1 citations · 1 across the 4 of their papers we have counts for
4 papers
Satire: Computing Rigorous Bounds for Floating-Point Rounding Error in Mixed-Precision Loop-Free Programs
Tanmay Tirpankar, Arnab Das, Ganesh Gopalakrishnan
Techniques that rigorously bound the overall rounding error exhibited by a numerical program are of significant interest for communities developing numerical software. However, the…
TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning Models
Soumick Chatterjee, Arnab Das, Chirag Mandal +7
Clinicians are often very sceptical about applying automatic image processing approaches, especially deep learning based methods, in practice. One main reason for this is the black…
An Abstraction-guided Approach to Scalable and Rigorous Floating-Point Error Analysis
Arnab Das, Ian Briggs, Ganesh Gopalakrishnan +2
Automated techniques for rigorous floating-point round-off error analysis are important in areas including formal verification of correctness and precision tuning. Existing tools a…
FPDetect: Efficient Reasoning About Stencil Programs Using Selective Direct Evaluation
Arnab Das, Sriram Krishnamoorthy, Ian Briggs +2
We present FPDetect, a low overhead approach for detecting logical errors and soft errors affecting stencil computations without generating false positives. We develop an offline a…