙
04/17/2020
Parallelization Techniques for Verifying Neural Networks
Inspired by recent successes with parallel optimization techniques for s...
research
∙
10/29/2019
G2SAT: Learning to Generate SAT Formulas
The Boolean Satisfiability (SAT) problem is the canonical NP-complete pr...
research
∙
10/31/2017
Two Error Bounds of Imperfect Binary Search
Suppose we know that an object is in a sorted table and we want to deter...
research
∙
10/30/2017
Improve SAT-solving with Machine Learning
In this project, we aimed to improve the runtime of Minisat, a Conflict-...
research
∙
10/30/2017