Elvis Dohmatob, PhD

• Trustworthy AI/ML (algorithmic bias, adversarial robustness, out-of-distribution generalization, etc.),
• Learning Theory (neural scaling laws, model collapse, etc.),
• Neural Networks (attention, associative memories, etc.),
• Representation Learning,
• Optimization (convex, discrete, etc.)

2024

• E. Dohmatob, Y. Feng, P. Yang, F. Charton, J. Kempe, "A Tale of Tails: Model Collapse as a Change of Scaling Laws", In International Conference on Machine Learning (ICML), volume 235 of Proceedings of Machine Learning Research, 2024
• E. Dohmatob, Y. Feng, J. Kempe, "Model Collapse Demystified: The Case of Regression",  In Advances in Neural Information Processing Systems (NeurIPS), volume 37, 2024
• V. Cabannes, E. Dohmatob, A. Bietti, "Scaling Laws for Associative Memories",  In The Twelfth International Conference on Learning Representations (ICLR), 2024
• E. Dohmatob, M. Scetbon, "Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms", In International Conference on Machine Learning (ICML), volume 235 of Proceedings of Machine Learning Research, 2024
• E. Dohmatob, "Consistent Adversarially Robust Linear Classification: Non-Parametric Setting", In International Conference on Machine Learning (ICML), volume 235 of Proceedings of Machine Learning Research, 2024
• E. Dohmatob, Y. Feng, A. Subramonian, J. Kempe, "Strong Model Collapse", ArXiv preprint
• A. Subramonian, S. Bell, L. Sagun, E. Dohmatob, "An Effective Theory of Bias Amplification", ArXiv preprint
• Y. Feng, E. Dohmatob, P. Yang, F. Charton, J. Kempe, "Beyond Model Collapse: Scaling Up with Synthesized Data Requires Reinforcement", ArXiv preprint

Complete List

• DBLP
• Google Scholar