Matus Telgarsky
University of Illinois at Urbana-Champaign
H-index: 22
North America-United States
Top articles of Matus Telgarsky
Title | Journal | Author(s) | Publication Date |
|---|---|---|---|
Transformers, parallel computation, and logarithmic depth | arXiv preprint arXiv:2402.09268 | Clayton Sanford Daniel Hsu Matus Telgarsky | 2024/2/14 |
Representational strengths and limitations of transformers | Advances in Neural Information Processing Systems | Clayton Sanford Daniel J Hsu Matus Telgarsky | 2024/2/13 |
Spectrum Extraction and Clipping for Implicitly Linear Layers | arXiv preprint arXiv:2402.16017 | Ali Ebrahimpour Boroojeny Matus Telgarsky Hari Sundaram | 2024/2/25 |
Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency | arXiv preprint arXiv:2402.15926 | Jingfeng Wu Peter L Bartlett Matus Telgarsky Bin Yu | 2024/2/24 |
On achieving optimal adversarial test error | arXiv preprint arXiv:2306.07544 | Justin D Li Matus Telgarsky | 2023/6/13 |
Stochastic linear optimization never overfits with quadratically-bounded losses on general data | Matus Telgarsky | 2022/6/28 | |
Convex analysis at infinity: An introduction to astral space | arXiv preprint arXiv:2205.03260 | Miroslav Dudík Robert E Schapire Matus Telgarsky | 2022/5/6 |
Feature selection and low test error in shallow low-rotation ReLU networks | Matus Telgarsky | 2022/9/29 | |
Deep learning theory (DRAFT) | Matus Telgarsky | 2022/9/23 | |
Generalization bounds via distillation | arXiv preprint arXiv:2104.05641 | Daniel Hsu Ziwei Ji Matus Telgarsky Lan Wang | 2021/4/12 |
Characterizing the implicit bias via a primal-dual analysis | Ziwei Ji Matus Telgarsky | 2021/3/1 | |
Early-stopped neural networks are consistent | Advances in Neural Information Processing Systems | Ziwei Ji Justin Li Matus Telgarsky | 2021/12/6 |
Deep learning theory lecture notes | Matus Telgarsky | 2021 | |
Actor-critic is implicitly biased towards high entropy optimal policies | arXiv preprint arXiv:2110.11280 | Yuzheng Hu Ziwei Ji Matus Telgarsky | 2021/10/21 |
Fast margin maximization via dual acceleration | Ziwei Ji Nathan Srebro Matus Telgarsky | 2021/7/1 | |
Gradient descent follows the regularization path for general losses | Ziwei Ji Miroslav Dudík Robert E Schapire Matus Telgarsky | 2020/7/15 | |
Directional convergence and alignment in deep learning | Ziwei Ji Matus Telgarsky | 2020 |
Co-Authors
