Alex Damian

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 14

Top Topics

Pac Learnability

Sample Complexity

Top Venues

Publications

Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna
Computational-Statistical Gaps in Gaussian Single-Index Models (Extended Abstract). COLT (2024)
Eshaan Nichani, Alex Damian, Jason D. Lee
How Transformers Learn Causal Structure with Gradient Descent. CoRR (2024)
Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna
Computational-Statistical Gaps in Gaussian Single-Index Models. CoRR (2024)
Sadhika Malladi, Tianyu Gao, Eshaan Nichani, Alex Damian, Jason D. Lee, Danqi Chen, Sanjeev Arora
Fine-Tuning Language Models with Just Forward Passes. NeurIPS (2023)
Eshaan Nichani, Alex Damian, Jason D. Lee
Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks. NeurIPS (2023)
Alex Damian, Eshaan Nichani, Jason D. Lee
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability. ICLR (2023)
Eshaan Nichani, Alex Damian, Jason D. Lee
Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks. CoRR (2023)
Alex Damian, Eshaan Nichani, Rong Ge, Jason D. Lee
Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models. NeurIPS (2023)
Sadhika Malladi, Tianyu Gao, Eshaan Nichani, Alex Damian, Jason D. Lee, Danqi Chen, Sanjeev Arora
Fine-Tuning Language Models with Just Forward Passes. CoRR (2023)
Alex Damian, Eshaan Nichani, Rong Ge, Jason D. Lee
Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models. CoRR (2023)
Alex Damian, Eshaan Nichani, Jason D. Lee
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability. CoRR (2022)
Alex Damian, Jason D. Lee, Mahdi Soltanolkotabi
Neural Networks can Learn Representations with Gradient Descent. CoRR (2022)
Alex Damian, Tengyu Ma, Jason D. Lee
Label Noise SGD Provably Prefers Flat Global Minimizers. CoRR (2021)
Alex Damian, Tengyu Ma, Jason D. Lee
Label Noise SGD Provably Prefers Flat Global Minimizers. NeurIPS (2021)