Publications
Brendon G. Anderson, California Polytechnic State University
* indicates co-first author and equal contribution.
Preprints
Evolutionary games on infinite strategy sets: Convergence to Nash equilibria via dissipativity, 2023, under review
B. G. Anderson, S. Sojoudi, and M. Arcak
Towards optimal branching of linear and semidefinite relaxations for neural network robustness certification, 2023, under review
B. G. Anderson, Z. Ma, J. Li, and S. Sojoudi
Journal Papers
Improving the accuracy-robustness trade-off of classifiers via adaptive smoothing, SIAM Journal on Mathematics of Data Science (SIMODS), 2024
Second place method on RobustBench CIFAR-100 \(\ell_\infty\)-leaderboard as of May 2023
Y. Bai, B. G. Anderson, A. Kim, and S. Sojoudi
Projected randomized smoothing for certified adversarial robustness, Transactions on Machine Learning Research (TMLR), 2023
INFORMS Data Mining Best Student Paper Award runner-up
S. Pfrommer, B. G. Anderson, and S. Sojoudi
Data-driven certification of neural networks with random input noise, IEEE Transactions on Control of Network Systems (TCNS), 2022
B. G. Anderson and S. Sojoudi
Conference Papers
Approximately Gaussian replicator flows: Nonconvex optimization as a Nash-convergent evolutionary game, 63rd IEEE Conference on Decision and Control (CDC), 2024
B. G. Anderson, S. Pfrommer, and S. Sojoudi
Transport of algebraic structure to latent embeddings, International Conference on Machine Learning (ICML), 2024
Spotlight paper (top 3.5% of submissions, top 12.8% of accepted papers)
S. Pfrommer, B. G. Anderson, and S. Sojoudi
Mixing classifiers to alleviate the accuracy-robustness trade-off, 6th Annual Learning for Dynamics and Control Conference (L4DC), 2024
Y. Bai, B. G. Anderson, and S. Sojoudi
Asymmetric certified robustness via feature-convex neural networks, Neural Information Processing Systems (NeurIPS), 2023
First place in INFORMS OR/MS Tomorrow Mini-Poster Competition
S. Pfrommer*, B. G. Anderson*, J. Piet, and S. Sojoudi
Tight certified robustness via min-max representations of ReLU neural networks, 62nd IEEE Conference on Decision and Control (CDC), 2023
B. G. Anderson, S. Pfrommer, and S. Sojoudi
An overview and prospective outlook on robust training and certification of machine learning models, IFAC Symposium on System Structure and Control (SSSC), 2022
B. G. Anderson*, T. Gautam*, and S. Sojoudi
A sequential greedy approach for training implicit deep models, 61st IEEE Conference on Decision and Control (CDC), 2022
T. Gautam, B. G. Anderson, S. Sojoudi, and L. El Ghaoui
Towards optimal randomized smoothing: A semi-infinite linear programming approach, ICML Workshop on Formal Verification of Machine Learning (WFVML), 2022
One of six selected for oral presentation
B. G. Anderson, S. Pfrommer, and S. Sojoudi
Certified robustness via locally biased randomized smoothing, 4th Annual Learning for Dynamics and Control Conference (L4DC), 2022
B. G. Anderson and S. Sojoudi
Node-variant graph filters in graph neural networks, IEEE Data Science and Learning Workshop (DSLW), 2022
F. Gama, B. G. Anderson, and S. Sojoudi
Tightened convex relaxations for neural network robustness certification, 59th IEEE Conference on Decision and Control (CDC), 2020
B. G. Anderson, Z. Ma, J. Li, and S. Sojoudi
Global optimality guarantees for nonconvex unsupervised video segmentation, 57th Annual Allerton Conference on Communication, Control, and Computing, 2019
B. G. Anderson and S. Sojoudi
Quantitative assessment of robotic swarm coverage, 15th International Conference on Informatics in Control, Automation and Robotics (ICINCO), 2018
Shortlisted candidate for Best Student Paper Award
B. G. Anderson, E. Loeser, M. Gee, F. Ren, S. Biswas, O. Turanova, M. Haberland, and A. L. Bertozzi
Book Chapters
Quantifying robotic swarm coverage, Lecture Notes in Electrical Engineering (LNEE), volume 613, pp. 276–301, Springer, 2019
B. G. Anderson, E. Loeser, M. Gee, F. Ren, S. Biswas, O. Turanova, M. Haberland, and A. L. Bertozzi
|